Neural Network & Dialog Systems 2014


Neural Network & Dialog Systems

Notes:

A statistical language model is a probability distribution over sequences of words.

  • Deep neural network,17
  • Recurrent neural network,10
  • Neural network language model,6
  • Convolutional neural network,3

Resources:

  • ijcnn.org .. International Joint Conference on Neural Networks

Wikipedia:

References:

See also:

100 Best GoogleCode: Neural Network100 Best Java Neural Network Videos100 Best MATLAB Neural Network Videos100 Best Neural Network Training Videos100 Best Neural Network VideosAutomatic Summarization & Neural Networks 2014Best Convolutional Neural Network VideosBest Recurrent Neural Network VideosCNN (Convolutional Neural Network) & Natural Language 2014DNN (Deep Neural Network) & Human Language Technology 2014PNN (Probabilistic Neural Network) & Dialog SystemsRNN (Recurrent Neural Network) & Dialog Systems 2014Word2vec Neural Network


Leveraging frame semantics and distributional semantics for unsupervised semantic slot induction in spoken dialogue systems YN Chen, WY Wang, AI Rudnicky – … Technology Workshop (SLT …, 2014 – ieeexplore.ieee.org … web search and browse sessions for multi-turn spoken dialog systems,” in Proceedings of … in Proceedings of the 48th Annual Meeting of the As- sociation for Computational Linguistics. … Lukas Burget, Jan Cernock`y, and Sanjeev Khudanpur, “Recurrent neural network based lan … Cited by 9 Related articles All 6 versions

Web-style ranking and SLU combination for dialog state tracking JD Williams – 15th Annual Meeting of the Special Interest Group on …, 2014 – aclweb.org … 2013b. Deep neural network approach for the dialog state tracking challenge. … 2013. Discriminative state tracking for spoken dialog systems. In Proc Association for Computational Linguistics, Sofia. Blaise Thomson and Steve Young. 2010. … Cited by 20 Related articles All 13 versions

Word-based dialog state tracking with recurrent neural networks M Henderson, B Thomson… – 15th Annual Meeting of …, 2014 – anthology.aclweb.org … cO2014 Association for Computational Linguistics Word-Based Dialog State Tracking with Recurrent Neural … The method is based on a recurrent neural network structure which is capable of … While communicating with a user, statistical spo- ken dialog systems must maintain a … Cited by 16 Related articles All 12 versions

Markovian discriminative modeling for dialog state tracking H Ren, W Xu, Y Yan – 15th Annual Meeting of the Special …, 2014 – anthology.aclweb.org … Matthew Henderson, Blaise Thomson, and Steve Young. 2013. Deep neural network approach for the dialog state tracking challenge. … Association for Computational Linguistics. Jason Williams. 2012. A critical analysis of two statistical spoken dialog systems in public use. … Cited by 3 Related articles All 8 versions

Learning situated knowledge bases through dialog A Pappu, AI Rudnicky – Proceedings of the 15th …, 2014 – mazsola.iit.uni-miskolc.hu … rich stern: deep neural networks, speech recognition, signal processing, neural networks, machine learning … of names using speak and spell mode in spoken dialogue systems,” in Proceedings … of the iNorth American Chapter of the Association for Computational Linguistics on Hu … Cited by 3 Related articles All 5 versions

Knowledge acquisition strategies for goal-oriented dialog systems A Pappu, AI Rudnicky – Proceedings of the 15th SIGDIAL Conference, 2014 – aclweb.org … cO2014 Association for Computational Linguistics Knowledge Acquisition Strategies for Goal-Oriented Dialog … to be a promising technique for continuous learning in spoken dialog systems. … System Predicted Researcher-Interests 1 rich stern deep neural networks, speech recog … Cited by 2 Related articles All 9 versions

The SJTU system for dialog state tracking challenge 2 K Sun, L Chen, S Zhu, K Yu – 15th Annual Meeting of the Special Interest …, 2014 – aclweb.org … cO2014 Association for Computational Linguistics The SJTU System for Dialog State Tracking Challenge 2 Kai … a rule- based model, a maximum entropy and a deep neural network model. … 1 Introduction Dialog state tracking is important because spo- ken dialog systems rely on … Cited by 8 Related articles All 8 versions

Reranked aligners for interactive transcript correction B Favre, M Rouvier, F Bechet – Acoustics, Speech and Signal …, 2014 – ieeexplore.ieee.org … original, with clarification • Min, max and mean word-level score given by a Recurrent Neural Network language model … dialogue sys- tems by means of implicit recovery of asr errors,” in Spo- ken Dialogue Systems for Ambient … Association for Computational Linguistics, 2008, pp. … Cited by 1 Related articles All 4 versions

Neural network language models for off-line handwriting recognition F Zamora-Martínez, V Frinken, S España-Boquera… – Pattern Recognition, 2014 – Elsevier … Keywords. Handwritten text recognition (HTR); Language models (LMs); Neural networks (NNs); Neural network language model (NN LM); Bidirectional long short-term memory neural networks (BLSTM); Hybrid HMM/ANN models; ROVER combination. 1. Introduction. … Cited by 10 Related articles All 7 versions

Wikipedia-based Kernels for Dialogue Topic Tracking S Kim, RE Banchs, H Li – Proceedings of ICASSP, 2014 – rbanchs.com … against out-of-grammar utterances in multi- domain spoken dialogue system.,” in Proceedings of … in Proceedings of the 19th international conference on Computational linguistics (COLING), 2002 … Topic identification in natu- ral language dialogues using neural networks,” in Pro … Cited by 2 Related articles All 3 versions

A Comprehensive Study on Natural Language Processing and Natural Language Interface to Databases U Shafique, H Qaiser – International Journal of Innovation and …, 2014 – researchgate.net … Recent researches in computational linguistics indicates that empirical or corpus based approach is … As human language has capabilities that are based on neural network in the … Translation, Information Retrieval (IR), Information Extraction (IE), Dialogue Systems and Question … Cited by 1 Related articles All 2 versions

Hypotheses ranking for robust domain classification and tracking in dialogue systems JP Robichaud, PA Crook, P Xu… – Proc. of …, 2014 – mazsola.iit.uni-miskolc.hu … defined.” Originally applied to neural network models, Lambda Rank was later applied to … in Proceedings of the 23rd International Conference on Computational Linguistics (COL- ING … for recognition and classification of speech input in conversational dialogue systems.” in IEEE … Cited by 3 Related articles All 10 versions

Statistical script learning with multi-argument events K Pichotta, RJ Mooney – EACL 2014, 2014 – aclweb.org … cO2014 Association for Computational Linguistics Statistical Script Learning with Multi-Argument Events Karl … Miikkulainen (1990; 1993) gives a hi- erarchical Neural Network system which stores … domain-specific human-human dia- log for building dialog systems (Bangalore et … Cited by 5 Related articles All 9 versions

Improving deep neural network acoustic modeling for audio corpus indexing under the IARPA babel program X Cui, B Kingsbury, J Cui… – submitted to …, 2014 – mazsola.iit.uni-miskolc.hu … of delta pitch for speaker-change prediction in conversational dialogue systems,” ICASSP 2008 … X. Cui, A. Rosenberg, B. Kingsbury1, A. Sethy, “Recent improvements in neural network acoustic mod … The 52nd Annual Meeting of the Association for Computational Linguistics, 2014 … Cited by 3 Related articles All 4 versions

A historical perspective of speech recognition X Huang, J Baker, R Reddy – Communications of the ACM, 2014 – dl.acm.org … Carnegie Mellon University. 27. Mikolov, T. et al. Extensions of recurrent neural network language model. … Computational Linguistics 18, 1 (1992), 61–86. 36. … 42. Williams, J. and Young, S. Partially observable Markov decision processes for spoken dialog systems. … Cited by 19 Related articles All 3 versions

Word embeddings: A semi-supervised learning method for slot-filling in spoken dialog systems X Yang, Z Chen, J Liu – Chinese Spoken Language Processing …, 2014 – ieeexplore.ieee.org … Consequently the three-layer neural network is trained, with a goal that the score g(s, d) is bigger than g(s? … able to do significantly better slot filling on a noisy text, which is a promising setting for spoken dialog systems in real … Associa- tion for Computational Linguistics, 2010, pp. … Related articles

Bootstrapping Dialog Systems with Word Embeddings G Forgues, J Pineau, JM Larchevêque, R Tremblay – cs.cmu.edu … We accordingly focus on improving dialog systems in their early stages when very little … A unified architecture for natural language processing: Deep neural networks with multitask learning. … of the 50th Annual Meeting of the Association for Computational Linguistics, 2012 [7] Q … Related articles

A Proposal for Processing and Fusioning Multiple Information Sources in Multimodal Dialog Systems D Griol, JM Molina, J García-Herrero – Highlights of Practical Applications …, 2014 – Springer … and has been more precisely analyzed and widely adopted within computational linguistics (eg [26]). … L., Segarra, E., Sanchis, E.: A Statistical Approach to Spoken Dialog Systems Design and … Dai, X., Khorram, S.: Data fusion using artificial neural networks: a case study on … Related articles All 3 versions

IBM’s Belief Tracker: Results On Dialog State Tracking Challenge Datasets R Kadlec, J Libovický, J Macek, J Kleindienst – EACL 2014, 2014 – anthology.aclweb.org … Thus it might be beneficial to use a generative tracker for a newly deployed dialog system with only a few training dialogs available and switch to a discriminative … Deep neural network approach for the dialog state tracking challenge. … Association for Computational Linguistics. … Cited by 1 All 6 versions

The Social Psychology of Dialogue Simulation as Applied in Elbot F Roberts – International Journal of Synthetic Emotions (IJSE), 2014 – igi-global.com … The Social Psychology Of Dialogue Simulation As Applied In Elbot. The history of dialogue systems spans the decades, beginning with Joseph Weizenbaum’s classic Eliza designed in 1966 and ending with the multitude of systemic approaches available today. …

Semi-supervised learning of dialogue acts using sentence similarity based on word embeddings X Yang, J Liu, Z Chen, W Wu – Audio, Language and Image …, 2014 – ieeexplore.ieee.org … An important task in spoken dialog systems is dialog act modeling which determines the dialogue … There- fore we choose the neural network in the figure[12] to train word … act modeling for automatic tagging and recognition of conversational speech,” Computational linguistics, vol … Related articles

A Composite Kernel Approach for Dialog Topic Tracking with Structured Domain Knowledge from Wikipedia S Kim, RE Banchs, H Li – anthology.aclweb.org … In Pro- ceedings of the 40th annual meeting on association for computational linguistics, pages 263 … ro- bust domain selection against out-of-grammar utter- ances in multi-domain spoken dialogue system. … Topic identification in natural language dialogues using neural networks. … Cited by 1 Related articles All 7 versions

Alex: Bootstrapping a Spoken Dialogue System for a New Domain by Real Users O Dušek, O Plátek, L Žilka… – 15th Annual Meeting of …, 2014 – anthology.aclweb.org … cO2014 Association for Computational Linguistics Alex: Bootstrapping a Spoken Dialogue System for a … Our spoken dialogue system framework is freely available on GitHub2 and designed for … hand-written rules or external services: • ASR used a neural network based voice … Cited by 2 Related articles All 8 versions

User Modeling by Using Bag-of-Behaviors for Building a Dialog System Sensitive to the Interlocutor’s Internal State Y Chiba, T Nose, A Ito, M Ito – … of the Special Interest Group on …, 2014 – anthology.aclweb.org … 70.0 Condition (2)+ RBF-SVM 67.7 73.8 70.7 Condition (2)+ MKL-SVM 68.0 76.4 72.0 used as input for a neural network for the … Developing a flexible spoken dialog system using simulation. … the 42nd Annual Meet- ing on Association for Computational Linguistics, pages 63–70. … Related articles All 8 versions

The Dialog State Tracking Challenge Series JD Williams, M Henderson, A Raux, B Thomson… – BE A PART OF …, 2014 – dropline.net … on conditional random fields (Lee and Eskenazi 2013), recurrent neural networks (Henderson, Thomson … Stroudsburg PA: Association for Computational Linguistics. … His interests include spoken dialog systems, planning under uncertainty, spoken language understanding, and … Cited by 1 Related articles All 4 versions

Automatic dialogue act recognition with syntactic features P Král, C Cerisara – Language Resources and Evaluation, 2014 – Springer … combines the advantages of the hidden Markov model approach with those of artificial neural networks. … emission probabilities computed from the output neuron activations of a neural network (such as … module is designed to be used with a rule-based dialogue system that only … Cited by 2 Related articles All 5 versions

Biomedical text mining: State-of-the-art, open problems and future challenges A Holzinger, J Schantl, M Schroettner, C Seifert… – … Discovery and Data …, 2014 – Springer … CH, Chen, MJ: Ontology-based speech act identification in a bilingual dialog system using partial … In: The 2012 International Joint Conference on Neural Networks (IJCNN), pp. … Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics: Long Papers … Cited by 11 Related articles All 5 versions

Extraction of Salient Sentences from Labelled Documents M Denil, A Demiraj, N de Freitas – arXiv preprint arXiv:1412.6815, 2014 – arxiv.org … et al., 2014; Hermann & Blunsom, 2014), question answering (Bordes et al., 2014; Weston et al., 2014), dialogue systems (Kalchbrenner & … Fast and Robust Neural Network Joint Models for Statistical Machine Translation. In Association for Computational Linguistics, 2014. … Cited by 4 Related articles All 3 versions

Multimodal analytics and its data ecosystem M Koutsombogera, H Papageorgiou – Proceedings of the 2014 …, 2014 – dl.acm.org … of the different modalities involved in human-computer interaction and multimodal dialogue systems [3, 9 … New types of deep neural network learning for speech recognition and related applications … In Proceedings of the ACL 51, Association for Computational Linguistics, 973-982 … Cited by 1 Related articles All 3 versions

Markovian discriminative modeling for cross-domain dialog state tracking H Ren, W Xu, Y Yan – Spoken Language Technology …, 2014 – ieeexplore.ieee.org … In [12] it has been shown that a neural network model with two hidden layers is … [2] Jason Williams, “A critical analysis of two statistical spoken dialog systems in public … tems,” in Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics (Volume 1 … Cited by 1 Related articles

Comparing Open-Source Speech Recognition Toolkits? C Gaida, P Lange, R Petrick, P Proba, A Malatawy… – 2014 – sinaidiagnostics.com … the project is to increase spoken language understanding performance in spoken dialog systems [17]. … Fur- ther the training of Deep Neural Networks (DNN) on top of GMM models with … HLT ’89, Stroudsburg, PA, USA, Association for Computational Linguistics (1989) 238–242 15 … Cited by 4 Related articles All 11 versions

Conversational entrainment in the use of discourse markers Š Be?uš – Recent Advances of Neural Network Models and …, 2014 – Springer … eds.), Recent Advances of Neural Network Models and … entrainment is thus important for all applications in human- machine communication that rely on Spoken Dialogue Systems. … Computational Linguistics 38(1), 1–39 (2012) 9. Gravano, A., Benus, S., Chávez, H., Hirschberg, … Cited by 2 Related articles All 4 versions

Multimodal interaction: A review M Turk – Pattern Recognition Letters, 2014 – Elsevier People naturally interact with the world multimodally, through both parallel and sequential use of multiple perceptual modalities. Multimodal human–computer i. Cited by 32 Related articles All 5 versions

Representing Syntactic-Semantic Knowledge from English Texts R Guidry Jr, J Chen – … on the International Conference on Artificial …, 2014 – world-comp.org … One can also see the various works in computational linguistics and NLP using, for example, dependency grammars and conceptual dependency graphs (Schank [26]). … Dialogue systems: From theory to practice in TRAINS96 … NLP based on Artificial Neural Networks: Introduction … Related articles All 2 versions

Distributed open-domain conversational understanding framework with domain independent extractors Q Li, G Tur, D Hakkani-Tur, X Li, T Paek… – … (SLT), 2014 IEEE, 2014 – ieeexplore.ieee.org … B. Renger, D. Gibbon, Z. Liu, and B. Shahraray, “Bootstrapping spoken dialogue systems by exploiting … TINA: A natural language system for spoken language applications,” Computational Linguistics, vol. … 28] P. Xu and R. Sarikaya, “Convolutional neural network based triangular … Cited by 2 Related articles All 3 versions

Improving Domain-independent Cloud-based Speech Recognition with Domain-dependent Phonetic Post-processing J Twiefel, T Baumann… – Twenty-Eighth …, 2014 – nats-www.informatik.uni-hamburg.de … in terms of their applicability for develop- ing domain-restricted dialogue systems. … Application of pretrained deep neural networks to large vocabulary speech recognition. … Processing: An Introduction to Natural Language Process- ing, Computational Linguistics, and Speech … Cited by 5 Related articles All 5 versions

Reinforcement learning of cooperative persuasive dialogue policies using framing T Hiraoka, G Neubig, S Sakti, T Toda… – Proceedings …, 2014 – anthology.aclweb.org Proceedings of COLING 2014, the 25th International Conference on Computational Linguistics: Technical Papers … Guser is not usually observable because traditional dialogue systems have automatic speech … of nodes in the hidden layer of the neural network for approximating … Cited by 2 Related articles All 7 versions

Towards a differential diagnostic of PTSD using cognitive computing methods N Howard, L Jehel, R Arnal – Cognitive Informatics & Cognitive …, 2014 – ieeexplore.ieee.org … In this paper, we link recent advances in computational linguistics and language-based mind state analysis to PTSD factors and demonstrate its potential as a new, more definitive diagnostic and differentiation method … 2013) introduce an adaptive dialogue system for assessment … Related articles All 3 versions

Semantic Similarity Calculation of Short Texts Based on Language Network and Word Semantic Information Z Zhan, F Lin, X Yang – Advanced Computer Architecture, 2014 – Springer … it also has important applications in health advisory dialogue system [5], property … data mining, machine learning, pattern recognition, artificial intelligence, statistics, computational linguistics, compute network … used in life sciences[13], stress media[14], neural networks[15], space … Related articles All 3 versions

An attribute detection based approach to automatic speech processing SM Siniscalchi, CH Lee – Loquens, 2014 – loquens.revistas.csic.es … to as a CM, serves as a reference guide for the dialogue system to provide an … demonstrated that phone accuracies can be boosted using a deep neural network (Deng & … on a large Mandarin read speech corpus TCC300 (Association for Computational Linguistics and Chinese … Related articles

Combining visual recognition and computational linguistics: linguistic knowledge for visual recognition and natural language descriptions of visual content M Rohrbach – 2014 – scidok.sulb.uni-saarland.de … and Computational Linguistics Linguistic Knowledge for Visual Recognition … On the other side, computational linguistics faces the challenge to understand external references from text representations alone while they might be visually observable. … Related articles All 4 versions

Taking Antonymy Mask off in Vector Space E Santus, Q Lu, A Lenci, CR Huang – 2014 – anthology.aclweb.org … Retrieval (IR), Ontology Learning (OL), Machine Translation (MT), Sentiment Analysis (SA) and Dialogue Systems (Roth and … Kim and de Marneffe (2013) exploited word vectors learned by Neural Network Language Models (NNLMs) to … Computational Linguistics, 36(4):673–721 … Cited by 2 Related articles All 9 versions

Spoken Language Processing: Time to Look Outside? RK Moore – Statistical Language and Speech Processing, 2014 – Springer … A., Vanhoucke, V., Nguyen, P., Sainath, TN, Kingsbury, B.: Deep neural networks for acoustic … Conference of the European Chapter of the Association for Computational Linguistics (EACL-09 … Hastie, H., Lemon, O., Dethlefs, N.: Incremental spoken dialogue systems: tools and … Cited by 3 Related articles All 2 versions

Unsupervised Induction of Semantic Roles within a Reconstruction-Error Minimization Framework I Titov, E Khoddam – arXiv preprint arXiv:1412.2812, 2014 – arxiv.org … textual entailment [46], machine translation [57, 36, 56, 21], and dialogue systems [5, 53 … One alternative, popular in the neural network community, is to instead use autoencoders … of the Thirty-Sixth Annual Meeting of the Association for Computational Linguistics and Seventeenth … Related articles All 3 versions

Optimizing Generative Dialog State Tracker via Cascading Gradient Descent BJ Lee, W Lim, D Kim, KE Kim – 15th Annual Meeting of the …, 2014 – anthology.aclweb.org … cO2014 Association for Computational Linguistics Optimizing Generative Dialog State Tracker via Cascading Gradient … 1 Introduction Spoken dialog systems, a field rapidly growing with the spread of smart … over weighted features, which is in other words a neural network with no … Cited by 4 Related articles All 10 versions

Adaptive cognitive technical systems F Putze, T Schultz – Journal of neuroscience methods, 2014 – Elsevier … Experimental results indicated that subjective and objective criteria, such as driving quality, improved when the dialog system adapted its voice … multi-attribute task battery, using six EEG channels and other physiological sensors, combined in a neural network for classification. … Cited by 1 Related articles All 4 versions

Speak Correct: Phonetic Editor Approach H Al-Barhamtoshy, K Jambi, W Al-Jedaibi… – Life Science …, 2014 – researchgate.net … used to map the observation vector Otto a probability, and neural networks or multi … The structure of the probabilistic neural network model includes the number of input speech … Weighted Finite State and Weighted ATN/Lattice Computational linguistics and automata theory have … Related articles All 3 versions

Speech-Based Emotion Recognition: Feature Selection by Self-Adaptive Multi-Criteria Genetic Algorithm M Sidorov, C Brester, W Minker… – … Conference on Language …, 2014 – lrec-conf.org … opportunity might be useful in various applications, including improvement of the spoken dialogue systems (SDSs) performance … emotion recognition using fcbf fea- ture selection method and ga-optimized fuzzy artmap neural network. … Asso- ciation for Computational Linguistics. … Cited by 4 Related articles

Situated Incremental Natural Language Understanding using a Multimodal, Linguistically-driven Update Model C Kennington, S Kousidis, D Schlangen – Proceedings of CoLing, 2014 – aclweb.org … forms (Zettlemoyer and Collins, 2007; Zettlemoyer and Collins, 2009), dependency-based compositional semantics (Liang et al., 2011), neural networks (Huang and … Association for Computational Linguistics. … 2010. Towards Incremental Speech Generation in Dialogue Systems. … Cited by 2 Related articles All 6 versions

Emotional Intelligence and Agents: Survey and Possible Applications M Ivanovi?, M Radovanovi?, Z Budimac… – Proceedings of the 4th …, 2014 – dl.acm.org … than when only a single approach is used, while the authors of [9] have pro- posed a neural network-based approach … Emotion detection in dialog systems: Applications, strategies and challenges. … Computational Linguistics and Chinese Language Processing, 9(2):45–62, 2004. … Related articles All 7 versions

Adjective-Based Estimation of Short Sentence’s Impression NTT An, M Hagiwara – ep.liu.se Page 1. KEER2014, LINKÖPING | JUNE 11-13 2014 INTERNATIONAL CONFERENCE ON KANSEI ENGINEERING AND EMOTION RESEARCH Adjective-Based Estimation of Short Sentence’s Impression Nguyen Thi Thu An1, Masafumi Hagiwara2 … Related articles

Two-phase reanalysis model for understanding user intention S Kang, J Seo – Pattern Recognition Letters, 2014 – Elsevier … A conventional dialogue system consists of the following components: natural language understanding, dialogue management … a two-step SA analysis model by means of neural networks: in the … of useful features is established, and in the second step, a neural network without a … Related articles All 2 versions

Dynamically supporting unexplored domains in conversational interactions by enriching semantics with neural word embeddings YN Chen, A Rudnicky – Spoken Language Technology …, 2014 – ieeexplore.ieee.org … Unsupervised induction and filling of semantic slots for spoken dialogue systems using frame … Schneider, and Noah A. Smith, “Frame-semantic parsing,” Computational Linguistics, 2013 … Lukas Burget, Jan Cernock`y, and Sanjeev Khudanpur, “Recurrent neural network based lan … Cited by 9 Related articles All 4 versions

Dialogue Act Recognition Using Probabilistic Networks And Ranking Feature Selection Approaches AA Yahya, AR Ramli – researchgate.net … For instance, the speaker’s utterance “Can you reserve three tickets for me?” to the dialogue system is interpreted as if a user questioning its ability … approaches have also been investigated such as neural networks [14], transformation-based learning [21], and decision trees [25]. … Related articles

Automatic scoring for answers to Arabic test questions WH Gomaa, AA Fahmy – Computer Speech & Language, 2014 – Elsevier … system focuses mainly on measuring the similarity between the student and the model answers using a bag of words (BOW) model and disregarding complex Arabic computational linguistics tasks. … It has been used in the tutorial dialog system Why2-Atlas (VanLehn et al., 2002). … Cited by 4 Related articles All 4 versions

Translation rescoring through recurrent neural network language models Á PERIS ABRIL – 2014 – riunet.upv.es … Recurrent neural network unfolded in time. . … NLP) is a knowledge field of Artificial In- telligence and Computational Linguistics, concerned with … and understanding, speech recognition, topic segmentation and recognition, information retrieval, dialog systems, question answering … Related articles All 2 versions

Formal semantics for perceptual classification PREPRINT VERSION S Larsson – researchgate.net … There are already computational models of neural networks acting as classifiers con- nected to linguistic expressions (colour terms), including learning of perceptual aspects of meaning (Steels and Belpaeme, 2005), but these models do not attempt to connect to the formal … Related articles All 2 versions

Personal knowledge graph population from user utterances in conversational understanding X Li, G Tur, D Hakkani-Tur, Q Li – … Technology Workshop (SLT), …, 2014 – ieeexplore.ieee.org … data with web search queries which are inquiring similar information as dialog system users. … S. Seneff, “TINA: A natural language system for spoken language applications,” Computational Linguistics, vol … 27] P. Xu and R. Sarikaya, “Convolutional neural network based triangular … Cited by 1 Related articles All 6 versions

Deep learning of knowledge graph embeddings for semantic parsing of twitter dialogs L Heck, H Huang – Signal and Information Processing ( …, 2014 – ieeexplore.ieee.org … In the 1990s, deep neural network methods were developed to automatically discover new … web search and browse sessions for multi-turn spoken dialog systems,” in Proceedings … in Proceedings of the Annual Meeting of the Association of Computational Linguistics (ACL), 2011 … Cited by 2 Related articles All 8 versions

Gaze-enhanced speech recognition M Slaney, R Rajan, A Stolcke… – Acoustics, Speech and …, 2014 – ieeexplore.ieee.org … 6]. The acoustic models incorporate the latest advances in context-dependent deep neural networks (DNN) for … This suggests that dialog systems in- volving selection steps would benefit from gaze. … Association for Computational Linguistics, Stroudsburg, PA, USA, 83–87, 1991. … Cited by 5 Related articles All 9 versions

Knowledge-based Dialog State Tracking R Kadlec, M Vodolan, J Libovicky… – … (SLT), 2014 IEEE, 2014 – ieeexplore.ieee.org … Or a neural network that can encode even more complex behaviors used in [12]. IX. … of the AMI Workshop on Statistical and Empirical Methods in Spoken Dialogue Systems, 2006. … Metz, France: Association for Computational Linguistics, August 2013, pp. 414-422. … Cited by 4 Related articles

Resolving referring expressions in conversational dialogs for natural user interfaces A Celikyilmaz, Z Feizollahi… – Proceedings of …, 2014 – anthology.aclweb.org … cO2014 Association for Computational Linguistics … Unlike traditional over-the-phone spoken dialog systems (SDSs), modern dialog systems tend to have visual rendering on the device screen as an additional modal- ity to communicate the system’s response to the user. … Cited by 3 Related articles All 8 versions

KWSnet Robots/Robotics Index KW Smith – 2014 – kwsnet.com … Specific interests include vector space models, dialogue systems, unsupervised grammar induction … and animal behavior, and the application of neural network architectures to … many contributions to AI, cognitive psychology, mathematics, computational linguistics, robotics, and … All 2 versions

Language Learning via Unsupervised Corpus Analysis B Goertzel, C Pennachin, N Geisweiller – Engineering General Intelligence …, 2014 – Springer … Our approach does not use conventional deep learning archi- tectures like Deep Boltzmann machines or recurrent neural networks. … we construct, are guided by existing knowledge about what works and what doesn’t in (both statistical and rule-based) computational linguistics. …

KIT-Conferences PI Lichtblau – 2014 – isl.anthropomatik.kit.edu … Improving Language-Universal Feature Extraction with Deep Maxout and Convolutional Neural Networks, … Optimization of Neural Network Language Models for Keyword Search, … of the European Chapter of the Association for Computational Linguistics (EACL), Gothenborg … All 2 versions

A Model to Incorporate Emotional Sensitivity into Human Computer Interactions S Ramnani, RP Gorthi – Proceedings of the 2014 workshop on Emotion …, 2014 – dl.acm.org … emotive and cognitive learning and decision making capabilities using mainly neural networks. … use of natural language processing, text analysis and computational linguistics to identify … the emotion dynamics of a multimodal conversational agent”.Affective Dialogue Systems. … Related articles All 2 versions

TSVD as a Statistical Estimator in the Latent Semantic Analysis Paradigm G Pilato, G Vassallo – ieeexplore.ieee.org … Many researchers have successfully applied this technique for typical Semantic Computing applications, such as natural language understanding, cognitive modeling, speech recog- nition, smart indexing, anti-spam filters, dialogue systems and other Statistical Natural … Cited by 1 Related articles All 5 versions

User behavior fusion in dialog management with multi-modal history cues M Yang, J Tao, L Chao, H Li, D Zhang, H Che… – Multimedia Tools and …, 2014 – Springer … effective multi-modal behavior fusion model and flexible behavior sensitive DM are necessary for practical human computer dialog systems. … It adopts recurrent neural network architectures which take into account past observations by cyclic connections in the network’s hidden … Cited by 1 Related articles All 2 versions

Modern conversational agents D Suendermann-Oeft – Technologien für digitale Innovationen, 2014 – Springer … N./Zadrozny, W./Melville, P. 2002: Natural Language Assistant–A Dialog System for Online … J./Rollinger, C. 1991: Text Understanding in LILOG: Integrating Computational Linguistics and Artificial … V./Nguyen, P./Sainath, T./Kingsbury, B. 2012: Deep Neural Networks for Acous- tic … Cited by 3 Related articles All 3 versions

A domain-independent statistical methodology for dialog management in spoken dialog systems D Griol, Z Callejas, R López-Cózar… – Computer Speech & …, 2014 – Elsevier … Volume 28, Issue 3, May 2014, Pages 743–768. Cover image Cover image. A domain- independent statistical methodology for dialog management in spoken dialog systems ?. … Highlights. • Dialog systems (DS) allow intuitive interaction through natural language. • … Cited by 9 Related articles All 5 versions

Emoticon Analysis for Chinese Health and Fitness Topics S Yu, H Zhu, S Jiang, H Chen – Smart Health, 2014 – Springer … Nakamura et al. [14] used a neural network-based algorithm to … Kaomojiya, http://kaomojiya.com/ 14. Nakamura, J., Ikeda, T., Inui, N., Kotani, Y.: Learning Face Marks for Natural Language Dialogue Systems. … 43– 48. Association for Computational Linguistics (June 2005) 18. … Related articles All 3 versions

Automatic Dialogue Act Recognition with Syntactic P Král, C Cerisara – Citeseer … combines the advantages of the hidden Markov model approach with those of artificial neural networks. … emission probabilities computed from the output neuron activations of a neural network (such as … module is designed to be used with a rule-based dialogue system that only … Related articles All 4 versions

Semantic language models for Automatic Speech Recognition AO Bayer, G Riccardi – Spoken Language Technology …, 2014 – ieeexplore.ieee.org … models based on long-distance dependencies for a spoken dialog system,” in Proceedings … N. Schneider, and N. Smith, “Frame-semantic parsing,” Computational Linguistics, vol. … JH Cernocky, and Sanjeev Khudanpur, “Extensions of recurrent neural network language model … Cited by 1 Related articles All 3 versions

Heterogeneous networks and their applications: Scientometrics, name disambiguation, and topic modeling B King, R Jha, DR Radev – … for Computational Linguistics, 2014 – tacl2013.cs.columbia.edu … D. Manning ? 26 University of Tokyo ? 5 Computational Linguistics ? 16 dialogue … based attachment model models phrase prepositional disambiguation Dialogue systems dialogue spoken … speech robust recognition real network time neural networks language environments … Cited by 2 Related articles All 13 versions

Cognitively-inspired representational approach to meaning in machine dialogue M Gnjatovi?, V Deli? – Knowledge-Based Systems, 2014 – Elsevier … We report on a framework for end-user programming of adaptive dialogue systems. Abstract. One … etc. Hence, a dialogue system should be able to cope with such dialogue phenomena. The paper is divided in two main parts. … Cited by 3 Related articles All 2 versions

Automatic speech recognition for under-resourced languages: A survey L Besacier, E Barnard, A Karpov, T Schultz – Speech Communication, 2014 – Elsevier … 3.3. Feature processing. In the last few years, Neural Networks showed large potential to improve ASR performance. … (2013) is well suited for deep neural network architectures for ASR (Yu et al., 2012). 3.5. Lexical modeling. 3.5.1. Grapheme-based approaches. … Cited by 34 Related articles All 8 versions

Situated incremental natural language understanding using Markov Logic Networks C Kennington, D Schlangen – Computer Speech & Language, 2014 – Elsevier … 2.1. Statistical nlu. An important part of a dialogue system is the nlu component. … (2011) created dependency-based compositional semantics, and Huang and Er (2010) made use of neural networks as a meaning representation. … Cited by 6 Related articles All 5 versions

Natural Language, Discourse, and Conversational Dialogues within Intelligent Tutoring Systems: A Review K Brawner, A Graesser – Design Recommendations for Intelligent …, 2014 – books.google.com … Computerized learning environments that incorporate research in discourse psychology, cognitive science, and computational linguistics. … Paper presented at the Building Dialogue Systems for Tutorial Applications, Papers of the 2000 AAAI Fall Symposium. … Cited by 3 Related articles All 7 versions

Eye-trackers and Multimodal Communication Studies K Jokinen – Proceedings from the 1st European Symposium on … – ep.liu.se Page 1. Eye-trackers and Multimodal Communication Studies Kristiina Jokinen Institute of Behavioural Sciences University of Helsinki kristiina.jokinen@helsinki.fi Abstract This article provides an overview of eye-tracking technology in multimodal communication studies. … Related articles All 2 versions

An emotion understanding framework for intelligent agents based on episodic and semantic memories M Kazemifard, N Ghasem-Aghaee, BL Koenig… – Autonomous agents and …, 2014 – Springer … As was the case for episodic memory, researchers are still fleshing out how to computationally model semantic memory. Semantic memory has been implemented in Soar [39], in avatars [40], and as a synthetic neural network model [41]. … Cited by 5 Related articles All 7 versions

Theoretical analysis of diversity in an ensemble of automatic speech recognition systems K Audhkhasi, AM Zavou, PG Georgiou… – Audio, Speech, and …, 2014 – ieeexplore.ieee.org … Another common approach is to combine structurally diverse AMs such as based on Gaussian mixture model (GMM) HMMs and deep neural networks (DNNs) [7]. Other works [9]–[14] have used machine learning techniques such as bagging [15], boosting [16], [17] and random … Cited by 9 Related articles All 4 versions

Integration of Multiple Cues for Speech Activity Detection and Word Segmentation P Mikias – honda-ri.de Page 1. Diploma Thesis Integration of Multiple Cues for Speech Activity Detection and Word Segmentation Paschalis Mikias Advised by: Dr.-Ing. Martin Heckmann* Prof. Dr.-Ing. Dorothea Kolossa Dr.-Ing. Steffen Zeiler * Honda Research Institute Europe … Related articles

Scalable summary-state pomdp hybrid dialog system for multiple goal drifting requests and massive slot entity instances S Koo, S Ryu, K Lee, GG Lee – uni-ulm.de … Neural Networks 2007 15th European Symposium on Artificial Neural Networks 2007 6 … H., Young, S.: Agenda-based user simulation for bootstrapping a pomdp dialogue system. … of the North American Chapter of the Association for Computational Linguistics; Companion Volume … Related articles All 2 versions

Alignment to the Actions of a Robot AL Vollmer, KJ Rohlfing, B Wrede… – International Journal of …, 2014 – Springer … (b) Participants interact with the iCub humanoid robot, instead of an artificial computer dialog system. … Alignment toward computers or artificial dialog systems has been identified as similar and even stronger alignment than toward human interlocutors [5,16,33]. … Related articles All 2 versions

[BOOK] Routledge Encyclopedia of Translation Technology S Chan – 2014 – books.google.com … research spans several areas of NLP including dialogue systems, grammar formalisms … His research interests are computational linguistics, linguistic resource and ontology engineering … surface physics, machine learning (especially with neural networks) and automata theory. … Cited by 1 Related articles All 2 versions

A hierarchical probabilistic framework for recognizing learners’ interaction experience trends and emotions I Jraidi, M Chaouachi, C Frasson – Advances in Human-Computer …, 2014 – dl.acm.org … emotional states. The first cat- egory uses conventional classification algorithms including rule-based reasoning [44], support vector machines [42, 45], neural networks [46, 47], and decision trees [48, 49]. These approaches … Cited by 2 Related articles All 4 versions

A unified framework for translation and understanding allowing discriminative joint decoding for multilingual speech semantic interpretation B Jabaian, F Lefèvre, L Besacier – Computer Speech & Language, 2014 – Elsevier … The framework can be generalized to other components of a dialogue system. Abstract. … It has been shown that using lattices as SLU input decreased the classification error rate in the case of the AT&T’s “How May I Help You” dialogue system. In parallel Servan et al. … Cited by 1 Related articles All 5 versions

Learning to rank for information retrieval and natural language processing H Li – Synthesis Lectures on Human Language Technologies, 2014 – morganclaypool.com … page monographs on topics relating to natural language processing, computational linguistics, information retrieval … Spoken Dialogue Systems Kristiina Jokinen and Michael McTear 2009 … employ, such as the SVM based, Boosting based, and Neural Network based approaches. … Cited by 100 Related articles All 27 versions

Computer Engineering and Information Technology EE Editions – 2014 – phindia.com … Neural Networks. … solving, search techniques, intelligent agents, constraint satisfaction problems, knowledge representation, planning, machine learning, natural language processing, pattern recognition, game playing, hybrid and fuzzy systems, neural network-based learning … Related articles All 8 versions

Large vocabulary Russian speech recognition using syntactico-statistical language modeling A Karpov, K Markov, I Kipyatkova, D Vazhenina… – Speech …, 2014 – Elsevier … Artificial neural networks are used for the language modeling. … In (Bechet and Nasr, 2009), a syntactic parser for spontaneous speech recognition outputs is used for identification of verbal sub-categorization frames for dialogue systems and spoken language understanding tasks … Cited by 20 Related articles All 6 versions

Exploiting psychological factors for interaction style recognition in spoken conversation WL Wei, CH Wu, JC Lin, H Li – Audio, Speech, and Language …, 2014 – ieeexplore.ieee.org … RELATED WORK Automatically extracting social meaning and intention from spoken dialogue is a crucial task for dialogue systems and social … An artificial neural network was then adopted to detect interaction style by considering the scores estimated from the aforementioned … Cited by 3 Related articles All 4 versions

An Information Retrieval Approach to Short Text Conversation Z Ji, Z Lu, H Li – arXiv preprint arXiv:1408.6988, 2014 – arxiv.org … An alternative approach is to build a dialogue system with a knowledge base consisting of large number of question-answer pairs. … We propose employing a new deep neural network model, referred to it as deep matching model (DeepMatch) in the paper, to model the … Cited by 3 Related articles All 3 versions

Cross-Domain and Cross-Language Porting of Shallow Parsing E Stepanov – 2014 – eprints-phd.biblio.unitn.it … We have contributed to the optimization with the re-ranking of n-best list of translation hypotheses with the joined Recurrent Neural Network Language Model trained on reference word-concept pairs. An alternative to the cross-language porting of language resource anno- … Related articles

Duration and speed of speech events: A selection of methods D Gibbon, K Klessa, J Bachan – Lingua Posnaniensis, 2014 – degruyter.com Page 1. lingua posnaniensis 2014 lVi (1) Duration and speed of speech events: a selection of methods Dafydd Gibbon1, Katarzyna Klessa2 & Jolanta Bachan2 1 Fakultät für linguistik und literaturwissenschaft, universität Bielefeld … Cited by 1

Combining multiple parallel streams for improved speech processing JTR de Sousa Miranda – 2014 – l2f.inesc-id.pt … is unfamiliar with the task at hand, or needs to have their hands free, dialog systems … led to the use of pre-trained deep neural networks, leading to the HMM-DNN concept [10], … In the tandem approach [24], a neural network is trained to produce posterior probabilities that are … Related articles

[BOOK] The Johns Hopkins guide to digital media ML Ryan, L Emerson, BJ Robertson – 2014 – books.google.com … John Duda Combinatory and Automatic Text Generation Philippe Bootz and Christopher Funkhouser Computational Linguistics Inderjeet Mani … Laure Ryan Cyborg and Posthuman Raine Koskimaa Data Matthew Fuller Database Christiane Paul Dialogue Systems Jichen Zhu … Cited by 5 Related articles All 2 versions

2014 Index IEEE/ACM Transactions on Audio, Speech, and Language Processing Vol. 22 O Abdel-Hamid, T Abhayapala, TD Abhayapala… – ieeexplore.ieee.org … 2014 138-150 Han, K., and Wang, D., Neural Network Based Pitch Tracking … Masking Approach to Noise-Robust Speech Recognition Using Deep Neural Networks; TASLP Aug. … Under Uncertainty: Adaptive Information Pre- sentation for Statistical Dialogue Systems; TASLP May …

Foundations and Trends in Signal Processing L Deng, Y Dong – Signal Processing, 2014 – research.microsoft.com … In the speech recognition lit- erature [42], a system, in which a neural network’s output is directly used to estimate the emission probabilities of an HMM, is often called an ANN/HMM hybrid system. … [154], has been adopted, where the output of the neural networks in the form of … Cited by 2 Related articles All 12 versions

Social Power in Interactions V Prabhakaran – 2014 – cs.columbia.edu … For example, if a dialog system is engineered to behave appropriately given the user’s expectation of relative power, then the user may … the related work in the area of analyzing manifestations of power in interactions, both in social sciences and in computational linguistics. … Related articles

A News Aggregator Using Semantic and Data Mining Technologies AP Ventouris – ikee.lib.auth.gr … The first time that identification of patterns appeared was in 1700s with the Bayes’ Theorem. Since then, many other techniques have been included in data mining like neural networks, cluster analysis, genetic algorithms, decision trees and support vector machines. …

Development and Evaluation of Semantically Constrained Speech Recognition Architectures S Wermter, J Twiefel, T Baumann – 2014 – informatik.uni-hamburg.de … approach. ASR system are able to transform acoustic data to text and can be used for dialogues between humans and machines. In combination with a text- to-speech system, useful dialogue systems can be created. Speech … Related articles

Machine Learning for Social Multiparty Human–Robot Interaction S Keizer, M Ellen Foster, Z Wang… – ACM Transactions on …, 2014 – dl.acm.org Page 1. 14 Machine Learning for Social Multiparty Human–Robot Interaction SIMON KEIZER, MARY ELLEN FOSTER, ZHUORAN WANG, and OLIVER LEMON, Heriot-Watt University We describe a variety of machine-learning … Cited by 3 Related articles All 2 versions

Statistical post-editing and quality estimation for machine translation systems H Bechara – 2014 – doras.dcu.ie … 2012 – H. Béchara, R. Rubino, Y. He, YJ Ma, J. van Genabith. An Evaluation of Statistical Post-editing Systems applied to RBMT and SMT Systems, Conference on Computational Linguistics (COLING), Mumbai, India 7 Page 17. Chapter 2 Machine Translation, … Cited by 2 Related articles All 2 versions

Latent semantic rational kernels for topic spotting on conversational speech C Weng, DL Thomson, P Haffner… – Audio, Speech, and …, 2014 – ieeexplore.ieee.org Page 1. 2329-9290 (c) 2013 IEEE. Personal use is permitted, but republication/ redistribution requires IEEE permission. See http://www.ieee.org/ publications_standards/publications/rights/index.html for more information. This … Related articles All 2 versions

Gaussian processes for POMDP-based dialogue manager optimization M Gasic, S Young – Audio, Speech, and Language Processing, …, 2014 – ieeexplore.ieee.org … Various approximations allow such a model to be used for building real- world dialogue systems. … I. INTRODUCTION SPOKEN dialogue systems enable human-computer inter- action where the primary input is speech. As such they have innumerable benefits. … Cited by 8 Related articles All 5 versions

Statistical Analysis of Interactional Patterns: a Social Signal Processing Perspective A Pesarin – 2014 – researchgate.net … Interestingly, recent neuropsychologi- cal research suggested that communicative perspective-sharing is supported by frontal neural networks that determine the … defined in [20] as the problem of assigning a task category to spoken utterances in task-oriented dialog systems; … Related articles

Dialogue-based Exploration of Graphics for Users with a Visual Disability J Plhak – 2014 – is.muni.cz … 30 4.1.1 DialogueStrategies . . . . . 32 4.2 Types of Dialogue Systems . . . . . 32 4.3 Dialogue Systems Supported by Ontologies . . . . . 34 4.3.1 UK Cancer Referrals and Home Control . . . . . 34 4.3.2 SmartWeb . . . . . … Related articles All 3 versions

Artificial Conversations for Chatter Bots Using Knowledge Representation, Learning, and Pragmatics C Chakrabarti – 2014 – repository.unm.edu … Existing approaches to artificial conversation generation focus on linguistic and gram- matical modeling using natural language processing and computational linguistics techniques to generate individual sentence-level utterances. … 27 2.4 Dialogue systems . . . . . … Cited by 1 Related articles All 5 versions

Conquering Data in Austria PIKT der Zukunft, I Systeme – bmvit.gv.at … This is further supported by the geographical proximity of Austria’s ma jor cities. In terms of research and technological competences the stakeholders see weaknesses in the areas of Recommendation Systems, Computational Linguistics as well as Inference. …

Referring expression generation towards mediating shared perceptual basis in situated dialogue R Fang – 2014 – cse.msu.edu Page 1. REFERRING EXPRESSION GENERATION TOWARDS MEDIATING SHARED PERCEPTUAL BASIS IN SITUATED DIALOGUE By Rui Fang A DISSERTATION Submitted to Michigan State University in partial fulfillment of the requirements for the degree of …

Computational linguistics resources for Indo-Iranian languages S Virk – 2014 – 130.241.16.4 Page 1. Thesis for the degree of Doctor of Philosophy Computational Linguistics Resources for Indo-Iranian Languages Shafqat Mumtaz Virk … Page 2. Computational Linguistics Resources for Indo-Iranian Languages Shafqat Virk Copyright © Shafqat Virk, 2013 … Related articles All 7 versions

[BOOK] Text Mining of Web-based Medical Content A Neustein – 2014 – books.google.com … The chapter on user satisfaction with a health dialogue system is followed by a fascinating presentation of the Smith-Kettlewell Eye Research Institute’s … 4.3.2.4 Validation 92 4.3.3 Prediction analysis 93 4.3.3.1 Multiple linear regression 93 4.3.3.2 Artificial neural network 96 4.3 … Related articles All 4 versions

A pragmatic tutorial dialogue system: design, implementation and evaluation in a health sciences domain JA McDonald – 2014 – ourarchive.otago.ac.nz … and practitioners in context. (p.61) The tutorial dialogue system described is new in the context of teaching first year … ligence (AI) research, in particular, intelligent tutoring systems (ITS) and aspects of computational linguistics and natural language processing (NLP). … Related articles All 2 versions