Language Modeling & Dialog Systems 2017


Notes:

A statistical language model (SLM) is a probability distribution P(s) over strings S that attempts to reflect how frequently a string S occurs as a sentence.

Langauge modeling may be spelled with one “L” or two “LL” (language modelling).

  • Anonymized language modeling
  • Attention-based language models
  • Bidirectional language modeling
  • Character-level language modeling
  • Contextual language modeling
  • Deep neural language model
  • Discourse language modeling
  • Hierarchical-rnn-based language modeling
  • LSTM language models
  • LSTM-based language models
  • LVCSR language modeling
  • Low-resource language modelling
  • M-gram language modeling
  • Natural language modelling
  • Neural language model
  • Online language modeling
  • Personalized language modeling
  • Phonotactic language modeling
  • Pitman-yor language modeling
  • Probabilistic language modeling
  • Recurrent neural network language modeling
  • Recurrent-neural-network-based language model
  • RNN language models
  • RNN based language modeling
  • Self-organized language modeling
  • Spoken language modeling
  • Statistical language modeling
  • Stochastic language modelling
  • Syntactic language modeling
  • Syntactico-statistical language modeling
  • Turn-based language modeling

Resources:

Wikipedia:

See also:

OpenOME (Organization Modelling Environment)Rule-based Language Modeling | Tool for Agent Oriented Modeling for Eclipse (TAOM4E)


A Hierarchical Latent Variable Encoder-Decoder Model for Generating Dialogues.
IV Serban, A Sordoni, R Lowe, L Charlin, J Pineau… – AAAI, 2017 – aaai.org
… 2016), language modelling (Graves 2012; Mikolov and others 2010) machine translation (Sutskever, Vinyals, and Le 2014; Cho and others 2014 … Such models are not specifically designed for the goal-oriented setting, in which dialogue systems were originally developed (Gorin …

Adversarial learning for neural dialogue generation
J Li, W Monroe, T Shi, A Ritter, D Jurafsky – arXiv preprint arXiv …, 2017 – arxiv.org
… than its se- quence outputs. Such a strategy makes the system differentiable and achieves promising results in tasks like character-level language modeling and handwriting generation. Yu et al. (2016a) use pol- icy gradient …

Training end-to-end dialogue systems with the ubuntu dialogue corpus
RT Lowe, N Pow, IV Serban, L Charlin… – Dialogue & …, 2017 – dad.uni-bielefeld.de
… doi: 10.5087/dad.2017.102 Training End-to-End Dialogue Systems with the … As a result of this analysis, we suggest some promising directions for future research on the Ubuntu Dialogue Corpus, which can also be applied to end-to-end dialogue systems in general …

Coherent Dialogue with Attention-Based Language Models.
H Mei, M Bansal, MR Walter – AAAI, 2017 – aaai.org
… Introduction Automatic conversational models (Winograd 1971), also known as dialogue systems, are of great importance to a large variety of applications, ranging from open-domain en- tertaining chatbots to goal-oriented technical support agents …

A copy-augmented sequence-to-sequence architecture gives good performance on task-oriented dialogue
M Eric, CD Manning – arXiv preprint arXiv:1701.04024, 2017 – arxiv.org
… maximizing the log-likelihood. An effective task-oriented dialogue system must have powerful language modelling capabilities and be able to pick up on relevant entities of an underlying knowledge base. We augment the at …

Generative encoder-decoder models for task-oriented spoken dialog systems with chatting capability
T Zhao, A Lu, K Lee, M Eskenazi – arXiv preprint arXiv:1706.08476, 2017 – arxiv.org
… Task-oriented spoken dialog systems have trans- formed human-computer interaction by enabling people interact with computers via spoken lan … on learning the reasoning process of task-oriented di- alogs instead of leveraging too much information from the language modeling …

Neural networks for information retrieval
T Kenter, A Borisov, C Van Gysel, M Dehghani… – arXiv preprint arXiv …, 2017 – arxiv.org
… applied to all key parts of the typical modern IR pipeline, such core ranking algorithms [26, 42, 51], click models [9, 10], knowledge graphs [8, 35], text similarity [28, 47], entity retrieval [52, 53], language modeling [5], question answering [22, 56], and dialogue systems [34, 54] …

A deep reinforced model for abstractive summarization
R Paulus, C Xiong, R Socher – arXiv preprint arXiv:1705.04304, 2017 – arxiv.org
… The goal of this weight-sharing is to use the syntactic and semantic information contained in the embedding matrix to improve the token- generation function. Similar weight-sharing meth- ods have been applied to language modeling (Inan et al., 2016; Press and Wolf, 2016) …

Maximum-likelihood augmented discrete generative adversarial networks
T Che, Y Li, R Zhang, RD Hjelm, W Li, Y Song… – arXiv preprint arXiv …, 2017 – arxiv.org
… 4. Experiments To examine the effectiveness of the proposed algorithms, we conduct experiments on three discrete sequence genera- tion tasks. We achieve promising results on all three tasks, including a standard and challenging language modeling task …

Towards SamiTalk: a Sami-speaking robot linked to Sami Wikipedia
G Wilcock, N Laxström, J Leinonen, P Smit… – Dialogues with Social …, 2017 – Springer
… A number of major issues in internationalisation and localisation of spoken dialogue systems are discussed by [5], using WikiTalk as an example … For language modelling a varigram model created with VariKN toolkit 4 [13] is used …

Affect-lm: A neural language model for customizable affective text generation
S Ghosh, M Chollet, E Laksana, LP Morency… – arXiv preprint arXiv …, 2017 – arxiv.org
… The automated processing of affect in human verbal communication is of great importance to understanding spoken language sys- tems, particularly for emerging applications such as dialogue systems and conversational agents. Statistical language modeling is an integral …

Recent trends in deep learning based natural language processing
T Young, D Hazarika, S Poria, E Cambria – arXiv preprint arXiv …, 2017 – arxiv.org
… of natural language related tasks at all levels, ranging from parsing and part-of-speech (POS) tagging, to machine translation and dialog systems … This template is naturally suited for many NLP tasks such as language modeling (Mikolov et al., 2010, 2011; Sutskever et al., 2011 …

Neural personalized response generation as domain adaptation
W Zhang, T Liu, Y Wang, Q Zhu – arXiv preprint arXiv:1701.02073, 2017 – arxiv.org
… Task-oriented Dialogue Generation The most successful research on the task-oriented dialogue system is mainly based on the partially observed Markov decision process (POMDP) [34]. The task oriented dialogue system mainly focuses on the dialogue state tracking, ac …

Key-Value Retrieval Networks for Task-Oriented Dialogue
M Eric, CD Manning – arXiv preprint arXiv:1705.05414, 2017 – arxiv.org
… BLEU: We use the BLEU metric, commonly employed in evaluating machine translation systems (Papineni et al., 2002), which has also been used in past literature for evaluating dialogue systems (Ritter et al., 2011 … is known to have very robust language modelling capabilities …

A theoretical framework for conversational search
F Radlinski, N Craswell – Proceedings of the 2017 Conference on …, 2017 – dl.acm.org
… free-form queries and critiques, the information retrieval system could build its models based on the language modeling approach to … 2.2 Spoken Dialog Systems Spoken dialog system research enables a flexible conversation to take place including corrections and clarifications …

Controlling linguistic style aspects in neural language generation
J Ficler, Y Goldberg – arXiv preprint arXiv:1707.02633, 2017 – arxiv.org
… 5.1 Conditioned vs. Unconditioned Our model is a language model that is conditioned on various parameters. As a sanity check, we ver- ify that knowing the parameters indeed helps in achieving better language modeling results …

Adversarial generation of natural language
S Rajeswar, S Subramanian, F Dutil, C Pal… – arXiv preprint arXiv …, 2017 – arxiv.org
… A dataset com- prising simple English sentences3 which we will henceforth refer to as CMU?SE, the version of the Penn Treebank commonly used in language modeling experiments (Zaremba et al., 2014) and the Google 1-billion word dataset (Chelba et al …

Sequence-to-sequence models for punctuated transcription combining lexical and acoustic features
O Klejch, P Bell, S Renals – Acoustics, Speech and Signal …, 2017 – ieeexplore.ieee.org
… Since the language modelling data is much larger than the data used in this paper, we also show results for a lexical system trained on the same amount of … 3] I. V Serban, A. Sordoni, Y. Bengio, A. Courville, and J. Pineau, “Building end-to-end dialogue systems using generative …

Deconvolutional paragraph representation learning
Y Zhang, D Shen, G Wang, Z Gan… – Advances in Neural …, 2017 – papers.nips.cc
… step toward more applied tasks, such as sentiment analysis [1, 2, 3, 4], machine translation [5, 6, 7], dialogue systems [8, 9, 10 … between deconvolutional and RNN Decoders The proposed framework can be seen as a complementary building block for natural language modeling …

Evidence and interpretation in language learning research: Opportunities for collaboration with computational linguistics
D Meurers, M Dickinson – Language Learning, 2017 – Wiley Online Library
… Petersen ([65]) created a dialogue system offering information gap activities and used it to examine the developmental effects of recast-intensive interaction on English as a second language (ESL) question formation and morphosyntactic accuracy …

Exploring neural text simplification models
S Nisioi, S Štajner, SP Ponzetto, LP Dinu – … of the 55th Annual Meeting of …, 2017 – aclweb.org
… Neural sequence to sequence models have been successfully used in many applications (Graves, 2012), from speech and signal processing to text processing or dialogue systems (Serban et al., 2015 … Improving text simplification language modeling using unsimplified text data …

Toward abstraction from multi-modal data: empirical studies on multiple time-scale recurrent models
J Zhong, A Cangelosi, T Ogata – Neural Networks (IJCNN) …, 2017 – ieeexplore.ieee.org
… it was designed, it has achieved satisfaction results in competitions [7] as well as tasks such as dialogue system [8], sentiment … Furthermore, according to the previous literature with natural language modelling, the gated mechanisms RNN would be necessary to model the long …

Iterative policy learning in end-to-end trainable task-oriented neural dialog models
B Liu, I Lane – arXiv preprint arXiv:1709.06136, 2017 – arxiv.org
… [7] Steve Young, Milica Gašic, Blaise Thomson, and Ja- son D Williams, “Pomdp-based statistical spoken dialog systems: A review,” Proceedings of the IEEE, vol … [11] Bing Liu and Ian Lane, “Joint online spoken language understanding and language modeling with recurrent …

Morph-fitting: Fine-tuning word vector spaces with simple language-specific rules
I Vuli?, N Mrkši?, R Reichart, DÓ Séaghdha… – arXiv preprint arXiv …, 2017 – arxiv.org
… 2Representation models that do not distinguish between synonyms and antonyms may have grave implications in down- stream language understanding applications such as spoken dialogue systems: a user looking for ‘an affordable Chinese restaurant in west Cambridge …

Sequence to Sequence Modeling for User Simulation in Dialog Systems
P Crook, A Marin – Proceedings of the 18th Annual Conference of …, 2017 – isca-speech.org
… Baseline: LM-based simulator As baseline, we use a natural language simulator built using language modelling techniques. LM-based user simulators are a popular approach for building simulated users, in particular for dialog system evaluation tasks [4]. A common approach …

Definition Modeling: Learning to Define Word Embeddings in Natural Language.
T Noraset, C Liang, L Birnbaum, D Downey – AAAI, 2017 – aaai.org
… train the definition model. DM is a special case of language modeling, and as in lan- guage modeling the performance of a definition model can be measured by using the perplexity of a test corpus. Lower perplexity suggests …

Revisiting Activation Regularization for Language RNNs
S Merity, B McCann, R Socher – arXiv preprint arXiv:1708.01009, 2017 – arxiv.org
… Tying Word Vectors and Word Classifiers: A Loss Framework for Language Modeling. arXiv preprint arXiv:1611.01462, 2016 … Semanti- cally Conditioned LSTM-based Natural Language Gen- eration for Spoken Dialogue Systems. arXiv preprint arXiv:1508.01745, 2015 …

Sequential Dialogue Context Modeling for Spoken Language Understanding
A Bapna, G Tur, D Hakkani-Tur, L Heck – Proceedings of the 18th …, 2017 – aclweb.org
… Joint model- ing of intent classification and language modeling showed promising improvements in intent recog- nition, especially in the … 2016) show improved performance on an informational dialogue agent by incorporating knowledge base context into their dialogue system …

Label-dependencies aware recurrent neural networks
Y Dupont, M Dinarelli, I Tellier – arXiv preprint arXiv:1706.01740, 2017 – arxiv.org
… However [5] has shown that RNNs for language modeling learn best with only N = 5 previous steps … 10 Page 11. The ATIS corpus (Air Travel Information System) [26] was collected for building a spoken dialog system able to provide flight information in the United States …

Natural language processing
K Sirts – 2017 – courses.cs.ut.ee
… Natural language generation • Text summarization • Dialog systems 23 Page 24. The general plan • A matrix of tasks and methods Tasks Classical Feature-?based Neural networks Language modeling Ngram model Maximum entropy model Recurrent neural networks Parsing …

A first look into a Convolutional Neural Network for speech emotion detection
D Bertero, P Fung – Acoustics, Speech and Signal Processing …, 2017 – ieeexplore.ieee.org
… Bertero and Pascale Fung, “Towards a corpus of speech emotion for interactive dialog systems,” Oriental COCOSDA, 2016. [18] Anthony Rousseau, Paul Deléglise, and Yannick Est`eve, “Enhancing the TED-LIUM corpus with selected data for language modeling and more …

Semi-supervised Learning with Semantic Knowledge Extraction for Improved Speech Recognition in Air Traffic Control
A Srinivasamurthy, P Motlicek… – … of Interspeech 2017, 2017 – infoscience.epfl.ch
… 534– 545, 2005. [14] SS Pradhan and WH Ward, “Estimating semantic confidence for spoken dialogue systems,” in Proc … [20] A. Rousseau, P. Deléglise, and Y. Estève, “Enhancing the TED- LIUM Corpus with Selected Data for Language Modeling and More TED Talks,” in Proc …

Hybrid methodological approach to context-dependent speech recognition
D Miškovi?, M Gnjatovi?, P Štrbac… – International …, 2017 – journals.sagepub.com
Although the importance of contextual information in speech recognition has been acknowledged for a long time now, it has remained clearly underutilized even in…

Navigation-orientated natural spoken language understanding for intelligent vehicle dialogue
Y Zheng, Y Liu, JHL Hansen – Intelligent Vehicles Symposium …, 2017 – ieeexplore.ieee.org
… A. Word Dictionary Since this speech interface is designed for a navigation- orientated dialogue system, the word dictionary is a … Deep learning has been successfully applied to a number of human language technology areas including language modeling [23, 24], especially …

Dialog State Tracking Challenge 6 End-to-End Goal-Oriented Dialog Track
YL Boureau, A Bordes, J Perez – 2017 – workshop.colips.org
… Goal-oriented dialog requires skills that go beyond language modeling, eg, asking questions to clearly define a user request, querying Knowledge … However, because end-to-end dialog systems make no assumption on the domain or dialog state structure, they are holding the …

Towards an autarkic embedded cognitive user interface
F Duckhorn, M Huber, W Meyer… – Proc …, 2017 – pdfs.semanticscholar.org
… 1. Introduction Recent speech dialog systems and cognitive user interfaces al- low natural verbal human-machine-interaction and achieve an excellent performance … 2 – and related to language modelling, whereas [7] defines several operations on FVRs …

Two-stage multi-intent detection for spoken language understanding
B Kim, S Ryu, GG Lee – Multimedia Tools and Applications, 2017 – Springer
… Ronald R (1996) A maximum entropy approach to adaptive statistical language modeling. Comput Speech Lang 10:187–228CrossRefGoogle Scholar. 16 … Seo H (2013) Multiple user intent understanding for spoken dialog system. MS Thesis, POSTECHGoogle Scholar. 18 …

Significance of neural phonotactic models for large-scale spoken language identification
BML Srivastava, H Vydana, AK Vuppala… – … Joint Conference on, 2017 – ieeexplore.ieee.org
… a vital module for a wide range of multilingual applications like, call centers, multilingual spoken dialog systems, emergency services … language independent phone recognizer to generate the phone sequences from raw signal and two different language modeling ap- proaches …

Modelling semantic context of oov words in large vocabulary continuous speech recognition
I Sheikh, D Fohr, I Illina… – IEEE/ACM Transactions on …, 2017 – ieeexplore.ieee.org
Page 1. 598 IEEE/ACM TRANSACTIONS ON AUDIO, SPEECH, AND LANGUAGE PROCESSING, VOL. 25, NO. 3, MARCH 2017 Modelling Semantic Context of OOV Words in Large Vocabulary Continuous Speech Recognition …

Investigating Scalability in Hierarchical Language Identification System
S Irtza, V Sethu, E Ambikairajah, H Li – Proc. Interspeech 2017, 2017 – isca-speech.org
… the research community to be used as an auxiliary technology for many applications eg speech recognition and dialogue systems [1, 2 … to expand this framework to include new target languages/dialects, the TV space, i- vector extraction and language modelling modules require …

A Context-Aware Speech recognition and Understanding System for Air Traffic Control Domain
Y Oualil, D Klakow, G Szaszák… – in IEEE Automatic …, 2017 – publications.idiap.ch
… [5] proposed a dialogue system for gyms … [12] Martin Sundermeyer, Ralf Schlüter, and Hermann Ney, “LSTM neural networks for language modeling,” in 13th An- nual Conference of the International Speech Communication Association (INTERSPEECH), Portland, OR, USA, Sep …

Phoneme Set Design Based on Integrated Acoustic and Linguistic Features for Second Language Speech Recognition
X Wang, T Kato, S Yamamoto – IEICE TRANSACTIONS on …, 2017 – search.ieice.org
… or incorrect gram- mar [7]. More problematic is when non-native pronuncia- tions become an issue for spoken dialogue systems that tar- get … modeling [8], [10], [11], lexical modeling [12] and extended lexicon [9], and grammatical relations in terms of language modeling [13] for …

Edina: Building an Open Domain Socialbot with Self-dialogues
B Krause, M Damonte, M Dobre, D Duma… – arXiv preprint arXiv …, 2017 – arxiv.org
… Our focus on data collection stems from the scarcity of publicly available corpora for training dialogue systems … features of a multiplicative RNN [Sutskever et al., 2011] and an LSTM [Hochreiter and Schmidhuber, 1997] to achieve a stronger language modeling performance …

Predicting head pose in dyadic conversation
D Greenwood, S Laycock, I Matthews – International Conference on …, 2017 – Springer
… The LSTM has been a powerful tool in speech and language modelling, and as the encoder-decoder in our CVAE has shown great utility … Nishimura, R., Kitaoka, N., Nakagawa, S.: A spoken dialog system for chat-like conversations considering response timing …

Neural Matching Models for Question Retrieval and Next Question Prediction in Conversation
L Yang, H Zamani, Y Zhang, J Guo, WB Croft – arXiv preprint arXiv …, 2017 – arxiv.org
… In many question answering and chatbot/dialogue systems, new questions issued by users have no explicit prede ned category … Bordes et al. [1] proposed a testbed to break down the strengths and shortcomings of end-to-end dialog systems in goal-oriented applications …

A knowledge graph based speech interface for question answering systems
AJ Kumar, C Schmidt, J Köhler – Speech Communication, 2017 – Elsevier
… It is a challenge to create open domain dialogue systems … In QA based on database querying, ASR is usually developed with a set of transcribed audio training data for acoustic modeling and a pre-defined set of question answer pair for language modeling …

Yeah, Right, Uh-Huh: A Deep Learning Backchannel Predictor
R Ruede, M Müller, S Stüker, A Waibel – arXiv preprint arXiv:1706.01340, 2017 – arxiv.org
… al.: Switchboard discourse language modeling project (1997) 7. Kawahara, T., Uesato, M., Yoshino, K., Takanashi, K.: Toward Adaptive Generation of Backchannels for Attentive Listening Agents. In: International Workshop Serien on Spo- ken Dialogue Systems Technology, pp …

Gated end-to-end memory networks
F Liu, J Perez – Proceedings of the 15th Conference of the European …, 2017 – aclweb.org
… objec- tive (all involved in a restaurant reservation sce- nario). This dataset essentially tests the capac- ity of end-to-end dialog systems to conduct dialog with various goals. Each dialog starts with a user request with subsequent …

Approximated and domain-adapted LSTM language models for first-pass decoding in speech recognition
M Singh, Y Oualil, D Klakow – Proceedings of the 18th …, 2017 – pdfs.semanticscholar.org
… The speech corpus collected during the Metalogue project aims to develop a dialogue system to monitor, teach and interact with participants, debating a multi-issue … 7] M. Sundermeyer, R. Schlüter, and H. Ney, “LSTM neural net- works for language modeling,” in INTERSPEECH …

Incorporating android conversational agents in m?learning apps
D Griol, JM Molina, Z Callejas – Expert Systems, 2017 – Wiley Online Library
By continuing to browse this site you agree to us using cookies as described in About Cookies. Remove maintenance message …

Modeling Target-Side Inflection in Neural Machine Translation
A Tamchyna, MWD Marco, A Fraser – arXiv preprint arXiv:1707.06012, 2017 – arxiv.org
Page 1. Modeling Target-Side Inflection in Neural Machine Translation Aleš Tamchyna1,2 and Marion Weller-Di Marco1,3 and Alexander Fraser1 1LMU Munich, 2Memsource, 3University of Stuttgart ales.tamchyna@memsource …

Deep reinforcement learning: An overview
Y Li – arXiv preprint arXiv:1701.07274, 2017 – arxiv.org
… Then we discuss various applications of RL, including games, in particular, AlphaGo, robotics, spoken dialogue systems (aka chatbot), machine translation, text sequence prediction, neural architecture design, personalized web services, healthcare, finance, and music …

Do neural nets learn statistical laws behind natural language?
S Takahashi, K Tanaka-Ishii – PloS one, 2017 – journals.plos.org
… Deep learning has performed spectacularly in various natural language processing tasks such as machine translation [1], text summarization [2], dialogue systems [3], and question answering [4]. A fundamental question that we ask, however, is why deep learning is such an …

Two-stage approach to named entity recognition using Wikipedia and DBpedia
S Ryu, H Yu, GG Lee – Proceedings of the 11th International Conference …, 2017 – dl.acm.org
… Many natural language-based systems such as dialog systems, question answering, and in- formation retrieval use NER to represent important infor- mation … 4. LANGUAGE MODELING We use an LM to score NE candidates by computing the likelihood of character-level tokens …

Non-Native Differences in Prosodic-Construction Use
NG Ward, P Gallardo – Dialogue & Discourse, 2017 – dad.uni-bielefeld.de
Page 1. Dialogue & Discourse 8(1) (2017) 1–30 doi: 10.5087/dad.2017.101 Non-Native Differences in Prosodic-Construction Use Nigel G. Ward NIGELWARD@ACM.ORG Department of Computer Science University of Texas at El Paso and Kyoto University Paola Gallardo …

Recurrent Attentional Topic Model.
S Li, Y Zhang, R Pan, M Mao, Y Yang – AAAI, 2017 – aaai.org
… sentence levels, and they have been applied to various tasks, including machine translation (Bahdanau, Cho, and Bengio 2014), summarization (Rush, Chopra, and Weston 2015), dialog system (Serban et al … Bayesian models focus on language modeling with attention signals …

Learning to Remember Translation History with a Continuous Cache
Z Tu, Y Liu, S Shi, T Zhang – arXiv preprint arXiv:1711.09367, 2017 – arxiv.org
… Our work is inspired by recent successes of memory-augmented neural networks on multi- ple NLP tasks (Weston et al., 2015; Sukhbaatar et al., 2015; Miller et al., 2016; Gu et al., 2017), es- pecially the efficient cache-like memory networks for language modeling (Grave et al …

Joint, incremental disfluency detection and utterance segmentation from speech
J Hough, D Schlangen – Proceedings of the 15th Conference of the …, 2017 – aclweb.org
… Joint, Incremental Disfluency Detection and Utterance Segmentation from Speech Julian Hough and David Schlangen Dialogue Systems Group // CITEC // Faculty of Linguistics and Literature Bielefeld University firstname.lastname@uni-bielefeld.de Abstract …

Neural network methods for natural language processing
Y Goldberg – Synthesis Lectures on Human Language …, 2017 – morganclaypool.com
… v Semantic Role Labeling Martha Palmer, Daniel Gildea, and Nianwen Xue 2010 Spoken Dialogue Systems Kristiina Jokinen and Michael McTear 2009 … ese advances led to breakthroughs in language modeling, automatic machine translation, and various other applications …

Medical speech recognition: reaching parity with humans
E Edwards, W Salloum, GP Finley, J Fone… – … Conference on Speech …, 2017 – Springer
… Investigations into more sophisticated language modeling techniques are currently carried out, examples of which are given in Sect. 6. They will be subject to a future review publication … Suendermann, D., Pieraccini, R.: Crowdsourcing for industrial spoken dialog systems …

Attentive memory networks: Efficient machine reading for conversational search
T Kenter, M de Rijke – arXiv preprint arXiv:1712.07229, 2017 – arxiv.org
Page 1. Attentive Memory Networks: Efficient Machine Reading for Conversational Search Tom Kenter University of Amsterdam Amsterdam, The Netherlands tom.kenter@uva.nl Maarten de Rijke University of Amsterdam Amsterdam, The Netherlands derijke@uva.nl …

Using Knowledge Graph And Search Query Click Logs in Statistical Language Model For Speech Recognition
W Zhu – Proc. Interspeech 2017, 2017 – isca-speech.org
… approach,” in ICASSP, IEEE, vol. 2. IEEE, 1993, pp. 45–48. [7] R. Sarikaya, Y. Gao, H. Erdogan, and M. Picheny, “Turn-based language modeling for spoken dialog systems,” in ICASSP, IEEE, 2002, pp. I–781. [8] R. Kuhn and R …

Spoken language understanding and interaction: machine learning for human-like conversational systems
M Gaši?, D Hakkani-Tür, A Celikyilmaz – 2017 – Elsevier
… have drawn inspiration from machine learning solutions eg sequence tagging, syntactic parsing, and language modelling, primarily because … investigated their interaction by combining theoretical work from pragmatics, practical work from the dialogue system community and …

Dialog System & Technology Challenge 6 Overview of Track 1-End-to-End Goal-Oriented Dialog learning
J Perez, YL Boureau, A Bordes – workshop.colips.org
… beyond language modeling. For example, asking questions to clearly define a user request, querying Knowledge Bases (KBs), interpreting results from queries to display options to users or completing a transaction are some of the important competencies a dialog system has to …

Web Application for Romanian Language Phonetic Transcription
J Domokos, ZA Szakács – MACRo 2015, 2017 – degruyter.com
… The joint sequence n-gram model needed by Phonetisaurus was estimated using the MIT Language Modeling toolkit … C. Burileanu, V. Popescu, A. Buzo, CS Petrea, D. Ghelmez-Hane, “Spontaneous speech recognition for Romanian in spoken dialogue systems” in Proceedings …

Dialogue Response Generation using Neural Networks with Attention and Background Knowledge
S Kosovan, J Lehmann, A Fischer – jens-lehmann.org
… But picking the sentence out of predefined set rarely makes much sense in Dialogue Systems … RNN is neural sequence model that achieves state of the art performance on important tasks that include language modeling, speech recognition, machine translation and image …

End-to-end Character-Level Dialogue Breakdown Detection with External Memory Models
T Iki, A Saito – workshop.colips.org
… Y. Unno, and M. Fukuda, “Multi-task Learning of Recurrent Neural Network for Detecting Breakdowns of dialog and Language Modeling,” SIG-SLUD … [9] C.-W. Liu, R. Lowe, IV Serban, M. Noseworthy, L. Charlin, J. Pineau, “How not to evaluate your dialogue system: An empirical …

A Complete Bibliography of ACM Transactions on Speech and Language Processing (TSLP)
NHF Beebe – 2017 – tug.ctan.org
… Bulyko:2007:WRL [BOS+07] Ivan Bulyko, Mari Ostendorf, Manhung Siu, Tim Ng, Andreas Stolcke, and Özgür Çetin. Web resources for language modeling in conversational speech recog- nition … Evaluating dis- course understanding in spoken dialogue systems …

Multilingual spoken dialog systems for handheld devices
BML Srivastava – 2017 – researchgate.net
… This work progresses to develop a spoken dialog system for the domain of Healthcare and focuses on problems of 1. recognizing the language of communication within speech segments through large-scale spoken language modeling and 2. spotting keywords in speech signal …

User-Adaptive A Posteriori Restoration for Incorrectly Segmented Utterances in Spoken Dialogue Systems
K Komatani, N Hotta, S Sato… – Dialogue & Discourse, 2017 – dad.uni-bielefeld.de
… doi: 10.5087/dad.2017.209 User-Adaptive A Posteriori Restoration for Incorrectly Segmented Utterances in Spoken Dialogue Systems? Kazunori Komatani … Abstract Ideally, the users of spoken dialogue systems should be able to speak at their own tempo …

Improving Frame Semantic Parsing with Hierarchical Dialogue Encoders
A Bapna, G Túr, D Hakkani-Túr, L Heck – arXiv preprint arXiv:1705.03455, 2017 – arxiv.org
… Joint model- ing of intent classification and language modeling showed promising improvements in intent recog- nition, especially in the … 2016) show improved performance on an informational dialogue agent by incorpo- rating knowledge base context into their dialogue system …

Unbounded cache model for online language modeling with open vocabulary
E Grave, MM Cisse, A Joulin – Advances in Neural Information …, 2017 – papers.nips.cc
… language modeling. Computer, Speech and Language, 1996. [49] WJ Scheirer, A. de Rezende Rocha, A. Sapkota, and TE Boult. Toward open set recognition. PAMI, 2013. [50] IV Serban, A. Sordoni, Y. Bengio, A. Courville, and J. Pineau. Building end-to-end dialogue systems …

Speech recognition in a dialog system: from conventional to deep processing
A Becerra, JI de la Rosa, E González – Multimedia Tools and Applications, 2017 – Springer
… have presented samples of their experiments on applying deep learn- ing methods to advancing speech technology and related applications, including feature extraction, acoustic modeling, language modeling, speech understanding, and dialog state … 3.1 Spoken dialog system …

Towards Deep End-of-Turn Prediction for Situated Spoken Dialogue Systems
A Maier, J Hough, D Schlangen – … of INTERSPEECH 2017, 2017 – pub.uni-bielefeld.de
… [18] M. Atterer, T. Baumann, and D. Schlangen, “Towards incremental end-of-utterance detection in dialogue systems,” Proceedings of … Available: http://www.aclweb.org/anthology/ D14-1009 [24] A. Stolcke and E. Shriberg, “Statistical language modeling for speech disfluencies …

Learning Robust Dialog Policies in Noisy Environments
M Fazel-Zarandi, SW Li, J Cao, J Casale… – arXiv preprint arXiv …, 2017 – arxiv.org
… 2 Related Work A dialog system can be formalized as a Markov Decision Process (MDP) [16] … We model intent generation as a language modeling problem and use recurrent neural networks (RNNs) to predict the trajectory of intents …

Combining CNNs and Pattern Matching for Question Interpretation in a Virtual Patient Dialogue System
L Jin, M White, E Jaffe, L Zimmerman… – Proceedings of the 12th …, 2017 – aclweb.org
… word- and character-based convolutional neural net- works (CNNs) for question identification in a virtual patient dialogue system, out- performing a … models that embed individual characters as input units are also possible, and have been used for language modeling (Kim et al …

Ethical Challenges in Data-Driven Dialogue Systems
P Henderson, K Sinha, N Angelard-Gontier… – arXiv preprint arXiv …, 2017 – arxiv.org
… One billion word benchmark for mea- suring progress in statistical language modeling. arXiv preprint arXiv:1312.3005. Curry, AC; Hastie, H.; and Rieser, V. 2017. A review of evaluation techniques for social dialogue systems. arXiv preprint arXiv:1709.04409 …

Classification-based spoken text selection for LVCSR language modeling
V Chunwijitra, C Wutiwiwatchai – EURASIP …, 2017 – asmp-eurasipjournals.springeropen …
… Classification-based spoken text selection for LVCSR language modeling. Vataya Chunwijitra 1 Email author and; Chai Wutiwiwatchai 1. EURASIP Journal on Audio, Speech, and Music Processing20172017:24. https://doi.org/10.1186/s13636-017-0121-5. © The Author(s) 2017 …

Hierarchical Module Classification in Mixed-initiative Conversational Agent System
SXY Suzanna, LL Anthony – Proceedings of the 2017 ACM on …, 2017 – dl.acm.org
… KEYWORDS Conversational Agent; Machine Learning; Ensemble Classifiers, Recurrent Neural Networks; Language Modeling … Our operational context is practical task-oriented dialog systems that interacts with real world users …

Recent Results in Speech Recognition for the Tatar Language
A Khusainov – International Conference on Text, Speech, and …, 2017 – Springer
… Some preprocessing steps have been implemented to prepare texts for language modelling: 1 … sub-word based speech recognition system showed 0% OOV rate, so it can be used in the applications where this factor can play an essential role, for example, in dialogue systems …

User Intention Classification in an Entities Missed In-vehicle Dialog System
K Zhang, Q Zhu, N Zhang, Z Shi, Y Zhan – International Conference in …, 2017 – Springer
… Recently, recurrent neural networks have demonstrated good performance in various natural language processing tasks such as language modeling (LM) [9 … DBN achieved good results in the long text classification, however, dialogue systems are often dozens of phrase or word …

Learning Generative End-to-end Dialog Systems with Knowledge
T Zhao – 2017 – cs.cmu.edu
… Page 2. November 21, 2017 DRAFT Keywords: dialog systems, end-to-end models, deep learning, reinforcement learn- ing, generative models, transfer learning, zero-shot learning Page 3 … Page 17. November 21, 2017 DRAFT Chapter 2 Related Work 2.1 Dialog Systems …

Dialog acts in greeting and leavetaking in social talk
E Gilmartin, B Spillane, M O’Reilly, K Su… – Proceedings of the 1st …, 2017 – dl.acm.org
… Dialog systems model spoken or written synchronous/near-synchronous interactions, often to fulfill a task but increasingly to create the illusion of social interaction … 1997. Switchboard Discourse Language Modeling Project (Final Report). (1997). [3] Volha Viktarauna Petukhova …

Miscommunication handling in spoken dialog systems based on error-aware dialog state detection
CH Wu, MH Su, WB Liang – EURASIP Journal on Audio, Speech, and …, 2017 – Springer
… December 2017 , 2017:9 | Cite as. Miscommunication handling in spoken dialog systems based on error-aware dialog state detection … Keywords. Error-aware dialog act Miscommunication Spoken dialog systems. Download fulltext PDF. 1 Introduction …

A spoken query system for the agricultural commodity prices and weather information access in Kannada language
TG Yadava, HS Jayanna – International Journal of Speech Technology, 2017 – Springer
… (2014). Large vocabulary Russian speech recognition using syntactico-statistical language modeling. Speech Communication, 56, 213–228.CrossRefGoogle Scholar. Kotkar, P., Thies, W., & Amarsinghe, S. (2008) … Tamil market: A spoken dialog system for rural india …

A Part-of-Speech Enhanced Neural Conversation Model
C Luo, W Li, Q Chen, Y He – European Conference on Information …, 2017 – Springer
… Perplexity is the most widely-used evaluation metric for language modeling … 1577–1586 (2015)Google Scholar. 5. Serban, IV, Sordoni, A., Bengio, Y., Courville, A., Pineau, J.: Building end-to-end dialogue systems using generative hierarchical neural network models …

Annotation of greeting, introduction, and leavetaking in dialogues
E Gilmartin, B Spillane, M O’Reilly, C Saam… – Proceedings of the 13th …, 2017 – aclweb.org
… of dialogues in more social as well as task-based terms, and that their use in the development of the ADELE system will be useful to other researchers in the field of casual or social dialogue system design … Switchboard Discourse Language Modeling Project (Final Report) …

Language Model Optimization for a Deep Neural Network Based Speech Recognition System for Serbian
E Pakoci, B Popovi?, D Pekar – International Conference on Speech and …, 2017 – Springer
… language models, such as class n-grams, which might amplify the good acoustic modeling with better language modeling as well … of Education, Science and Technological Development of the Republic of Serbia, within the project “Development of Dialogue Systems for Serbian …

Hierarchical Text Generation and Planning for Strategic Dialogue
D Yarats, M Lewis – arXiv preprint arXiv:1712.05846, 2017 – arxiv.org
Page 1. Hierarchical Text Generation and Planning for Strategic Dialogue Denis Yarats * 1 Mike Lewis * 1 Abstract End-to-end models for strategic dialogue are challenging to train, because linguistic and strategic aspects are entangled in latent state vec- tors …

Asystent–a Prototype of a Motivating Electronic Assistant
P ?wieczkowska, J Bachan, R Rzepka, K Araki – ceur-ws.org
… At this stage, we created a simple dialogue system Asystent to gather some basic data regarding successful human-computer cooperation … The testers’ comments provided valuable insight which will serve as guidelines for creating the actual dialogue system in the future …

Acoustic Feature Analysis and Discriminative Modeling for Language Identification of Closely Related South-Asian Languages
F Adeeba, S Hussain – Circuits, Systems, and Signal Processing, 2017 – Springer
… improve the performance of speech translation [53], multilingual speech recognition [32], user interaction with spoken dialog system [60], and … Parallel Phone Recognition and Language Modeling (PPRLM) [47] and Phone recognition-SVM [57] are two widely used phonotactic …

Dialogue Intent Classification with Long Short-Term Memory Networks
L Meng, M Huang – National CCF Conference on Natural Language …, 2017 – Springer
… Previous work in dialogue act classification mainly focused on domain-specific classification for goal-oriented dialogue systems [4] and researchers in … 13] showed a neural network with an explicit memory and a recurrent attention mechanism, in their language modeling tasks, it …

Proceedings of the 29th Conference on Computational Linguistics and Speech Processing (ROCLING 2017)
LW Ku, Y Tsao – Proceedings of the 29th Conference on Computational …, 2017 – aclweb.org
… Technical Staff and Director of the Dialogue Systems Research Department. His research interests include multimedia communication, multimedia signal and information processing, speech and speaker recognition, speech and language modeling, spoken …

Jee haan, I’d like both, por favor: Elicitation of a Code-Switched Corpus of Hindi–English and Spanish–English Human–Machine Dialog
V Ramanarayanan, D Suendermann-Oeft – Proc. Interspeech 2017, 2017 – oeft.de
… 23] and Hindi–English [24], which have in turn led to developments in automatic speech recognition [25, 26] and language modeling [27] … or no research on the automated analysis of conversational, code-switched dialog, let alone the building of bilingual dialog systems that are …

Predicting Users’ Negative Feedbacks in Multi-Turn Human-Computer Dialogues
X Wang, J Wang, Y Liu, X Wang, Z Wang… – Proceedings of the Eighth …, 2017 – aclweb.org
… wangbaoxun}@trio.ai Abstract User experience is essential for human- computer dialogue systems. However, it is impractical to ask users to provide explicit feedbacks when the agents’ responses dis- please them. Therefore, in …

Proceedings of the 2nd Workshop on Representation Learning for NLP
P Blunsom, A Bordes, K Cho, S Cohen, C Dyer… – Proceedings of the 2nd …, 2017 – aclweb.org
… Improving Language Modeling using Densely Connected Recurrent Neural Net- works Fréderic Godin, Joni Dambre and Wesley De Neve … A Frame Tracking Model for Memory-Enhanced Dialogue Systems Hannes Schulz, Jeremie Zumer, Layla El Asri and Shikhar Sharma …

Automatic Speech Recognition Adaptation to the IoT Domain Dialogue System
M Zembrzuski, H Jeon, J Marhula, K Beksa… – … on Methodologies for …, 2017 – Springer
… particularly by [6]. Additionally, within the area of recognition and understanding of various proficiency-level speakers by the dialogue system, our approach does not exploit acoustic modeling methods [5], but it concentrates on contextual language modeling enhancement …

Exploring personalized neural conversational models
S Kottur, X Wang, VR Carvalho – Proceedings of the 26th …, 2017 – xiaoyumu.com
… Improved backing-off for m-gram language modeling. ICASSP, 1:181–184, 1995 … How not to evaluate your dialogue system: An empirical study of unsupervised evaluation met- rics for dialogue response generation. arXiv preprint arXiv:1603.08023, 2016 …

EncodingWord Confusion Networks with Recurrent Neural Networks for Dialog State Tracking
G Jagfeld, NT Vu – arXiv preprint arXiv:1707.05853, 2017 – arxiv.org
… Task-oriented dialog systems are often imple- mented in a modular architecture to break up the complex task of conducting dialogs into … been shown to outper- form GRUs for speech signal sequence processing (Chung et al., 2014) and for language modeling with recurrent lay …

Effective Spoken Language Labeling with Deep Recurrent Neural Networks
M Dinarelli, Y Dupont, I Tellier – arXiv preprint arXiv:1706.06896, 2017 – arxiv.org
… This is a very important feature in spoken dialog systems, as the correct in- terpretation of a dialog turn may depend on the information extracted from previous … However [Mikolov et al., 2011] has shown that RNNs for language modeling learn best with only N = 5 previous steps …

Towards a Knowledge Graph based Speech Interface
AJ Kumar, S Auer, C Schmidt – arXiv preprint arXiv:1705.09222, 2017 – arxiv.org
… Using a knowledge graph for natural language processing, in particular, for language modeling is in- troduced in [4]. The authors propose … can be exploited for error detection and applications such as voice-based semantic search, question answering or spoken- dialog systems …

Big Data for Conversational Interfaces: Current Opportunities and Prospects
D Griol, JM Molina, Z Callejas – Big Data Management, 2017 – Springer
… Hoxha J, Weng C (2016) Leveraging dialog systems research to assist biomedical researchers interrogation of big clinical data. J Biomed Inf 61:176–184CrossRefGoogle Scholar. 27 … Jelinek F (1990) Self-organized language modeling for speech recognition …

Evaluating LSTM Networks, HMM and WFST in Malay Part-of-Speech Tagging
TP Tan, B Ranaivo-Malançon… – Journal of …, 2017 – journal.utem.edu.my
… tienping@usm.my Abstract—Long short term memory (LSTM) networks have been gaining popularity in modeling sequential data such as phoneme recognition, speech translation, language modeling, speech synthesis, chatbot-like dialog systems and others …

Integration of context-aware conversational interfaces to develop practical applications for mobile devices
D Griol, JM Molina, A Sanchis – Journal of Ambient Intelligence …, 2017 – content.iospress.com
… First, the Web emerged as a universal communications channel. Web-based dialogue systems are scalable enterprise systems that leverage the Internet to simultaneously deliver dialogue services to large populations of users …

Recognizing Emotionally Coloured Dialogue Speech Using Speaker-Adapted DNN-CNN Bottleneck Features
K Mukaihara, S Sakti, S Nakamura – International Conference on Speech …, 2017 – Springer
… Developing a natural spoken dialogue system that mimics human interaction requires a speech-oriented interface that can handle the various emotions often found in conversations … Stolcke, A.: SRILM – an extensible language modeling toolkit …

Towards a General, Continuous Model of Turn-taking in Spoken Dialogue using LSTM Recurrent Neural Networks
G Skantze – Proceedings of the 18th Annual SIGdial Meeting on …, 2017 – aclweb.org
… This poses a challenge for spoken dialogue systems, where the system needs to coordinate its speaking with the user to avoid interruptions and (inappropriate) gaps and overlaps … The model should also be applicable for mak- ing decisions in dialogue systems …

Multiple-Weight Recurrent Neural Networks
Z Cao, L Wang, G De Melo – Proceedings of the 26th International Joint …, 2017 – ijcai.org
… LSTM-based language models have also achieved strong results on language modeling due to their superior capability of capturing longer-term depen- dencies [Hochreiter and Schmidhuber, 1997]. For dialogue systems, contextual information and dialogue interactions be …

Personalization in Goal-Oriented Dialog
CK Joshi, F Mi, B Faltings – arXiv preprint arXiv:1706.07503, 2017 – arxiv.org
… In addition to fulfilling the original goal, the modified tasks also require the dialog system to personalize the conversation based on … successful for a variety of language understanding tasks such as question answering (Weston et al., 2015b), language modelling (Sukhbataar et al …

A Neural Language Model for Dynamically Representing the Meanings of Unknown Words and Entities in a Discourse
S Kobayashi, N Okazaki, K Inui – arXiv preprint arXiv:1709.01679, 2017 – arxiv.org
… Second, we introduce a new evaluation task and dataset called Anonymized Language Modeling … 3 Proposed Method: Dynamic Neural Text Modeling In this section, we introduce the extension of dy- namic entity representation to language modeling …

Low Frequency Words Compression in Neural Conversation System
S Wu, Y Li, Z Wu – International Conference on Neural Information …, 2017 – Springer
… reduced by 50% in almost configurations), which indicates that our approach can improve the performance of the dialogue system under the … log }p(y_{i} )) \) or it’s log version \( log \)-\( perplexity \) (LP) is the most popular automatic metric for language modeling and conversation …

Compositional Sentence Representation from Character within Large Context Text
G Kim, H Lee, B Kim, S Lee – International Conference on Neural …, 2017 – Springer
… Successful examples can be found in language modeling [16, 18] and machine translation [9]. 5 Conclusion … Serban, IV, Sordoni, A., Bengio, Y., Courville, A., Pineau, J.: Building end-to-end dialogue systems using generative hierarchical neural network models …

Simulation-Based Usability Evaluation of Spoken and Multimodal Dialogue Systems
S Hillmann – 2017 – Springer
… Stefan Hillmann Simulation-Based Usability Evaluation of Spoken and Multimodal Dialogue Systems Page 2. T-Labs Series in Telecommunication Services Series editors Sebastian Möller, Berlin, Germany Axel Küpper, Berlin, Germany Alexander Raake, Berlin, Germany …

Broad Discourse Context for Language Modeling
M Torres Garcia – 2017 – research-collection.ethz.ch
… Probabilistic language modeling is the area of Natural Language Processing (NLP) concerned with the development of statistical models capable of … An- other example are dialogue systems, where discourse understanding is needed to produce valid utterances for a given …

A Proposal to Integrate Conversational Interfaces in Mobile Learning Applications
D Griol, A Sanchis, JM Molina – … Joint Conference SOCO’17-CISIS’17 …, 2017 – Springer
… Z., López-Cózar, R., Riccardi, G.: A domain-independent statistical methodology for dialog management in spoken dialog systems. Comput. Speech Lang. 28(3), 743–768 (2014)CrossRefGoogle Scholar. 9. Kaufmann, T., Pfister, B.: Syntactic language modeling with …

Automatic Spoken Language Identification by Digital Signal Processing Methods. Tatar and Russian Languages
R Latypov, R Nigmatullin, E Stolov – International Conference on …, 2017 – Springer
… by a computer [1]. Applications of LID systems include front-end ones for speech recognition, automated dialogue systems, call routing … 152–157 (2011)Google Scholar. 6. Zissman, MA: Language identification using phoneme recognition and phonotactic language modeling …

Input-to-Output Gate to Improve RNN Language Models
S Takase, J Suzuki, M Nagata – arXiv preprint arXiv:1709.08907, 2017 – arxiv.org
… Hakan Inan, Khashayar Khosravi, and Richard Socher. 2016. Tying Word Vectors and Word Classifiers: A Loss Framework for Language Modeling. In … 2015. Se- mantically Conditioned LSTM-based Natural Lan- guage Generation for Spoken Dialogue Systems …

Speech Recognition Systems: A Comparative Review
R Matarneh, S Maksymova, VV Lyashenko, NV Belova – researchgate.net
… Sphinx2 uses dialog system language learning system and it is oriented on speech recognition in real time which makes it ideally suited for developing various mobile … This system can use weighted finite state machine as a language model in the stage of language modeling …

End-to-End Large Vocabulary Speech Recognition for the Serbian Language
B Popovi?, E Pakoci, D Pekar – International Conference on Speech and …, 2017 – Springer
… in this paper was supported in part by the Ministry of Education, Science and Technological Development of the Republic of Serbia, within the project “Development of Dialogue Systems for Serbian and … Kneser, R., Ney, H.: Improved backing-off for M-gram language modeling …

A Hybrid Language Understanding Approach for Robust Selection of Tutoring Goals
R Srivastava, K VanLehn – cs.cmu.edu
… 2001. Initiative management for tutorial dialogue. In Proceedings of the NAACL Workshop Adaption in Dialogue Systems. 5] MS Glass. 1999 … 1996. Bow: A toolkit for statistical language modeling, text retrieval, classi cation and clustering. http://www.cs.cmu.edu/ mccallum/bow …

Towards Natural Language Understanding using Multimodal Deep Learning
S Bos – pdfs.semanticscholar.org
Page 1. Towards Natural Language Understanding using Multimodal Deep Learning Steven Bos Delft Un iversity of T echnolog y Page 2. Page 3. Towards Natural Language Understanding using Multimodal Deep Learning THESIS …

Business Administration and Information Systems
RPDK Ambrosi – Data Analytics International Master – uni-hildesheim.de
… Elective Modules–Application–Natural Language Processing–Language Modelling Language English … 4. Language Technology as method and tool: digital- humanities applications, Language Processing daily life tools (eg dialogue systems, correction of orthography, style …

Unsupervised Segmentation of Phoneme Sequences based on Pitman-Yor Semi-Markov Model using Phoneme Length Context
R Takeda, K Komatani – Proceedings of the Eighth International Joint …, 2017 – aclweb.org
… Figure 3: Word segmentation Goldwater et al., 2009; Elsner et al., 2013; Uchiumi et al., 2015). The lexical acquisition technique is necessary in other areas, such as dialogue system that acquires knowledge through dialogue (Ono et al., 2016) …

Listen, Interact and Talk: Learning to Speak via Interaction
H Zhang, H Yu, W Xu – arXiv preprint arXiv:1705.09906, 2017 – arxiv.org
… forming another level of recurrence at the scale of time steps. 3.2.1 Imitation with Hierarchical-RNN-based Language Modeling The teacher’s way of speaking provides a source for the learner to mimic. One way to learn from this source of information is by predictive imitation …

Sequence Modeling with Hierarchical Deep Generative Models with Dual Memory
Y Zheng, L Wen, J Wang, J Yan, L Ji – Proceedings of the 2017 ACM on …, 2017 – dl.acm.org
… The results of language modeling show our method significantly outperforms state-of-the-art results in terms of generative perfor- mance … as central tasks towards multiple applications related to language understanding, such as machine translation [2, 7], dialogue system [35, 36 …

Deep Speech Recognition
L Deng – microsoft.com
Page 1. Deep Speech Recognition New-Generation Models & Methodology for Advancing Speech Technology and Information Processing Li Deng Microsoft Research, Redmond, USA IEEE ChinaSIP Summer School, July 6, 2013 …

Building Natural Language Interfaces to Web APIs
Y Su, AH Awadallah, M Khabsa, P Pantel… – Proceedings of the …, 2017 – dl.acm.org
… 3.2). Similar to language modeling for information retrieval [23], we assume NL commands are generated from the corresponding API calls, and estimate a language model for each API call to capture this generative process …

Negotiation of Antibiotic Treatment in Medical Consultations: A Corpus based Study
N Wang – Proceedings of ACL 2017, Student Research …, 2017 – aclweb.org
… Current research for dialogue systems offer an alternative ap- proach … With the com- bination of the social science research method of conversation analysis and computational methods for language modeling, we aim to discover how language practices in doctor-patient …

Steering output style and topic in neural response generation
D Wang, N Jojic, C Brockett, E Nyberg – arXiv preprint arXiv:1709.03010, 2017 – arxiv.org
… The words of input sentences were first con- verted to 300-dimensional vector representations learned from the RNN based language modeling tool word2vec (Mikolov et al., 2013). The begin- ning and end of each passage are also padded with a special boundary symbol …

Handling long-term dependencies and rare words in low-resource language modelling
M Singh – 2017 – publikationen.sulb.uni-saarland.de
… 58 5.3 Language Modeling Experiments … Secondly, we address out-of-vocabulary words for low-resource languages and en- able better representations for language modelling tasks. In both of these cases, we evaluate our models on a downstream NLP task …

Semi-Supervised Learning of a Pronunciation Dictionary from Disjoint Phonemic Transcripts and Text
T Shinozaki, S Watanabe, D Mochihashi… – Proc. Interspeech …, 2017 – merl.com
… by performing character recognition [1]. However, many applications including infor- mation retrieval and spoken dialog systems still require … Mochihashi, T. Yamada, and N. Ueda, “Bayesian unsupervised word segmentation with nested Pitman-Yor language modeling,” in Proc …

Reinforcement Learning Based Conversational Search Assistant
M Aggarwal, A Arora, S Sodhani… – arXiv preprint arXiv …, 2017 – arxiv.org
… set of question answering specific tasks have been developed to test the reasoning and deduction ability of dialogue systems [15 … Recurrent neural networks (RNN) have been successfully used in language modeling task where given an input sequence, the system predicts the …

KIT-Conferences
MIAR Roedder – 2017 – isl.anthropomatik.kit.edu
… 04, 2017. Yeah, Right, Uh-Huh: A Deep Learning Backchannel Predictor, Robin Ruede, Markus Müller, Sebastian Stüker, Alex Waibel. International Workshop on Spoken Dialogue Systems Technology 2017, Farmington, Pennsylvania, USA. 6th – 9th June, 2017 …

Neural Text Generation: A Practical Guide
Z Xie – arXiv preprint arXiv:1711.09534, 2017 – arxiv.org
… Task X (example) Y (example) language modeling none (empty sequence) … Before neural network-based approaches, count-based methods [Chen and Goodman, 1996] and methods involving learning phrase pair probabilities were used for language modeling and translation …

Multi-scale Context Adaptation for Improving Child Automatic Speech Recognition in Child-Adult Spoken Interactions
M Kumar, D Bone, K McWilliams, S Williams… – Proc. Interspeech …, 2017 – researchgate.net
… [28] A. Stolcke et al., “Srilm-an extensible language modeling toolkit.” in Interspeech, vol. 2002, 2002, p. 2002 … 51, no. 6, pp. 499–509, 2009. [31] IV Serban, A. Sordoni, Y. Bengio, A. Courville, and J. Pineau, “Building end-to-end dialogue systems using generative hierar- chical …

End-to-end Adversarial Learning for Generative Conversational Agents
O Ludwig – arXiv preprint arXiv:1711.10122, 2017 – arxiv.org
… Neural language modeling [1], [2] uses recurrent neural net- works to create effective models for different tasks in Natural Language Processing, such as open … [17] IV Serban, A. Sordoni, Y. Bengio, AC Courville, J. Pineau, Building end-to-end dialogue systems using generative …

Shallow PARsing and Knowledge extraction for Language Engineering
I Annex – cogsci.ed.ac.uk
… Speech dialogue systems will soon be in the position of providing services such as data base access via telephone … Some approaches use stochastic language modelling inspired by the success of hidden Markov model (HMM) based lexical category disambiguation …

Building HMM-SGMM Continuous Automatic Speech Recognition on Myanmar Web News
AN Mon, WP Pa, K Thu – researchgate.net
… Another important applica- tion area is telephony, where speech recognition is al- ready used for example in spoken dialogue systems for entering digits … Language Model Our language model was trained using The SRI Lan- guage Modeling (SRILM) language modeling toolkit …

Proceedings of the Workshop on Logic and Algorithms in Computational Linguistics 2017 (LACompLing2017)
R Loukanova, K Liefke – Workshop on Logic and Algorithms in …, 2017 – diva-portal.org
… dialogue, di- alogue systems, language and cognition, pragmatics, formal semantics, semantic coordination, in-vehicle dialogue systems, philosophy of … She is currently working on integrating symbolic and statistical approaches to language modeling in order to develop a better …

YJTI at the NTCIR-13 STC Japanese Subtask
T Shimizu – research.nii.ac.jp
… In this work, we demonstrate that a retrieval-based dialog system can be effective and that the combinations of two el- ements, a large-scale neural model and … To expedite the process, we usually start a training process with language modeling and then move on to a main task …

Disfluency Detection using a Noisy Channel Model and a Deep Neural Language Model
PJ Lou, M Johnson – Proceedings of the 55th Annual Meeting of the …, 2017 – aclweb.org
… transcripts. Moreover, disfluen- cies pose a major challenge to natural language processing tasks, such as dialogue systems, that rely on speech transcripts (Ostendorf et al., 2008). Since … ularisation. 4 Corpora for Language Modelling In …

BEAT-o-matic: a baseline for learning behavior expressions from utterances
M Gallé, A Arora – pdfs.semanticscholar.org
… As open-domain dialogue systems are still out-of-scope of our current understanding of natural language processing and machine learning research, one of the biggest short- term challenges … One billion word benchmark for measuring progress in statistical language modeling …

VOCABULARY ON UBUNTU DIALOGUE CORPUS
E WORD – pdfs.semanticscholar.org
… The size of the corpus makes it attractive for the exploration of deep neural network modeling in the context of dialogue systems … representation for part-of-speech and name entity tagging tasks while the latter used only character-level representation for language modeling …

Emotional Human-Machine Conversation Generation Based on Long Short-Term Memory
X Sun, X Peng, S Ding – Cognitive Computation, 2017 – Springer
… Several attempts have been made to endow dialog systems or conversational agents with emotion [2, 33]. Kadish et al … [37] proposed a natural language dialog system that can estimate the user’s emotion from utterances and respond on the basis of the estimated emotion …

Modeling the clarification potential of instructions: Predicting clarification requests and other reactions
L Benotti, P Blackburn – Computer Speech & Language, 2017 – Elsevier
… Keywords. Clarification requests. Level-sensitive Gabsdil test. Conversational implicatures. Dialogue systems. Classical planning. Micro-planning. Negotiability … We first review a method of identifying clarification requests proposed in the dialogue system literature …

Incomplete Follow-up Question Resolution using Retrieval based Sequence to Sequence Learning
V Kumar, S Joshi – Proceedings of the 40th International ACM SIGIR …, 2017 – dl.acm.org
… statistical machine translation [4, 45], language modeling [31, 32, 53], paraphrase generation [16, 36], se- mantic slot lling [26], image caption generation [20, 22, 51] among many others. Sequence to sequence learning has also been applied in dialogue systems for user …

Slim Embedding Layers for Recurrent Neural Language Models
Z Li, R Kulhanek, S Wang, Y Zhao, S Wu – arXiv preprint arXiv:1711.09873, 2017 – arxiv.org
… Shuang Wu Yitu. Inc shuang.wu@gmail.com Abstract Recurrent neural language models are the state-of-the-art models for language modeling … Introduction Neural language models are currently the state of the art model for language modeling …

Adversarial generation of natural language
S Subramanian, S Rajeswar, F Dutil, C Pal… – Proceedings of the 2nd …, 2017 – aclweb.org
… sentences3 which we will henceforth refer to as CMU?SE, the version of the Penn Treebank commonly used in language modeling experiments (Zaremba … future work, we would like to ex- plore GANs in other domains of NLP such as non goal-oriented dialog systems where a …

AppTechMiner: Mining Applications and Techniques from Scientific Articles
M Singh, S Dan, S Agarwal, P Goyal… – Proceedings of the 6th …, 2017 – dl.acm.org
… Entity Recog- nition, Word Alignment, Conditional Random Fields, Maximum Entropy, Coreference Resolution, Machine Learning, Dialogue Systems, Textual Entailment … direct match with the set of area names then we further use the language modeling approach (discussed …

Voice-transformation-based data augmentation for prosodic classification
R Fernandez, A Rosenberg, A Sorin… – … , Speech and Signal …, 2017 – ieeexplore.ieee.org
… applied include the acoustic models (AM) of speech recognition systems, though some other applications, like language modeling (eg, [6 … Heldner, “An instantaneous vector representation of delta pitch for speaker-change predic- tion in conversational dialogue systems,” in Proc …

Enhancing Backchannel Prediction Using Word Embeddings
R Ruede, M Müller, S Stüker… – Proc. Interspeech …, 2017 – pdfs.semanticscholar.org
… S. Stüker, and A. Waibel, “Yeah, right, uh- huh: A deep learning backchannel predictor,” accepted to the International Workshop on Spoken Dialogue Systems, 2017 … [20] D. Jurafsky, C. Van Ess-Dykema, and others, “Switch- board discourse language modeling project,” http …

Enriching confusion networks for post-processing
S Ghannay, Y Estève, N Camelin – International Conference on Statistical …, 2017 – Springer
… JMLR.orgMATHGoogle Scholar. 8. Schwenk, H.: CSLM-a modular open-source continuous space language modeling toolkit … C., Vigouroux, N., et al.: The French MEDIA/EVALDA project: the evaluation of the understanding capability of spoken language dialogue systems …

Type Theory for Natural Language Semantics
S Chatzikyriakidis, R Cooper – researchgate.net
… natural language see Chatzikyriakidis and Luo (2017b). There is also a forthcoming special issue of the Journal of Language Modelling devoted to the application of type theories to lexical semantics (Retoré and Cooper, forth).

CCG Supertagging via Bidirectional LSTM-CRF Neural Architecture
R Kadari, Y Zhang, W Zhang, T Liu – Neurocomputing, 2017 – Elsevier
… for every element in a sequence. RNNs have been successfully used for many applications such as language modeling [26], spoken language understanding [27] and CCG supertagging [5]. The structure of widely used RNNs …

Natural Language Inference with External Knowledge
Q Chen, X Zhu, ZH Ling, D Inkpen – arXiv preprint arXiv:1711.04289, 2017 – arxiv.org
… In general, external knowledge have been shown to be effective in a wide range of NLP tasks, including machine translation (Shi et al., 2016; Zhang et al., 2017), language modeling (Ahn et al., 2 Page 3. 2016), and dialogue system (Chen et al., 2016) …

Evaluating Attention Networks for Anaphora Resolution
J Pilault, N Pappas, L Miculicich Werlen… – 2017 – infoscience.epfl.ch
… natural language processing tasks, including — but not limited to -– information retrieval, neural machine translation, and text understanding in dialog systems … that the classifier function H may need to be changed for other types of tasks, such as Language Modeling or Machine …

Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers
M Lapata, P Blunsom, A Koller – Proceedings of the 15th Conference of …, 2017 – aclweb.org
… 427 A Network-based End-to-End Trainable Task-oriented Dialogue System Tsung-Hsien Wen, David Vandyke, Nikola Mrkšic, Milica Gasic, Lina M. Rojas Barahona, Pei-Hao Su, Stefan Ultes and Steve Young …

Generating Sentences by Editing Prototypes
K Guu, TB Hashimoto, Y Oren, P Liang – arXiv preprint arXiv:1709.08878, 2017 – arxiv.org
… Compared to traditional mod- els that generate from scratch either left-to- right or by first sampling a latent sentence vec- tor, our prototype-then-edit model improves perplexity on language modeling and gener- ates higher quality outputs according to hu- man evaluation …

UE-HRI: a new dataset for the study of user engagement in spontaneous human-robot interactions
A Ben-Youssef, C Clavel, S Essid, M Bilac… – Proceedings of the 19th …, 2017 – dl.acm.org
… Ang et al. [1] use prosodic features, language modelling and speaking style to detect user frustration with a telephone-based dialog system interface. They show that a prosodic decision trees can predict whether an utterance is neutral or “annoyed or frustrated” …

Emotion Recognition by Combining Prosody and Sentiment Analysis for Expressing Reactive Emotion by Humanoid Robot
Y Li, CT Ishi, N Ward, K Inoue… – … of APSIPA Annual …, 2017 – sap.ist.i.kyoto-u.ac.jp
… The results of the neutral condition suggest that the user may feel uncomfortable about most of the current dialog systems which do not take emotion into … [14] NG Ward and A. Vega, “Towards empirical dialog-state modeling and its use in language modeling.” in Interspeech …

Sentence?Chain Based Seq2seq Model for Corpus Expansion
E Chung, JG Park – ETRI Journal, 2017 – Wiley Online Library
By continuing to browse this site you agree to us using cookies as described in About Cookies. Remove maintenance message …

Robust lecture speech translation for speech misrecognition and its rescoring effect from multiple candidates
K Sahashi, N Goto, H Seki, K Yamamoto… – Advanced …, 2017 – ieeexplore.ieee.org
… Class room lectures tend to have much broader topics and more conventional than that seen in speech translation tasks such as spoken dialog systems for travel assistance [3]. Combining automatic speech recognition (ASR … The SRI language modeling toolkit [21] was used …

Character-based Embedding Models and Reranking Strategies for Understanding Natural Language Meal Descriptions
M Korpusik, Z Collins, J Glass – Proc. Interspeech 2017, 2017 – groups.csail.mit.edu
… learned character-based word embeddings using a CNN followed by a highway network [19]; however, while their task is language modeling, to which they apply … [24] M. Korpusik and J. Glass, “Spoken language understanding for a nutrition dialogue system,” IEEE Transactions …

A Complete Bibliography of ACM Transactions on Asian Language Information Processing
NHF Beebe – 2017 – tug.ctan.org
… Gao:2002:TUA [2] Jianfeng Gao, Joshua Goodman, Mingjing Li, and Kai-Fu Lee. To- ward a unified approach to statistical language modeling for Chinese … [37] Harksoo Kim and Jungyun Seo. Resolution of referring expressions in a Korean multimodal dialogue system …

Analysis of Human Machine Interaction Design Perspective-A Comprehensive Literature Review
MM Ahamed – International Journal of Contemporary …, 2017 – arrasikhun.mediu.edu.my
… In their work proposed to improve the performance of an ASR (Automatic Speech Recognition) system with dialog system taking into account LM (Language Modelling) one hand and the other hand AM (Acoustic Modeling) …

Named Entity Recognition with Gated Convolutional Neural Networks
C Wang, W Chen, B Xu – … and Natural Language Processing Based on …, 2017 – Springer
… NER is also a popular NLP task and plays a vital role for downstream systems, such as machine translation systems and dialogue systems … Dauphin [7] have shown that gating mechanism is useful for language modeling tasks …

Can Discourse Relations be Identified Incrementally?
F Yung, H Noji, Y Matsumoto – Proceedings of the Eighth International …, 2017 – aclweb.org
… These incremental systems are advantageous since they are capable of synchronous analysis by accepting sentence pre- fixes as inputs. On top of generating more natural and timely response in dialogue systems and im- proving language modeling in speech recognition, 157 …

What Happens Next? Future Subevent Prediction Using Contextual Hierarchical LSTM.
L Hu, J Li, L Nie, XL Li, C Shao – AAAI, 2017 – aaai.org
Page 1. What Happens Next? Future Subevent Prediction Using Contextual Hierarchical LSTM Linmei Hu, 1 Juanzi Li, 1 Liqiang Nie, 2 Xiao-Li Li, 3 Chao Shao 1 1 Department of Computer Science and Technology, Tsinghua …

Extensions for Distributed Moving Base Driving Simulators
A Andersson – 2017 – books.google.com
Page 1. Linköping Studies in Science and Technology Licentiate Thesis No. 1777 Extensions for Distributed Moving Base Driving Simulators Anders Andersson Page 2. Linköping Studies in Science and Technology Licentiate Thesis No …

Incorporating Structural Bias into Neural Networks
Z Yang – 2017 – cs.cmu.edu
Page 1. November 2, 2017 DRAFT Thesis Proposal Incorporating Structural Bias into Neural Networks Zichao Yang Nov 2017 School of Computer Science Carnegie Mellon University Pittsburgh, PA 15213 Thesis Committee …

Reusing Neural Speech Representations for Auditory Emotion Recognition
E Lakomkin, C Weber, S Magg, S Wermter – Proceedings of the Eighth …, 2017 – aclweb.org
… More- over, in many applications, such as dialog systems, we would need to transcribe spoken text and iden- tify its emotion jointly … 2014. Enhancing the ted-lium corpus with selected data for language modeling and more ted talks. In LREC, pages 3935–3939 …

Statistical Language Models applied to News Generation
JRP Soares – 2017 – repositorio-aberto.up.pt
… 2.6.6 SRILM . . . . . 20 3 Statistical Language Modeling 23 3.1 ProblemApproach . . . . . 23 … 33 ix Page 14. CONTENTS 3.4 Language Modeling . . . . . 35 …

Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
R Barzilay, MY Kan – Proceedings of the 55th Annual Meeting of the …, 2017 – aclweb.org
Page 1. ACL 2017 The 55th Annual Meeting of the Association for Computational Linguistics Proceedings of the Conference, Vol. 1 (Long Papers) July 30 – August 4, 2017 Vancouver, Canada Page 2. Platinum Sponsors: Gold Sponsors: ii Page 3. Silver Sponsors …

Towards a top-down policy engineering framework for attribute-based access control
M Narouei, H Khanpour, H Takabi, N Parde… – Proceedings of the …, 2017 – dl.acm.org
… 4.2 Recurrent Neural Network (RNN) Sentence Classi er Recently, DNNs have been used with increasing frequency in a variety of text processing applications, from sentiment analysis [41] to conversational text processing for dialogue systems [22, 48]. Collobert et al …

Developing an Intelligent Chat-bot Tool to assist high school students for learning general knowledge subjects
D Dutta – 2017 – smartech.gatech.edu
… With the need to address such problems, the idea of natural language dialog system arises in which a user questions in natural language and the system reverts back … AIML language simplify the task of Natural Language modelling, in respect to a “stimulus-response” process …

Knowledge Guided Short-Text Classification for Healthcare Applications
S Cao, B Qian, C Yin, X Li, J Wei… – Data Mining (ICDM) …, 2017 – ieeexplore.ieee.org
… Page 2. the intent, as the medical type of “mitral valve prolapse” is a key indicator to the dialog system. If this is the case, the utterance the chatbot received turns into Fig … The same authors also explore adding a new task (Language Modeling) for joint training in [28] using RNN …

Phoneme Set Design for Second Language Speech Recognition
X Wang – 2017 – researchgate.net
… levels. These problems would cause deterioration in the effectiveness of general speech-driven applications, such as question-answering systems and spoken dialogue systems … for spoken dialogue systems that target tourists, such as travel assistance systems, hotel reserva …

Deep-Learning Based Automatic Spontaneous Speech Assessment in a Data-Driven Approach for the 2017 SLaTE CALL Shared Challenge
YR Oh, HB Jeon, HJ Song, BO Kang, YK Lee… – Proc. 7th ISCA … – slate2017.org
Page 1. Deep-Learning Based Automatic Spontaneous Speech Assessment in a Data-Driven Approach for the 2017 SLaTE CALL Shared Challenge Yoo Rhee Oh, Hyung-Bae Jeon, Hwa Jeon Song, Byung Ok Kang, Yun-Kyung Lee, Jeon-Gue Park, and Yun-Keun Lee …

Voice activity detection and garbage modelling for a mobile automatic speech recognition application
M Ishaq – 2017 – aaltodoc.aalto.fi
… 10 2.2.5 Language Modelling … In 2000s, the integration of full semantics model and text-to-speech synthesis system with the very large vocabulary system happened, which enabled the spoken dialog systems with multiple input-output approaches …

Incremental Tree Substitution Grammar for Parsing and Sentence Prediction
F Sangati, F Keller – research.ed.ac.uk
… evaluate the partial trees that the parser constructs for sentence prefixes; partial trees play an important role in incre- mental interpretation, language modeling, and psycholinguistics … A dialogue system should start interpreting a sentence while it is being spoken, and a question …

Deep keyphrase generation
R Meng, S Zhao, S Han, D He, P Brusilovsky… – arXiv preprint arXiv …, 2017 – arxiv.org
… Previous studies (Bahdanau et al., 2014; Cho et al., 2014) indicate that it can generally provide better performance of language modeling than a simple RNN and a simpler struc- ture than other Long Short-Term Memory net- works (Hochreiter and Schmidhuber, 1997) …

Text Generation Using Different Recurrent Neural Networks
P Taneja, KG Verma – 2017 – dspace.thapar.edu
… 3 Language Modeling and Text Generation ….. 3 … many NLP tasks. The following are some examples of it. Language Modeling and Text Generation These are the tasks in which a sequence of words is given and we want to predict the …

An End-to-End Deep Learning Approach to Simultaneous Speech Dereverberation and Acoustic Modeling for Robust Speech Recognition
B Wu, K Li, F Ge, Z Huang, M Yang… – IEEE Journal of …, 2017 – ieeexplore.ieee.org
Page 1. IEEE JOURNAL OF SELECTED TOPICS IN SIGNAL PROCESSING, VOL. 11, NO. 8, DECEMBER 2017 1289 An End-to-End Deep Learning Approach to Simultaneous Speech Dereverberation and Acoustic Modeling for Robust Speech Recognition …

CNLs for the semantic web: a state of the art
H Safwat, B Davis – Language Resources and Evaluation, 2017 – Springer
… MOLTO). 7 This has boosted the uptake of GF and resulted in many comprehensive applications. GF applications range from mathematical proofing, dialog systems, patent translation (España-Bonet et al. 2011), multilingual …

Learning and Knowledge Transfer with Memory Networks for Machine Comprehension
M Yadav, L Vig, G Shroff – Proceedings of the 15th Conference of the …, 2017 – aclweb.org
… Recently, Memory Net- works have been successfully applied to QA and dialogue-systems to work with a variety of dis- parate data sources such … It has been shown in the context of language modelling that presenting the training samples in an easy to hard ordering allows for …

Constructing a Language From Scratch: Combining Bottom–Up and Top–Down Learning Processes in a Computational Model of Language Acquisition
J Gaspers, P Cimiano, K Rohlfing… – IEEE Transactions on …, 2017 – ieeexplore.ieee.org
Page 1. IEEE TRANSACTIONS ON COGNITIVE AND DEVELOPMENTAL SYSTEMS, VOL. 9, NO. 2, JUNE 2017 183 Constructing a Language From Scratch: Combining Bottom–Up and Top–Down Learning Processes in a Computational Model of Language Acquisition …

Automatic Neural Question Generation using Community-based Question Answering Systems
T Baghaee – 2017 – uleth.ca
… They have shown promising results in machine translation, document summarization, ques- tion answering, image caption generation and language modeling (Olah, 2015). RNNs have … Consider the problem of language modeling. Given the sentence, “Lions live in the … ” …

A Survey of Design Techniques for Conversational Agents
K Ramesh, S Ravishankaran, A Joshi… – International Conference …, 2017 – Springer
… success in past few years when they were applied to different problem domains such as image captioning, language modeling, translation, speech … In: Proceedings of the 2010 Workshop on Companionable Dialogue Systems, Association for Computational Linguistics, pp …

A Survey of Design Techniques for Conversational Agents
K Chandrasekaran – … Conference, ICICCT 2017, New Delhi, India …, 2017 – books.google.com
… success in past few years when they were applied to different problem domains such as image captioning, language modeling, translation, speech … In: Proceedings of the 2010 Workshop on Companionable Dialogue Systems, Association for Computational Linguistics, pp …

Automated Crowdturfing Attacks and Defenses in Online Review Systems
Y Yao, B Viswanath, J Cryan, H Zheng… – Proceedings of the 2017 …, 2017 – dl.acm.org
Page 1. Automated Crowdturfing Attacks and Defenses in Online Review Systems Yuanshun Yao ysyao@cs.uchicago.edu University of Chicago Bimal Viswanath viswanath@cs.uchicago.edu University of Chicago Jenna Cryan …

Arabic Speech Recognition Systems
HMM Eljagmani – 2017 – repository.lib.fit.edu
… Sphinx2, Sphinx3, Sphinx4, Sphinxbase, PocketSphinx, SphinxTrain, and CMU Cambridge Language Modeling Toolkit are first introduced. The architecture of … It used in pronunciation learning systems, dialogue systems and interactive applications. Sphinx 2 introduced the …

Challenges in data-to-document generation
S Wiseman, SM Shieber, AM Rush – arXiv preprint arXiv:1707.08052, 2017 – arxiv.org
… one to produce the scores used in copy or pcopy. We train the generation models using SGD and truncated BPTT (Elman, 1990; Mikolov et al., 2010), as in language modeling. That is, we split each y1:T into contiguous blocks …

Sign to speak–hand shape descriptors and speech translation technique based tamil alphabet fingerspelling recognition system
SS Nidhyananthan, AR Madumathi… – Advances in Natural …, 2017 – go.galegroup.com
… The system was developed to use both manual and non-manual features in a Pa HMM to recognize signs, and furthermore, statistical language modelling is applied and compared … “HandTalker: A multimodal dialog system using sign language and 3-D virtual human,” in Proc …

Personalizing recurrent-neural-network-based language model by social network
HY Lee, BH Tseng, TH Wen, Y Tsao, HY Lee… – IEEE/ACM Transactions …, 2017 – dl.acm.org
… Index Terms—Personalized language modeling, recurrent neural network, social network … This leads to the fact that person- alization, which has been intensively studied in areas such as retrieval and language learning, is now feasible for language modeling as well …

Deep Reinforcement Learning in Natural Language Scenarios
J He – 2017 – digital.lib.washington.edu
… good/bad endings. Another example is a human-computer dialog system, where the action is the response generated by the dialog manager … In unsupervised tasks such as language modeling, Bengio et al. [13] first introduced a neu- Page 24. 12 …

Efficiently Trainable Text-to-Speech System Based on Deep Convolutional Networks with Guided Attention
H Tachibana, K Uenoyama, S Aihara – arXiv preprint arXiv:1710.08969, 2017 – arxiv.org
… Deep Learning Workshop, ICML, 2015. [20] IV Serban et al., “Building end-to-end dialogue systems us- ing generative hierarchical neural network models.,” in Proc … [25] YN Dauphin et al., “Language modeling with gated convolu- tional networks,” arXiv:1612.08083, 2016 …

Improving the understanding of spoken referring expressions through syntactic-semantic and contextual-phonetic error-correction
I Zukerman, A Partovi – Computer Speech & Language, 2017 – Elsevier
… system. Abstract. Despite recent advances in automatic speech recognition, one of the main stumbling blocks to the widespread adoption of Spoken Dialogue Systems is the lack of reliability of automatic speech recognizers …

A joint deep model of entities and documents for cumulative citation recommendation
L Ma, D Song, L Liao, Y Ni – Cluster Computing, 2017 – Springer
… For instance, due to its ability to capture long-distance dependencies, LSTM has re-emerge as pop- ular choice for many sequence-modeling tasks like language modeling, machine translation [19], natural language gen- eration [20] and so on …

Query responses
P ?upkowski, J Ginzburg – Journal of Language Modelling, 2017 – jlm.ipipan.waw.pl
… 9,279 ?/? cross-turn sequences, whereas 41,041 ?/. cross-turn sequences, so the ?/? pairs constitute 22.61%. Journal of Language Modelling Vol 4, No 2 (2016), pp. 245–292 Page 2. Pawe? ?upkowski, Jonathan Ginzburg the …

Expert finding by the Dempster?Shafer theory for evidence combination
N Torkzadeh Mahani, M Dehghani, MS Mirian… – Expert Systems – Wiley Online Library
By continuing to browse this site you agree to us using cookies as described in About Cookies. Remove maintenance message …

Learning to attend, copy, and generate for session-based query suggestion
M Dehghani, S Rothe, E Alfonseca, P Fleury – arXiv preprint arXiv …, 2017 – arxiv.org
Page 1. Learning to A end, Copy, and Generate for Session-Based ery Suggestion Mostafa Dehghani? University of Amsterdam dehghani@uva.nl Sascha Rothe Google Research rothe@google.com Enrique Alfonseca Google Research ealfonseca@google.com …

Multimodal Crowdsourcing for Transcribing Handwritten Documents
E Granell, CD Martinez-Hinarejos – IEEE/ACM Transactions on …, 2017 – ieeexplore.ieee.org
Page 1. IEEE/ACM TRANSACTIONS ON AUDIO, SPEECH, AND LANGUAGE PROCESSING, VOL. 25, NO. 2, FEBRUARY 2017 409 Multimodal Crowdsourcing for Transcribing Handwritten Documents Emilio Granell and Carlos-D. Mart?nez-Hinarejos …

Towards Micro-video Understanding by Joint Sequential-Sparse Modeling
M Liu, L Nie, M Wang, B Chen – Proceedings of the 2017 ACM on …, 2017 – dl.acm.org
… in [17] is one of the popular variations of RNN, which is designed to mitigate the gradient vanish problem of RNN [4]. In addition, it has been very success- ful in variety of temporal sequence tasks, such as language modeling [12, 29], translation [26], dialog system [11], time …

Memory augmented neural networks with wormhole connections
C Gulcehre, S Chandar, Y Bengio – arXiv preprint arXiv:1701.08718, 2017 – arxiv.org
… 3. Training TARDIS In this section, we explain how to train TARDIS as a language model. We use language modeling as an example application … In this paper, we focus on application of REINFORCE on sequential prediction tasks, such as language modelling …

Non-Markovian Control with Gated End-to-End Memory Policy Networks
J Perez, T Silander – arXiv preprint arXiv:1705.10993, 2017 – arxiv.org
… on sev- eral sequential decision tasks with immediate reward maximization like natural language translation [BCB14] or end-to-end dialog systems … we define our control model using the approach that have been described in the context of language modeling [SSWF15b] …

Integrating Extractive and Abstractive Models for Long Text Summarization
S Wang, X Zhao, B Li, B Ge… – Big Data (BigData …, 2017 – ieeexplore.ieee.org
… natural language processing tasks, including but not limited to machine translation [2], voice recognition [3] and dialogue systems [22], etc … constructed on the encoder-decoder framework, which combines a represen- tation learning encoder and a language modeling decoder to …

Sequential short-text classification with neural networks
F Dernoncourt – 2017 – dspace.mit.edu
Page 1. Sequential Short-Text Classification MAOT ITUTEl OF TECHNQLOGY with Neural Networks JUN 23 201 by Franck Dernoncourt ARCHiVES Submitted to the Department of Electrical Engineering and Computer Science …

Computer Vision and Natural Language Processing: Recent Approaches in Multimedia and Robotics
P Wiriyathammabhum, D Summers-Stay… – ACM Computing …, 2017 – dl.acm.org
Page 1. 71 Computer Vision and Natural Language Processing: Recent Approaches in Multimedia and Robotics PERATHAM WIRIYATHAMMABHUM, University of Maryland, College Park DOUGLAS SUMMERS-STAY, US …

Transition-Based Technique for Syntactic Linearization and Deep Input Linearization
RS Puduppully – 2017 – web2py.iiit.ac.in
Page 1. Transition-Based Technique for Syntactic Linearization and Deep Input Linearization Thesis submitted in partial fulfillment of the requirements for the degree of MS by Research in Computer Science by Ratish Surendran Puduppully 201407662 …

Modeling common sense knowledge via scripts
A Modi – 2017 – publikationen.sulb.uni-saarland.de
Page 1. Modeling Common Sense Knowledge via Scripts UNIVERSITÄT DES SAARLANDES Ashutosh Modi A dissertation submitted towards the degree Doctor of Engineering of the Faculty of Mathematics and Computer Science of Saarland University Saarbrücken, July 2017 …

Learning to A end, Copy, and Generate for Session-Based ery Suggestion
M Dehghani, S Rothe, E Alfonseca, P Fleury – 2017 – pdfs.semanticscholar.org
Page 1. Learning to A end, Copy, and Generate for Session-Based ery Suggestion Mostafa Dehghani? University of Amsterdam dehghani@uva.nl Sascha Rothe Google Research rothe@google.com Enrique Alfonseca Google Research ealfonseca@google.com …

Nonrecurrent Neural Structure for Long-Term Dependence
S Zhang, C Liu, H Jiang, S Wei, L Dai… – IEEE/ACM Transactions …, 2017 – ieeexplore.ieee.org
… We have evaluated the FSMNs in several standard benchmark tasks, including speech recognition and language modeling … Index Terms—CFSMN, Deep neural networks, feedforward se- quential memory networks, language modeling, speech recogni- tion. I. INTRODUCTION …

Toward Human Parity in Conversational Speech Recognition
W Xiong, J Droppo, X Huang, F Seide… – … on Audio, Speech …, 2017 – ieeexplore.ieee.org
… performance is the use of various convolutional and long-short-term memory acous- tic model architectures, combined with a novel spatial smoothing method and lattice-free discriminative acoustic training, multiple recurrent neural network language modeling approaches, and …

Maximum-a-Posteriori-Based Decoding for End-to-End Acoustic Models
N Kanda, X Lu, H Kawai – IEEE/ACM Transactions on Audio …, 2017 – ieeexplore.ieee.org
… VOL. 25, NO. 5, MAY 2017 conventional language modeling techniques, such as N-gram or RNN. An SWLM can be trained by the training label for end-to-end AMs. The term Pr(s|W) is a word-subword conversion proba- bility …

End-to-End Trainable Chatbot for Restaurant Recommendations
A Strigér – 2017 – diva-portal.org
… [4] has a similar structure. RNNs are commonly used for language modeling. RNNs are a type of neural networks that are specialized in processing sequential data, such as text [5, Ch. 10] … [24]. This model uses two encoder RNNs and one decoder to model a dialog system …

Deep Memory Networks for Natural Conversations
??? – 2017 – s-space.snu.ac.kr
… 11 it to tasks as diverse as (synthetic) question answering (Weston et al., 2015b) and to language modeling … An example is the popular N-gram model used for statistical language modeling – today, it is possible to train N-grams on virtually all available data (Brants et al., 2007) …

Emotion Recognition: A Literature Survey
S Goyal, N Tiwari – International Journal For Technological Research In … – ijtre.com
… Goal: artificial intelligence, robotics, psychology blogs, product reviews, CRM and service oriented companies, customer emotion. Applications: automatic answering systems, dialogue systems, and human like robots. Multi- Language Text …

Deriving and Exploiting Situational Information in Speech: Investigations in a Simulated Search and Rescue Scenario
S Mokaram Ghotoorlar – 2017 – etheses.whiterose.ac.uk
Page 1. Deriving and Exploiting Situational Information in Speech: Investigations in a Simulated Search and Rescue Scenario Saeid Mokaram Department of Computer Science The University of Sheffield PhD Thesis submitted for the degree of Doctor of Philosophy …

Information Retrieval Models: Trends and Techniques
S Krishnamurthy, V Akila – Web Semantics for Textual and Visual …, 2017 – igi-global.com
… It is mostly adopted in many systems like library OPAC’s, dialog systems and few search engines. Example … The queries are evaluated using the language modeling estimates instead of the statistical estimates (tf-idf estimates) …

Automatic Generation of News Comments Based on Gated Attention Neural Networks
HT Zheng, W Wang, W Chen, JY Chen… – IEEE …, 2017 – ieeexplore.ieee.org
… of NLG have been applied successfully in some fields, such as automatic generation of news [2], weather reports [3] and questions [4]. Recently Recurrent Neural Networks (RNN) has shown promising performance in textual generation [5], [6], [7] and language modeling [8], [9 …

Robust Recognition of Noisy Speech Through Partial Imputation of Missing Data
KE Kafoori, SM Ahadi – Circuits, Systems, and Signal Processing, 2017 – Springer
Page 1. Circuits Syst Signal Process DOI 10.1007/s00034-017-0616-4 Robust Recognition of Noisy Speech Through Partial Imputation of Missing Data Kian Ebrahim Kafoori1 · Seyed Mohammad Ahadi1 Received: 21 September …

Methods and Techniques for Clinical Text Modeling and Analytics
Y Ling – 2017 – search.proquest.com
Methods and Techniques for Clinical Text Modeling and Analytics. Abstract. This study focuses on developing and applying methods/techniques in different aspects of the system for clinical text understanding, at both corpus and document level …

Synthesizing normalized faces from facial identity features
F Cole, D Belanger, D Krishnan, A Sarna… – IEEE Conference on …, 2017 – arxiv.org
… to a complete characterization of the maximum secret key rate achievable under a constraint on the total discussion rate. arXiv:1701.05011 [pdf, ps, other] Title: Assessing User Expertise in Spoken Dialog System Interactions …

Multi-behavioral sequential prediction with recurrent log-bilinear model
Q Liu, S Wu, L Wang – IEEE Transactions on Knowledge and …, 2017 – ieeexplore.ieee.org
Page 1. Multi-Behavioral Sequential Prediction with Recurrent Log-Bilinear Model Qiang Liu, Shu Wu, Member, IEEE, and Liang Wang, Senior Member, IEEE Abstract—With the rapid growth of Internet applications, sequential …

Sabbiu Shah (070/BCT/531) Sagar Adhikari (070/BCT/533) Samip Subedi (070/BCT/536)
U Chalise – 2017 – researchgate.net
… Chatterbots are typically used in dialog systems for various practical purposes including customer service or information acquisition … language tasks, for example in language modeling, parsing, and many others. 3.1.2. Major Tasks …

Neural Models for Information Retrieval
B Mitra, N Craswell – arXiv preprint arXiv:1705.01509, 2017 – arxiv.org
… 8 Page 9. Language modelling (LM) In the language modelling based approach [79, 161, 230], documents are ranked by the posterior probability p(d|q). p(d|q) = p(q|d).p(d) ? ¯d?D p(q| ¯d).p( ¯d) ? p(q|d).p(d) (9) = p(q|d) , assuming p(d) is uniform (10) = ? tq ?q p(tq|d) (11) …

LEARNING LOGIC RULES FROM TEXT USING STATISTICAL METHODS FOR NATURAL LANGUAGE PROCESSING
M KAZMI – 2017 – peterschueller.com
Page 1. LEARNING LOGIC RULES FROM TEXT USING STATISTICAL METHODS FOR NATURAL LANGUAGE PROCESSING by MISHAL KAZMI Submitted to the Graduate School of Engineering and Natural Sciences in Partial Fulfillment of the Requirements for the Degree of …

Neural machine translation and sequence-to-sequence models: A tutorial
G Neubig – arXiv preprint arXiv:1703.01619, 2017 – arxiv.org
… T term in our original LM joint probability in Equation 3. In this example, when we have ?/s? as the 4th word in the sentence, we know we’re done and our final sentence length is 3. Once we have the formulation in Equation 4, the problem of language modeling now becomes a …

ALBAYZIN 2016 spoken term detection evaluation: an international open competitive evaluation in Spanish
J Tejedor, DT Toledano… – EURASIP …, 2017 – asmp-eurasipjournals.springeropen …
Skip to main content …

Unsupervised feature learning based on deep models for environmental audio tagging
Y Xu, Q Huang, W Wang, P Foster… – … on Audio, Speech …, 2017 – ieeexplore.ieee.org
Page 1. 1230 IEEE/ACM TRANSACTIONS ON AUDIO, SPEECH, AND LANGUAGE PROCESSING, VOL. 25, NO. 6, JUNE 2017 Unsupervised Feature Learning Based on Deep Models for Environmental Audio Tagging Yong …

Reasoning Schemes, Expert Opinions and Critical Questions. Sex Offenders Case Study
DM Gabbay, G Rozenberg – The IfCoLog Journal of Logics and their …, 2017 – orbilu.uni.lu
Page 1. Reasoning Schemes, Expert Opinion and Critical Questions. Sex Offenders Case Study Dov Gabbay Ashkelon Academic College, Bar Ilan University, King’s College London, University of Luxembourg, University of Manchester dov.gabbay@kcl.ac.uk …

Towards Building a Shallow Parsing Pipeline for English-Telugu Code Mixed Social Media Data
K Nelakuditi – 2017 – web2py.iiit.ac.in
Page 1. Towards Building a Shallow Parsing Pipeline for English-Telugu Code Mixed Social Media Data Thesis submitted in partial fulfillment of the requirements for the degree of MS by Research in Computational Linguistics by Kovida Nelakuditi 201125226 …

End-to-End Online Speech Recognition with Recurrent Neural Networks
K Hwang – 2017 – s-space.snu.ac.kr
… cases, a large amount of additional text data is used to improve the language modeling performance. 1 … speech recognition (ISR) [12], is more focused on the decoding latency, and usually employed for real-time applications such as spoken dialog systems or real-time auto …

A New Classification Framework to Evaluate the Entity Profiling on the Web: Past, Present and Future
AA Barforoush, H Shirazi, H Emami – ACM Computing Surveys (CSUR), 2017 – dl.acm.org
… representation models. For example, for knowledge base ac- celeration (KBA) task, Frank et al. [2014] often employed language modeling format. Some others employed a combination of different representation schemas. For …

Helping users learn about social processes while learning from users: developing a positive feedback in social computing
VSS Pillutla – 2017 – search.proquest.com
… 27. 2.14 Document retrieval timeline showing vector space models [137], BM25 [125],. language modeling approach [115], and KL divergence retrieval technique [93].. . 28 … in turn. Then we will explain language modeling approaches such as the query likelihood model …

Towards efficient Neural Machine Translation for Indian Languages
R Agrawal – 2017 – pdfs.semanticscholar.org
… The end-to-end nature of the training phase is also very conducive when dealing with sequences of unknown lengths beforehand, thereby making neural models an appropriate choice for other tasks like chatbots, speech recognition, dialogue systems, time series, question …

Schedule Highlights
P Sturm – Machine Learning, 2017 – pdfs.semanticscholar.org
… Research community challenge tasks are proliferating, including the sixth Dialog Systems Technology Challenge (DSTC6), the Amazon Alexa prize, and the Conversational Intelligence Challenge live competition at NIPS 2017 …

Automatic Text Simplification
H Saggion – Synthesis Lectures on Human Language …, 2017 – morganclaypool.com
… Semantic Role Labeling Martha Palmer, Daniel Gildea, and Nianwen Xue 2010 Spoken Dialogue Systems Kristiina Jokinen and Michael McTear 2009 Introduction to Chinese Natural Language Processing Kam-Fai Wong, Wenjie Li, Ruifeng Xu, and Zheng-sheng Zhang 2009 …

Linguistic Knowledge Transfer for Enriching Vector Representations
JK Kim – 2017 – rave.ohiolink.edu
… BLSTMs for language-specific representations. The cross-lingual model is trained with language-adversarial training and bidirectional language modeling as auxiliary objectives to better represent language-general information while not losing the information about a …

Finite state models for recognition and validation of read prompts
A Rouhe – 2017 – aaltodoc.aalto.fi
… 13 2.4.4 Gaussian mixture models . . . . . 13 2.4.5 Deep neural networks in acoustic modeling . . . . . 16 2.5 Language modeling . . . . . 18 2.5.1 N-gram models …

Noise Robust Automatic Speech Recognition Based on Spectro-Temporal Techniques
G Kovács – 2017 – doktori.bibl.u-szeged.hu
… From dictating systems to voice translation, from digital assistants like Siri, Google Now, and Cortana, to telephone dialogue systems. Many of these applications have to rely on an Automatic Speech Recognition (ASR) component … 24 1.5 Language Modelling …

(Visited 75 times, 1 visits today)