Language-independent & Dialog Systems 2017


Notes:

In the context of dialog systems, “language-independent” may refer to natural language. However, “language-independent” may also refer to programming language.

Resources:

Wikipedia:

References:

See also:

Dialog Agents


HELPR: A framework to break the barrier across domains in spoken dialog systems
M Sun, YN Chen, AI Rudnicky – Dialogues with Social Robots, 2017 – Springer
… We asked participants to talk to a Wizard-of-Oz dialog system to reenact their own multi-domain tasks using speech … In this study, we used the Rapid Automatic Keyword Extraction (RAKE 5 ) algorithm [29], an unsupervised, language-independent and domain-independent …

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
Page 1. Generative Encoder-Decoder Models for Task-Oriented Spoken Dialog Systems with Chatting Capability … Abstract Generative encoder-decoder models of- fer great promise in developing domain- general dialog systems …

Natural Language Understanding (NLU, not NLP) in Cognitive Systems.
M McShane – AI Magazine, 2017 – search.ebscohost.com
… For example, agents in dialogue systems receive one and only one formula- tion of each utterance. Moreover, they must also deal with performance errors such as unfinished thoughts, fragmentary utterances, self-interruptions, repetitions, and non sequiturs …

Design and Implementation of a Semantic Dialogue System for Radiologists
D Sonntag, M Huber, M Möller, A Ndiaye… – arXiv preprint arXiv …, 2017 – arxiv.org
… Page 11. Design and Implementation of a Semantic Dialogue System… 11 … Using the same representation formalism to represent domain knowledge and annotations allows us to formulate cross-modal and language-independent search queries …

Differentiable scheduled sampling for credit assignment
K Goyal, C Dyer, T Berg-Kirkpatrick – arXiv preprint arXiv:1704.06970, 2017 – arxiv.org
… 2015. Building end-to-end dialogue systems using generative hier- archical neural network models … pages 3104–3112. Erik F Tjong Kim Sang and Fien De Meulder. 2003. Introduction to the conll-2003 shared task: Language-independent named entity recognition …

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 …

Multimodal dialogue system with NAO and VoiceXML dialogue manager
S Ondáš, J Juhár, M Pleva, P Fer?ák… – … ), 2017 8th IEEE …, 2017 – ieeexplore.ieee.org
… IV. CONCLUSION The newly designed multimodal dialogue system with NAO robot has been introduced and described … Designed multimodal system is language-independent; it means that it supports all languages supported by built-in ASR and TTS systems in NAO robot …

Treating Unexpected Input in Incremental Semantic Analysis
M McShane, K Blissett, I Nirenburg – … of The Fifth Annual Conference on …, 2017 – cogsys.org
Page 1. Advances in Cognitive Systems 2017 © 2017 Cognitive Systems Foundation. All rights reserved. Treating Unexpected Input in Incremental Semantic Analysis Marjorie McShane MARGEMC34@GMAIL.COM Kevin Blissett KEVINPBLISSETT@GMAIL.COM …

Significance of neural phonotactic models for large-scale spoken language identification
BML Srivastava, H Vydana, AK Vuppala… – … Joint Conference on, 2017 – ieeexplore.ieee.org
… Abstract—Language identification (LID) is vital frontend for spoken dialogue systems operating in diverse linguistic settings to reduce recognition and … The input speech signal is tokenized to phone sequences by using a common language-independent phone recognizer with …

PDTSC 2.0-Spoken Corpus with Rich Multi-layer Structural Annotation
M Mikulová, J Mírovský, A Nedoluzhko, P Pajas… – … Conference on Text …, 2017 – Springer
… The markup used in PDTSC 2.0 is the language-independent Prague Markup Language (PML), which is an XML subset customized for multi-layered linguistic annotation … Either way, we hope that this resource can help build automatic speech understanding and dialog systems …

Utterance Retrieval based on Recurrent Surface Text Patterns
GD Duplessis, F Charras, V Letard, AL Ligozat… – … on Information Retrieval, 2017 – Springer
… The main goal is to provide a dialogue system with the ability to appropriately react to a large variety of unexpected out-of-domain human utterances by offering … Its main features are to implement a corpus-based, unsupervised, parameterless and language-independent process …

Do You Think You Can? The Influence of Student Self-Efficacy on the Effectiveness of Tutorial Dialogue for Computer Science
JB Wiggins, JF Grafsgaard, KE Boyer… – International Journal of …, 2017 – Springer
… Development of tutorial dialogue systems presents many challenges, but these systems can currently engage with students in topic areas such … to the variety of different forms computer science education can take, research must also make language-independent strides forward …

A knowledge graph based speech interface for question answering systems
AJ Kumar, C Schmidt, J Köhler – Speech Communication, 2017 – Elsevier
… Like their predecessors in the Microsoft Speech Application Interface (SAPI), SALT objects are programming language independent … on the Web-based distributed computing environment and elaborates how SALT can be used to implement multimodal dialogue systems …

Topic Identification for Speech without ASR
C Liu, J Trmal, M Wiesner, C Harman… – arXiv preprint arXiv …, 2017 – arxiv.org
… Note that this rescoring model is estimated using a portion of transcribed Switchboard, but it is still a legitimate language-independent UTD approach while … [14] C. Liu, P. Xu, and R. Sarikaya, “Deep contextual language under- standing in spoken dialogue systems.” in Proc …

Detecting Dementia Through Interactive Computer Avatars
H Tanaka, H Adachi, N Ukita, M Ikeda… – IEEE journal of …, 2017 – ieeexplore.ieee.org
… Users can operate and communicate with it using speech throughout the interaction. All of the dialogue system’s utterances were created using templates … This resembles a language- independent task. We used a regular Windows viewer application to display it …

Semantic specialisation of distributional word vector spaces using monolingual and cross-lingual constraints
N Mrkši?, I Vuli?, DÓ Séaghdha, I Leviant… – arXiv preprint arXiv …, 2017 – arxiv.org
… in each case outperforming the monolin- gual model. To the best of our knowledge, this is the first work on multilingual training of any compo- nent of a statistical dialogue system. Our results in- dicate that multilingual training …

Automatic sentence stress feedback for non-native English learners
GG Lee, HY Lee, J Song, B Kim, S Kang, J Lee… – Computer Speech & …, 2017 – Elsevier
Skip to main content …

A “small-data”-driven approach to dialogue systems for natural language human computer interaction
T Boros, SD Dumitrescu – Speech Technology and Human …, 2017 – ieeexplore.ieee.org
… A scenario is the equivalent of a frame in a in frame-based dialogue system, but by default we don’t log any previous … Plus, because we seek a language- independent approach, the classical NLP tricks such as “stop words”, “lexical chains” and “index terms” must be avoided …

Spoken language understanding and interaction: machine learning for human-like conversational systems
M Gaši?, D Hakkani-Tür, A Celikyilmaz – 2017 – Elsevier
… In the area of spoken dialogue systems typically one or a hand-full of languages dominates. However, the underlying machine learning methods are language-independent and in principle allow for development of a system in any language provided sufficient training data …

Dialogue Breakdown Detection Considering Annotation Biases
J Takayama, E Nomoto, Y Arase – workshop.colips.org
… As chat-oriented dialogue systems, which are known as chat- bots, implemented by generation-based and example-based ap- proaches gain popularity, output utterances that collapse the di … However, our models are language independent that are applicable to dialogue …

End-to-end Character-Level Dialogue Breakdown Detection with External Memory Models
T Iki, A Saito – workshop.colips.org
… Recent work on dialogue systems with neural networks in- cludes a promissing approach, end-to-end memory networks (MemN2N) [4]. MemN2N … is a kind of data augmentation under the hypothesis that some break- downs are caused by language independent patterns of …

Deep Learning for Acoustic Addressee Detection in Spoken Dialogue Systems
A Pugachev, O Akhtiamov, A Karpov… – Conference on Artificial …, 2017 – Springer
… Text classification: Best choice for a dialogue system in a specific domain. Domain dependent – Language dependent. 2. Acoustic analysis: Still valid by reason of ASR imperfection. Domain and language independent. Harder to train than a text classifier. 3. Gaze detection …

Multilingual spoken dialog systems for handheld devices
BML Srivastava – 2017 – researchgate.net
… As stated earlier, language Identification (LID) systems are a vital front-end for multilingual spoken dialogue systems … In this work, the input speech signal is tokenized to phone sequences by using a common language-independent phone recognizer with varying phonetic …

Novel Methods for Natural Language Generation in Spoken Dialogue Systems
O Dušek – 2017 – dspace.cuni.cz
… Ond?ej Dušek Novel Methods for Natural Language Generation in Spoken Dialogue Systems Institute of Formal and Applied Linguistics Supervisor: Ing … iii Page 4. Page 5. Title: Novel Methods for Natural Language Generation in Spoken Dialogue Systems Author: Ond?ej Dušek …

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 …

Reducing latency for language identification based on large-vocabulary continuous speech recognition
T Okamoto, A Hiroe, H Kawai – Acoustical Science and Technology, 2017 – jstage.jst.go.jp
… language applications such as bilingual speech translation systems, eg, VoiceTraÃ, or multilingual spoken dialogue systems, the number … 3. In the simple constant timeout and utterance length-dependent variable timeout approaches, a language-independent timeout duration …

Text, Speech, and Dialogue: 20th International Conference, Tsd 2017, Prague, Czech Republic, August 27-31, 2017, Proceedings
K Ekštein, V Matoušek – 2017 – books.google.com
… One of the ambitions of the conference is, as its name suggests, not only to deal with dialogue systems but also to improve … 138 Jind?ich Matoušek and Michal Klíma Language Independent Assessment of Motor Impairments of Patients with Parkinson’s Disease Using i-Vectors …

Dependency Parsing and Dialogue Systems: an investigation of dependency parsing for commercial application
A Adams – 2017 – diva-portal.org
Page 1. Dependency Parsing and Dialogue Systems an investigation of dependency parsing for commercial application … Page 2. Abstract In this thesis, we investigate dependency parsing for commercial application, namely for future integration in a dialogue system …

A data-driven model of explanations for a chatbot that helps to practice conversation in a foreign language
S Höhn – Proceedings of the 18th Annual SIGdial Meeting on …, 2017 – aclweb.org
… The the study contributes to language understanding for dialogue systems tar- geting language learners and has implications for user and expert models for CommICALL. 3 Practices of repair in chat … These features are language independent …

A Study on Natural Language Processing for Human Computer Interaction
N MPSTME – ijarcet.org
… relating syntactic structures, from phrase, clauses, sentences and paragraphs to writing them as a whole, to their language-independent meanings … state based systems 2) Frame based systems 3) Agent based systems [31] 4) Answering systems 5) Semi-dialogue systems 6) Full …

Cognitive science, language as a tool for interaction, and a new look at language evolution
R Kempson, S Chatzikyriakidis, C Howes – FADLI 2017 – christinehowes.com
… On a more general level, this might point to the possi- bility of a set of language independent (and poten- tially domain general) computational actions that given appropriate data … Bootstrapping incremental dialogue systems: using linguistic knowledge to learn from minimal data …

Domain Transfer for Deep Natural Language Generation from Abstract Meaning Representations
N Dethlefs – IEEE Computational Intelligence Magazine, 2017 – ieeexplore.ieee.org
… in a rich lexicon [61]. MTT has been a popular choice in multi-lin- gual NLG [62], [63] for its feature of allowing the separation of language-specific and language- independent resources. Recent efforts in linguistically-informed …

A demo of FORGe: the Pompeu Fabra Open Rule-based Generator
S Mille, L Wanner – Proceedings of the 10th International Conference on …, 2017 – aclweb.org
… to languages such as Spanish, German French, and Polish, in the context of ontology-to-text generation as part of a dialogue system … Sec- ond, many rules are language-independent, and oth- ers can be easily adapted to other languages, which means that, with good quality …

Bilingual Word Embeddings for Cross-Lingual Personality Recognition Using Convolutional Neural Nets
FB Siddique, P Fung – Learning, 2017 – pdfs.semanticscholar.org
… Having such a personality recognition module in dialogue systems will enable us to have more intelligent and personal human-agent conversations in the future [3, 4]. The Big Five … There is inadequate work done in the task of language independent personality classification …

Personalized Questions, Answers and Grammars: Aiding the Search for Relevant Web Information
M Gatius – Proceedings of the 10th International Conference on …, 2017 – aclweb.org
… Do- main and language independent rules to extract the relevant data from these two types of documents have been defined and … Domain knowledge representation has been incorporated into a considerable number of rele- vant dialogue systems (Guzzoni et al., 2006; Sonntag …

Talking Open Data
S Neumaier, V Savenkov, S Vakulenko – European Semantic Web …, 2017 – Springer
… We envision our prototype to be the first step towards an intelligent dialogue system supporting contextual multilingual semantic search [1 … The Babelfy API provides a list of corresponding “babelSynsetIDs” for an input string, language-independent entity identifiers in the …

Speech applications for human-robot interaction systems.
M Pleva, S Ondas – iit.bas.bg
… is focused mainly on the Slovak language processing including automatic speech recognition [1] and synthesis [2]. A task for language independent voice search … NAO can be considered as a great tool to prepare a multimodal dialogue system due to its support of vision, hearing …

STREAMLInED Challenges: Aligning Research Interests with Shared Tasks
GA Levow, EM Bender, P Littell, K Howell… – Proceedings of the 2nd …, 2017 – aclweb.org
… that they produce data sets and bench- marks to allow researchers to test whether their proposed language-independent solutions work … will operate over less-structured human-directed speech, rather than the computer-directed speech prevalent in dialog systems tasks listed …

Shallow PARsing and Knowledge extraction for Language Engineering
I Annex – cogsci.ed.ac.uk
… The lexicon acquisition system will thus be parameterisable for each choice of language, making it possible to incorporate language-independent as well … The speech dialogue system, developed by Daimler Benz for German, will also make use of sparkle’s parsers and lexica to …

What Ignites a Reply?: Characterizing Conversations in Microblogs
J Torres, C Vaca, CL Abad – Proceedings of the Fourth IEEE/ACM …, 2017 – dl.acm.org
… In this research, we propose a language independent model to identify seed tweets that have the potential to form conversations for … conversation acts3. Several applications have rely on acts identification, such as: con- versational agents [20], dialogue systems [2], automated …

Enhancing A Role And Reference Grammar Approach To English Motion Constructions In A Natural Language Processing Environment
A Luzondo-Oyón, R Jiménez-Briones – 2017 – pdfs.semanticscholar.org
… The lexical and grammatical levels are language-specific, while the conceptual level is language-independent and therefore shared by all the languages included in the knowledge base … is connected to a target language, while ontological knowledge is language-independent …

Exploiting end of sentences and speaker alternations in language modeling for multiparty conversations
H Ashikawa, N Tawara, A Ogawa… – Asia-Pacific Signal …, 2017 – ieeexplore.ieee.org
… [6] K. Yoshino, S. Mori, and T. Kawahara, “Language modeling for spoken dialogue system based on sentence transformation and filtering using predicate-argument structures,” in Proc … 2882–2886. [8] F. Valente and A. Vinciarelli, “Language-independent socio-emotional role …

Non-Contextual Modeling of Sarcasm using a Neural Network Benchmark
V Ashokkumar, ND Radpour – 2017 – ttic.edu
… One of the most crucial components of natural human-robot interaction is artificial intuition and its influence on dialog systems … Davidov, Tsur, and Rappoport 2010a), lexical features (González-Ibánez, Muresan, and Wacholder 2011) and language-independent features (Ptácek …

Symbol sequence search from telephone conversation
M Suzuki, G Kurata, A Sethy… – Proc. Interspeech …, 2017 – isca-speech.org
… There are already many successful applications of spoken interaction, such as IoT applications, dictation, voice search, and spoken dialog systems … [21] EF Tjong Kim Sang and F. De Meulder, “Introduction to the conll-2003 shared task: Language-independent named entity …

Controlling Target Features in Neural Machine Translation via Prefix Constraints
S Takeno, M Nagata, K Yamamoto – … of the 4th Workshop on Asian …, 2017 – aclweb.org
… There are no language independent meth- ods that can cope with unaligned target words. 4.2 Identifying Unaligned Target Words We first propose a language independent method for automatically identifying unaligned target words …

Natural Language Processing: State of The Art, Current Trends and Challenges
D Khurana, A Koli, K Khatter, S Singh – arXiv preprint arXiv:1708.05148, 2017 – arxiv.org
… Dialogue systems. 6.7 Medicine … It’s task was to implement a robust and multilingual system able to analyze/comprehend medical sentences, and to preserve a knowledge of free text into a language independent knowledge representation [95][96] …

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 …

Leveraging Tokens in a Natural Language Query for NLIDB Systems
A Palakurthi – 2017 – pdfs.semanticscholar.org
… The authors also claim that the approach is both domain and language independent … 1.3 Challenges in Dialogue and NLIDB Systems Current Dialogue systems and NLIDB systems face multiple challenges [17], [2]. Few of them are …

Measuring Synchrony in Task-based Dialogues
J Reverdy, C Vogel – Proc. Interspeech 2017, 2017 – pdfs.semanticscholar.org
… As one of the possible future application of this measure of synchrony to quantify mutual understanding reside in its use in dialogue systems, and the possible determination of change in communicative strategies … [20] H. Schmid, “Treetagger— a language independent part-of …

Enhancing a Role and Reference Grammar approach to English motion constructions in a Natural Language Processing environment
A Luzondo-Oyón, R Jiménez-Briones – revistas.ucm.es
… As shown in Figure 1, FunGramKB comprises three major knowledge levels. The lexical and grammatical levels are language-specific, while the conceptual level is language-independent and therefore shared by all the languages included in the knowledge base …

Speaker and Language Recognition and Characterization: Introduction to the CSL Special Issue
E Lleida, LJ Rodriguez-Fuentes – 2017 – Elsevier
… On the other hand, spoken language recognition (SLR) has also witnessed a remarkable interest from the community as an auxiliary technology for speech recognition (Gonzalez-Dominguez et al., 2015b), dialogue systems (Lopez-Cozar and Araki, 2005) and multimedia …

Boosting a Rule-Based Chatbot Using Statistics and User Satisfaction Ratings
O Efraim, V Maraev, J Rodrigues – Conference on Artificial Intelligence …, 2017 – Springer
… 2 Related Work. The ability to predict a candidate answer’s fitness to a question is a potentially useful feature in a dialogue system’s answer selection module … The authors propose a language-independent framework based on convolutional neural networks (CNN) …

An overview of open-source chatbots social skills
A Augello, M Gentile, F Dignum – researchgate.net
… based chat- bots, we selected Chatterbot because it allows the developers to easily create and automate conversations in a language independent manner … This is a logical starting point for dialogue systems as the topic of a conver- sation is also part of the linguistic context …

Implementation of a Bangla chatbot
TD Orin – 2017 – dspace.bracu.ac.bd
… based on a language-independent natural language processing library with a learning mechanism … Statistical goal-oriented dialogue systems have long been modeled as partially observable Markov decision processes (POMDPs) (?Young et al., 2013?), and are trained using …

Non-Contextual Modeling of Sarcasm using a Neural Network Benchmark
ND Radpour, V Ashokkumar – arXiv preprint arXiv:1711.07404, 2017 – arxiv.org
… to capture different forms of nuances in communication and making for much more natural and engaging dialogue systems … Davidov, Tsur, and Rappoport 2010a), lexical features (Gonzalez-Ibanez, Muresan, and Wacholder 2011) and language-independent features (Ptacek …

Repetition detection in dysarthric speech
G Diwakar, V Karjigi – Wireless Communications, Signal …, 2017 – ieeexplore.ieee.org
… To detect repetition in spoken dialogue systems, a neural network based phoneme recognizer was proposed in [5]. Repetition detection involved two phases … The advantage of the proposed approach is that, it is a complete data driven approach and also language independent …

Enhancing a Role and Reference Grammar approach to English motion constructions in a Natural Language Processing environment
RJ Briones, A Luzondo – Círculo de Lingüística Aplicada a la Comunicación – recyt.fecyt.es
… The lexical and grammatical levels are language-specific, while the conceptual level is language-independent and therefore shared by all the languages included in the knowledge base … is connected to a target language, while ontological knowledge is language-independent …

19 Speech Synthesis: State of the Art and Challenges for the Future
K Georgila – Social Signal Processing, 2017 – books.google.com
… as an aid to people with disabilities (see Challenges for the Future), for generating the output of spoken dialogue systems (Lemon et … The first module is language-specific, whereas the second module can be largely language-independent (except for the language data used for …

Cross-language transfer of semantic annotation via targeted crowdsourcing: task design and evaluation
EA Stepanov, SA Chowdhury, AO Bayer… – Language Resources …, 2017 – Springer
… Keywords Crowdsourcing Á Evaluation Á Semantic annotation Á Cross-language transfer 1 Introduction With the increasing availability of intelligent digital assistants, spoken dialog systems (SDS) are at the forefront of research and development both in academia and industry …

Overview of the 2017 spoken CALL shared task
C Baur, C Chua, J Gerlach, E Rayner, M Russel, H Strik… – 2017 – archive-ouverte.unige.ch
… 2.1. Data The core resource for the task was an English speech corpus collected with the CALL-SLT dialogue game. In total, the corpus contains 38,771 spontaneous speech acts in the form of students’ interactions with the dialogue system …

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 …

Business Administration and Information Systems
RPDK Ambrosi – Data Analytics International Master – uni-hildesheim.de
… knowledge of Multilingual Informa- tion Retrieval, presents state-of-the-art language-dependent and language-independent methods and … Technology as method and tool: digital- humanities applications, Language Processing daily life tools (eg dialogue systems, correction of …

Parsing and beyond: Tools and resources for Estonian
K Muischnek, K Müürisep… – Acta Linguistica …, 2017 – akademiai.com
Page 1. Acta Linguistica Academica Vol. 64 (2017) 3, 347–367 DOI: 10.1556/ 2062.2017.64.3.2 Parsing and beyond Tools and resources for Estonian Kadri Muischnek University of Tartu, Estonia kadri.muischnek@ut.ee Kaili …

Multi-level mining and visualization of scientific text collections
P Accuosto, F Ronzano, D Ferrés, H Saggion – 2017 – repositori.upf.edu
… 18Using Babelfy’s Word Sense Disambiguation and Entity Linking algorithm to iden- tify occurrences of language-independent synsets is particularly useful to study the evolution … dialogue systems user dialogue system information models model items speech goals interaction …

Multi-level mining and visualization of scientific text collections: Exploring a bi-lingual scientific repository
P Accuosto, F Ronzano, D Ferrés… – Proceedings of the 6th …, 2017 – dl.acm.org
… 18Using Babelfy’s Word Sense Disambiguation and Entity Linking algorithm to iden- tify occurrences of language-independent synsets is particularly useful to study the evolution … dialogue systems user dialogue system information models model items speech goals interaction …

An educational system for learning search algorithms and automatically assessing student performance
F Grivokostopoulou, I Perikos… – International Journal of …, 2017 – Springer
… oriented programming. The provided animations present step by step executions of Java programs. ViLLE is a language-independent program visualization tool that provides a more abstract view of programming. It offers an …

Articulatory Modeling for Pronunciation Error Detection without Non-Native Training Data Based on DNN Transfer Learning
R Duan, T Kawahara, M Dantsuji… – … on Information and …, 2017 – search.ieice.org
… corpus. It opens new possibilities in language-independent pronuncia- tion error detection … He has published more than 300 techni- cal papers on speech recognition, spoken lan- guage processing, and spoken dialogue systems. He …

ExoTime: Temporal Information Extraction from Korean Texts Using Knowledge Base
YS Jeong, CG Lim, HJ Choi – ????????????, 2017 – dbpia.co.kr
… Thus, other than these features, we adopt some complementary features directly generated from the texts, as done in our previous work [1]. Here, we employ the features generated by the Language Independent Feature Generator (LIFE) model [22], where the model takes the …

End-to-end Adversarial Learning for Generative Conversational Agents
O Ludwig – arXiv preprint arXiv:1711.10122, 2017 – arxiv.org
… to sequence (seq2seq) modeling is being success- fully applied to neural machine translation [6], [7], since this model is language-independent and able to … [17] IV Serban, A. Sordoni, Y. Bengio, AC Courville, J. Pineau, Building end-to-end dialogue systems using generative …

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 … Sang, EFTK, De Meulder, F.: Introduction to the conll-2003 shared task: language-independent named entity recognition. Comput. Sci …

A Continuous Relaxation of Beam Search for End-to-end Training of Neural Sequence Models
K Goyal, G Neubig, C Dyer… – arXiv preprint arXiv …, 2017 – arxiv.org
… [6] IV Serban, A. Sordoni, Y. Bengio, A. Courville, and J. Pineau, “Building end-to-end dialogue systems using generative hierarchical … [27] EF Tjong Kim Sang and F. De Meulder, “Introduction to the conll-2003 shared task: Language- independent named entity recognition,” in …

HMM-based phrase-independent i-vector extractor for text-dependent speaker verification
H Zeinali, H Sameti, L Burget – IEEE/ACM Transactions on …, 2017 – ieeexplore.ieee.org
Page 1. IEEE/ACM TRANSACTIONS ON AUDIO, SPEECH, AND LANGUAGE PROCESSING, VOL. 25, NO. 7, JULY 2017 1421 HMM-Based Phrase-Independent i-Vector Extractor for Text-Dependent Speaker Verification Hossein Zeinali, Hossein Sameti, and Lukáš Burget …

Characterisation of voice quality of Parkinson’s disease using differential phonological posterior features
M Cernak, JR Orozco-Arroyave, F Rudzicz… – Computer Speech & …, 2017 – Elsevier
… takes the articulatory production mechanism as the underlying principle of phoneme organisation (and thus allows easier interpretation of obtained results), and (ii) SPE assumes that the flat, unstructured binary feature specifications are language independent and characterise …

A review of Serbian parametric speech synthesis based on deep neural networks
T Deli?, M Se?ujski, S Suzi? – Telfor Journal, 2017 – scindeks.ceon.rs
… of the actual speech signal on the basis of this specification (referred to as “back end”) is largely language independent, and mostly … The research was conducted within the project “Development of Dialogue Systems for Serbian and Other South Slavic Languages” (TR32035 …

Telugu dependency parsing using different statistical parsers
BVS Kumari, RR Rao – Journal of King Saud University-Computer and …, 2017 – Elsevier
… relationships between words. Parsing is useful in major NLP applications like Machine Translation, Dialogue Systems, Question Answering, etc. This led to the development of grammar-driven, data-driven and hybrid parsers. Due to …

Approaches for Computational Sarcasm Detection: A Survey
L Kumar, A Somani, P Bhattacharyya – pdfs.semanticscholar.org
… They have selected various n-grams, including un- igrams, bigrams, trigrams with frequency greater than three ((Liebrecht et al., 2013)), and a set of language-independent features, including punctu- ation marks, emoticons, quotes, capitalized words, character n-grams and skip …

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 …

Criticality of Components in Service-Oriented Distributed Systems
DG Design – 2017 – dai-labor.de
… 2012, Proceedings, pp. 145-154; 2012. Language-Independent Twitter Sentiment Analysis Sascha Narr, Michael Hülfenhaus, Sahin Albayrak In: KDML, LWA 2012, Dortmund, Germany; 2012. Recommender Systems Evaluation …

Monitoring disaster impact: detecting micro-events and eyewitness reports in mainstream and social media
H Tanev, V Zavarella, J Steinberger – idl.iscram.org
… 2016) we experimented with a minimal set of language features that could be mostly produced using language-independent methods, and … 2014) Using lexical, syntactic and semantic features for non-terminal grammar rule induction in Spoken Dialogue Systems, IEEE Spoken …

Automatic Neural Question Generation using Community-based Question Answering Systems
T Baghaee – 2017 – uleth.ca
Page 1. AUTOMATIC NEURAL QUESTION GENERATION USING COMMUNITY- BASED QUESTION ANSWERING SYSTEMS TINA BAGHAEE Bachelor of Science, Shahid Beheshti University, 2011 A Thesis Submitted to the …

Statistical Language Models applied to News Generation
JRP Soares – 2017 – repositorio-aberto.up.pt
Page 1. FACULDADE DE ENGENHARIA DA UNIVERSIDADE DO PORTO Statistical Language Models applied to News Generation João Ricardo Pintas Soares Mestrado Integrado em Engenharia Informática e Computação Supervisor: Prof. Sérgio Sobral Nunes July 24, 2017 …

Open source Icelandic resource grammar in GF
B Traustason – publications.lib.chalmers.se
… This gives way for opportunities in many language processing tasks, eg, machine translation, multi- lingual generation and spoken dialogue systems … Such applications can be written mathematical exercises, or dialogue systems …

Multilingual extension and evaluation of a poetry generator
HG Oliveira, R Hervás, A Díaz… – Natural Language …, 2017 – cambridge.org
… N-gram- based language models have shown great applicability in many contexts – such as machine translation, speech processing, text prediction or dialog systems – and they present the important advantage of being language independent to a great extent …

A class-specific copy network for handling the rare word problem in neural machine translation
F Wang, W Chen, Z Yang, X Zhang… – Neural Networks (IJCNN …, 2017 – ieeexplore.ieee.org
… of the model has been accelerated. In the future, we will try to apply the class-specific copy network in other NLP tasks, such as the dialogue system and the question answering. ACKNOWLEDGMENT This work is supported …

Speech perception by humans and machines
MH Davis, O Scharenborg – Speech perception and spoken word …, 2017 – books.google.com
… The most probable word sequence can then be transcribed, used to drive a dialogue system, or for other purposes (see … recognition performance in adverse conditions (Kirchhoff, 1998; Kirchhoff, Fink, & Sagerer, 2002) in order to build language-independent phone recognizers …

Community Standards for Linguistically-Annotated Resources
N Ide, N Calzolari, J Eckle-Kohler, D Gibbon… – Handbook of Linguistic …, 2017 – Springer
This chapter provides a broad overview of the state-of-the-art in standards development for language resources, beginning with a brief historical overview to serve as context. It describes in some det.

Agile model-based development using UML-RSDS
K Lano – 2017 – books.google.com
Page 1. Agile Model-Based Development Using UML-RSDS KEV | \ || ANO C Specification UML Q – Design. Automated translation | Automated code generation Implementations. Java C#. C++ – CRC Press | | || |H|E|| || | Page 2 …

Annotation of semantic roles for the Turkish Proposition Bank
GG ?ahin, E Adal? – Language Resources and Evaluation – Springer
Page 1. ORIGINAL PAPER Annotation of semantic roles for the Turkish Proposition Bank Gözde Gül Sahin1 • Esref Adal?1 © Springer Science+Business Media Dordrecht 2017 Abstract In this work, we report large-scale semantic …

Machine Translation Using Semantic Web Technologies: A Survey
D Moussallem, M Wauer, ACN Ngomo – arXiv preprint arXiv:1711.09476, 2017 – arxiv.org
… The main difference between them is the internal model which they rely upon. In contrast to TBMT approaches (where the target lan- guage plays a key role), Interlingua-based approaches rely on extracting a language-independent representation of the input text …

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 …

Towards the Implementation of an Intelligent Software Agent for the Elderly
AHF Dinevari – 2017 – era.library.ualberta.ca
Page 1. Towards the Implementation of an Intelligent Software Agent for the Elderly by Amir Hossein Faghih Dinevari A thesis submitted in partial fulfillment of the requirements for the degree of Master of Science Department of Computing Science University of Alberta …

Neural Wikipedian: Generating Textual Summaries from Knowledge Base Triples
P Vougiouklis, H Elsahar, LA Kaffee, C Gravier… – arXiv preprint arXiv …, 2017 – arxiv.org
… Answering platforms whose users’ experience could be im- proved by the ability to automatically generate a textual description of an entity that is returned at a user’s query (eg the Google Knowledge Graph1 and the Wikidata Reasonator2), or dialogue systems in commercial …

DAC-h3: A Proactive Robot Cognitive Architecture to Acquire and Express Knowledge About the World and the Self
C Moulin-Frier, T Fischer, M Petit… – … on Cognitive and …, 2017 – ieeexplore.ieee.org
… our framework, it is based on the implementation and cooperation between both episodic and semantic memories with a dialog system … is a set of capabilities that include the motivation to interact and communicate through universal (language independent) manners; including …

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
Page 1. 39 A New Classification Framework to Evaluate the Entity Profiling on the Web: Past, Present and Future AHMAD ABDOLLAHZADEH BARFOROUSH, HOSSEIN SHIRAZI, and HOJJAT EMAMI, Malek Ashtar University of Technology …

Helping users learn about social processes while learning from users: developing a positive feedback in social computing
VSS Pillutla – 2017 – search.proquest.com
Helping Users Learn About Social Processes While Learning from Users: Developing a Positive Feedback in Social Computing. Abstract. Social computing is concerned with the interaction of social behavior and computational systems …

Assessment Of Risk Scores For The Prediction And Detection Of Type 2 Diabetes Mellitus In Clinical Settings
AM Millana – 2017 – riunet.upv.es
Page 1 …

Amharic-to-Tigrigna Machine Translation Using Hybrid Approach
A Gebremariam – 2017 – etd.aau.edu.et
… human about arbitrary topics and the goal of research in NLP and in natural language understanding, and in dialogue system in particular is to break down the barrier [4]. Many researches been conducted on topics related to the application of natural language processing …

Developing Semantic Role Labeler for Hindi and Urdu
MA Nomani – 2017 – web2py.iiit.ac.in
… years appears to be motivated both by the gains in efficiency in analyzing the structure of the sentence to remove ambiguity and by its potential usefulness in several NLP applications like machine translation, semantic role labeling, discourse analysis and dialogue systems. 2 …

Thesis Material-Rasmus Dall
R Dall – 2017 – datashare.is.ed.ac.uk
Page 1. Statistical Parametric Speech Synthesis Using Conversational Data and Phenomena Rasmus Dall T H E U NIVER S I T Y O F E DI NBU R G H Doctor of Philosophy Institute for Language, Cognition and Computation School of Informatics University of Edinburgh 2017 …

Movement Data
S Hoogervorst – pure.tue.nl
Page 1. Eindhoven University of Technology MASTER Predicting website visitor gender and age with mouse movement data Hoogervorst, SJ Award date: 2016 Disclaimer This document contains a student thesis (bachelor’s …

(Visited 36 times, 1 visits today)