Language Modeling & Dialog Systems 2014

Language Model


  • Language modelling
  • Text analysis


See also:

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

[BOOK] Speech and language processing D Jurafsky, JH Martin – 2014 – … A similar spoken dialogue system has been deployed by as- tronauts on the International Space Station. … Progress on statistical approaches to machine trans- lation (Brown et al., 1990; Och and Ney, 2003) and topic modeling (Blei et al., 2003) demonstrated that effective … Cited by 26 Related articles All 20 versions

Probabilistic enrichment of knowledge graph entities for relation detection in conversational understanding D Hakkani-Tür, A Celikyilmaz… – Proceedings of …, 2014 – … new relation types from large text corpora [7]. Se- mantic knowledge graphs have also been used for SLU seman- tic parsing tasks in dialog systems [8, 9 … Our seeded topic modeling approach is based on the semi-supervised LDA presented in [32, 33], which is depicted in Fig. … Cited by 11 Related articles All 7 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 … Journal of Biomedical Informatics 41(6), 1070–1087 (2008) CrossRef; Yeh, JF, Wu, CH, Chen, MJ: Ontology-based speech act identification in a bilingual dialog system using partial pattern trees. J. Am. Soc. … 26–30 (2010); Arnold, C., Speier, W.: A topic model of clinical reports. … Cited by 11 Related articles All 5 versions

Heterogeneous networks and their applications: Scientometrics, name disambiguation, and topic modeling B King, R Jha, DR Radev – Transactions of the …, 2014 – … inspection of these topics, we found them to be very much like topics created by statistical topic models. … parsing detecting MaxEnt models entropy maximum approach based attachment model models phrase prepositional disambiguation Dialogue systems dialogue spoken … Cited by 2 Related articles All 13 versions

Discovering latent structure in task-oriented dialogues K Zhai, JD Williams – Proceedings of the Association for …, 2014 – … Our methods synthesize hidden Markov models (for underlying state) and topic models (to connect words to states … into human communication, compu- tational models of conversation underpin a host of real-world applications, including interactive dialogue systems (Young, 2006 … Cited by 4 Related articles All 13 versions

Core technologies for the internet of services T Becker, C Burghart, K Nazemi, P Ndjiki-Nya… – Towards the Internet of …, 2014 – Springer … A platform for multimodal and situation aware dialog systems has been created, whose architecture and some applications are described. … This eliminates the frequent transformation steps between modules that are typical for earlier dialog systems. … Cited by 3 Related articles All 3 versions

Two-stage stochastic natural language generation for email synthesis by modeling sender style and topic structure YN Chen, AI Rudnicky – INLG 2014, 2014 – … A lot of NLG systems are applied in dialogue systems, some of which focus on topic model- ing (Sauper and Barzilay, 2009; Barzilay and Lap- ata, 2008; Barzilay and Lee, 2004), proposing al- gorithms to balance local fit of information and global coherence. … Cited by 2 Related articles All 11 versions

An Information Retrieval Approach to Short Text Conversation Z Ji, Z Lu, H Li – arXiv preprint arXiv:1408.6988, 2014 – … An alternative approach is to build a dialogue system with a knowledge base consisting of large number of question-answer pairs. … 6.3.3. Model Training The training of DeepMatch is divided into two phases: (1) bilingual topic modeling for finding potentially matched subsets … Cited by 3 Related articles All 3 versions

Dialogue POMDP components (part I): learning states and observations HR Chinaei, B Chaib-Draa – International Journal of Speech Technology, 2014 – Springer … Fig. 1 The architecture of a spoken dialogue system adapted from Williams (2006) … In step 1 of Algorithm 1, we learn the dialogue inten- tions from unannotated dialogues using an unsupervised topic modeling approach, and make use of them as the dia- logue POMDP states. … Cited by 1 Related articles All 5 versions

Luke, I am your father: dealing with out-of-domain requests by using movies subtitles D Ameixa, L Coheur, P Fialho, P Quaresma – Intelligent Virtual Agents, 2014 – Springer … 21 3. Banchs, RE, Li, H.: Iris: a chat-oriented dialogue system based on the vector space model. … Waltinger, U., Breuing, A., Wachsmuth, I.: Interfacing virtual agents with collaborative knowledge: Open domain question answering using wikipedia-based topic models. … Cited by 3 Related articles All 8 versions

Minimal narrative annotation schemes and their applications E Rahimtoroghi, T Corcoran, R Swanson… – Seventh Intelligent …, 2014 – … Elahe Rahimtoroghi, Thomas Corcoran, Reid Swanson, and Marilyn A. Walker Natural Language and Dialogue Systems Lab University of California Santa Cruz Santa Cruz, CA, USA {reid, elahe, maw}@soe … 2012), where relevance feedback is used to learn a topic model for an … Cited by 1 Related articles All 3 versions

Generating test data for insider threat detectors B Lindauer, J Glasser, M Rosen, K Wallnau… – Journal of Wireless …, 2014 – … Topic Model: A user’s topical interests both for data consumption (ie, web browsing) and data production (ie, email communication). … [19] AH Oh and AI Rudnicky, “Stochastic natural language generation for spoken dialog systems,” Computer Speech & Language, vol. 16, no. … Cited by 3 Related articles

Topic model allocation of conversational dialogue records by Latent Dirichlet Allocation JF Yeh, CH Lee, YS Tan, LC Yu – Asia-Pacific Signal and …, 2014 – … The topic detection and tracking is more essential for understanding of spoken language especially in dialogue systems. … Wu et al [6] was compared tree topic model, these models is using to topic clustering on network news. … Related articles All 2 versions

Two-Stage Stochastic Email Synthesizer YN Chen, AI Rudnicky – INLG 2014, 2014 – … Request is generated at the narrative level. Form filling: • Topic Model • Sender Model • Slot fillers Figure 1: The system architecture (left) and the demo synthesizer (right). low. 2.1. … 2002. Stochastic natural language generation for spoken dialog systems. … Related articles All 11 versions

Advances in Wikipedia-based Interaction with Robots G Wilcock, K Jokinen – Proceedings of the 2014 Workshop on …, 2014 – … 4. OTHER NEW DIRECTIONS The main restriction on classical spoken dialogue systems has been their inability to move out of a limited … 4.1 Wikipedia-based Topic Modelling The WikiTalk system can make smooth topic shifts from one Wikipedia topic to another by predicting … Related articles All 2 versions

SemEval-2014 Task 2: Grammar Induction for Spoken Dialogue Systems I Klasinas, E Iosif, K Louka, A Potamianos – SemEval 2014, 2014 – … This task is part of a grammar rule induction scenario for high-level rules. The evaluation focuses in spoken dialogue system grammars for multiple domains and languages. … The fundamental idea behind the Biel system is the encoding of domain semantics via topic modeling. … Related articles All 9 versions

Dialogue Strategy Learning in Healthcare: A Systematic Approach for Learning Dialogue Models from Data HR Chinaei, B Chaib-draa, B Chaib – ACL 2014, 2014 – … 3 Objective SDS (Spoken dialogue system) researchers have addressed several practical challenges of apply- ing (PO) MDPs to SDS (Williams, 2006 … We learned the (PO) MDP states by learning the user intents occurred in the dialogue set using a topic modeling approach, ie … Related articles All 10 versions

Powering Spoken Language Interactions With the Crowd WS Lasecki, A Ritter, JP Bigham – … This architecture is, by design, very similar to that of a tradi- tional dialog system: the Scribe plays the role of the speech rec- ognizer … to recover topic information for Chorus workers, who can also be asked to mark key words, helping to increase the accuracy of topic modeling. … Related articles All 5 versions

Bielefeld SC: Orthonormal Topic Modelling for Grammar Induction JP McCrae, P Cimiano – SemEval 2014, 2014 – … Although, it remains unclear how topic model may be applied to the case of grammar induction, we show that it is not impossible and that this may … 1 Introduction Grammar induction is the task of inducing high- level rules for application of grammars in spoken dialogue systems. … Related articles All 9 versions

A Bibliography of the TSD 2014 Proceedings P Sojka – … A Topic Model Scoring Approach for Personalized QA Systems. In Sojka et al. [SHKP14], pages 84–92. [CŠŠ14] Adam Chýlek, Jan Švec, and Luboš Šmídl. Two-layer Semantic Entity Detection and Utterance Validation for Spoken Dialogue Systems. In Sojka et al. … Related articles

Hierarchical Dirichlet Process Topic Modeling for Large Number of Answer Types Classification in Open domain Question Answering S Park, D Lee, J Choi, S Ryu, Y Kim, S Kown… – Information Retrieval …, 2014 – Springer … Hierarchical Dirichlet Process Topic Modeling for Large Number 427 … Intelligence Technology] and National Research Founda- tion of Korean (NRF) [NRF-2014R1A2A1A01003041, Development of multi-party anticipatory knowledge-intensive natural language dialog system]. … Related articles All 3 versions

Model Adaptation GA Fink – Markov Models for Pattern Recognition, 2014 – Springer … In combination with a system for carrying out a natural language dialog, it is possible to use the prediction of the dialog system for the selection … In the same way as dialog-step dependent n-gram models, the individual topic models are trained in advance on text material which is … Cited by 1 Related articles All 2 versions

Cluster based Chinese Abbreviation Modeling Y Shi, YC Pan, MY Hwang – Fifteenth Annual Conference …, 2014 – … Using training data clustering or topic modeling not only addresses the data sparse- ness, but also takes advantage of the fact … abbreviation can improve the generalization capability of many natural lan- guage processing (NLP) systems such as dialogue systems, voice search … Related articles All 4 versions

Chancen und Gefahren automatischer Sprachverarbeitung M Strube – … Spo- ken dialog systems for automated survey interviewing. … 1723–1732. Li, Jiwei, Claire Cardie & Sujian Li (2013c). TopicSpam: A topic-model based approach for spam detection. In Proceedings of the ACL 2013 Conference Short Papers, Sofia, Bulgaria, 4–9 August 2013, pp. … Related articles

Using subtitles to deal with Out-of-Domain interactions D Magarreiro, L Coheur, FS Melo – … Recovering from Non-Understanding Errors in a Conversational Dialogue System. In Workshop on the Semantics and Pragmatics of Di- alogue. … Interfacing virtual agents with collaborative knowledge: Open domain question answering using Wikipedia-based topic models. … Related articles All 2 versions

Civilian Analogs of Army Tasks: Supporting Pedagogical Storytelling Across Domains A Gordon, M Core, SH Kang, C Wang, C Wienberg – … tools, story collections are created only from stories judged as relevant, a process that overcomes the less-than- perfect precision of both the learned topic model and the … Using a menu-based dialogue system, learners select conversational moves in an evolving dialogue context … Related articles All 4 versions

Topical establishment leveraging literature evolution H Xu, E Martin, A Mahidadia – Proceedings of the 14th ACM/IEEE-CS …, 2014 – … 2.3 Topic Modelling To model topics in the AAN, we used the Latent Dirichlet Allocation [1], a highly successful … Information Retrieval 5 Language Knowledge Base Verb Classification 6 NLP Frameworks/Systems Summarization 7 Dialogue Systems Dependency Parsing 8 … Cited by 1 Related articles All 4 versions

Dr. Tux: A Question Answering System for Ubuntu users BA Philip, M Jog, AM Upasani – … Finally, we would like to develop a dialogue system for higher interactive purpose. It would be very useful for the user, especially for resolution of troubleshooting questions. Page 8. 10. References … 6. Gensim: Topic modeling for humans, … Related articles

Picking the Amateur’s Mind–Predicting Chess Player Strength from Game Annotations C Scheible – … 2003. Flexible guidance genera- tion using user model in spoken dialogue systems. In Proceedings of the 41st Annual Meeting of the Association for Computational Linguistics (ACL), pages 256–263. … 2010. Citation author topic model in expert search. … Related articles All 4 versions

Wallace: Incorporating Search into Chatting AS da Silva, X Gao, P Andreae – PRICAI 2014: Trends in Artificial …, 2014 – Springer … For instance, techniques from topic modelling could be employed to help identify the topics in each Wikipedia page or even … Association for Computational Linguistics (2008) 5. Inoue, M., Matsuda, T., Yokoyama, S.: Web resource selection for dialogue system generating natural … Related articles

Computational Discourse Analysis M Dascalu – Analyzing Discourse and Text Complexity for Learning …, 2014 – Springer … 2005) and can be computed by various means of semantic similarity, including semantic distances in ontologies (see 4.3.1 Semantic Distances and Lexical Chains), latent vector space representations (see 4.3.2 Semantic Similarity through Tagged LSA) or topic models (see 4.3 … Related articles

Modeling Cultural Factors in Collaboration and Negotiation K Sycara, G Gordon, S Atran, J Ginges, M Lewis… – 2014 – DTIC Document … A Non-parametric Mixture Model for Topic Modeling Over Time, Social Data Mining. 15-OCT-13, . : , … Random walk features for network-aware topic models, NIPS Workshop on Frontiers of Network Analysis: Methods, Models, and Applications. 19-AUG-13, . : , … Related articles

Latent semantic rational kernels for topic spotting on conversational speech C Weng, DL Thomson, P Haffner… – Audio, Speech, and …, 2014 – … We present how to generalize the LSRK using tf-idf weighting, latent semantic analysis, WordNet and probabilistic topic models. … Then we focus on how to generalize the LSRK using probabilistic topic models, eg, PLSA [10] or LDA [11]. … Related articles All 2 versions

Aspectual Properties of Conversational Activities RJ Passonneau, B Guan, CH Yeung, Y Du… – 15th Annual Meeting of …, 2014 – … Topic modeling methods have also been applied to the identifica- tion of topical segments in speech (Purver et al., 2006)(Eisenstein and … and Cost Annotation (TSCA), was aimed at identifying individual dialog tasks analogous to those carried out by spoken dialog systems, to fa … Related articles All 8 versions

Interacting with Traditional Chinese Culture through Natural Language X Wang, ET Khoo, R Nakatsu, A Cheok – Journal on Computing and …, 2014 – … language interfaces General Terms: Algorithms, Design Additional Key Words and Phrases: Conversational agents, dialogue systems, intangible cultural … processing techniques such as Word Sense Disambiguation [Pedersen and Kolhatkar 2009] or Topic Modeling [Blei 2012]. … Related articles

Social Power in Interactions V Prabhakaran – 2014 – … For example, if a dialog system is engineered to behave appropriately given the user’s expectation of relative power, then the user may … More related work on computational analysis of specific aspects of interactions (eg, dialog act analysis, topic modeling) will be discussed in … Related articles

Generative Probabilistic Models of Goal-Directed Users in Task-Oriented Dialogs A Eshky – … 12 2.2 Components of a dialog system . . . . . … 28 5.1 Bayesian Mixture-of-Multinomials topic model defined over slot values 56 5.2 Mean per-utterance log probability of the held-out data . . . . . 63 5.3 Classifier performance in the extrinsic evaluation of model . . . . . 68 … Related articles All 2 versions

Quality Estimation for Automatic Speech Recognition M Negri, M Turchi, JGC de Souza, D Falavigna – … 2004. Combining acoustic and pragmatic features to predict recognition perfor- mance in spoken dialogue systems. pages 344–351. … 2013a. Topic Models for Translation Quality Estimation for Gisting Purposes. In Proceedings of the Machine Translation Summit XIV. 1822 … Cited by 1 Related articles All 5 versions

Incorporating Weak Statistics for Low-Resource Language Modeling S Novotney – 2014 – Page 1. Incorporating Weak Statistics for Low-Resource Language Modeling by Scott Novotney A dissertation submitted to The Johns Hopkins University in conformity with the requirements for the degree of Doctor of Philosophy. Baltimore, Maryland February, 2014 … Related articles All 2 versions

Statistical dialog management for health interventions U Yasavur – 2014 – … 53 4. Spoken Dialogue System Based on POMDP and Health Screening Dialogues 54 4.1 Underage Drinking Problems and Computer-based Interventions . . . . 55 4.2 Alcohol Screening And Brief Intervention For Youth . . . … 120 8.3.1 Named-Entities and Topic Modeling . . . … Related articles All 4 versions

A Semantic Framework for Harvesting Vague Enterprise Knowledge from Microposts P Alexopoulos, J Pavlopoulos… – International Journal on …, 2014 – World Scientific … isRelevantToResearchArea PARLANCE Open Information Extraction isRelevantToResearchArea PARLANCE Dialogue Systems isRelevantToResearchArea K-DRIVE Linked Data isRelevantToResearchArea K-DRIVE Ontologies … Related articles All 2 versions

Failure to Replicate the Unconscious Thought Advantages V ?avojová, EB Mikušková – Information Technology – Conferences. Related articles All 4 versions

Automatic Vocabulary Adaptation Based on Semantic and Acoustic Similarities S Yamahata, Y Yamaguchi, A Ogawa… – … on Information and …, 2014 – … For LDA, we first calculated topic models for relevant document set as ? z p(w|z) ? p(z|d) as described in [20], and then esti- mated the occurrence probabilities of words in target spoken documents p(w|S) = ? z p(w|z) ? p(z|S). Here, w indicates words in relevant documents, z … Related articles All 5 versions

Identifying relevant cues for uncertainty in dialogue T Schrank, B Schuppler – … to perform this task. As humans make use of such paralinguistic information quite heavily to shape communication, computer systems such as dialogue systems are likely to benefit from its use as well. This thesis provides an … Related articles All 2 versions

Adjective-Based Estimation of Short Sentence’s Impression NTT An, M Hagiwara – 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

Semi-automatic Domain Modeling from Multilingual Corpora S Pollak – 2014 – Page 1. Univerza v Ljubljani/University of Ljubjana Filozofska fakulteta/Faculty of Arts Oddelek za prevajalstvo/Department of Translation Senja Pollak Polavtomatsko modeliranje podro?nega znanja iz ve?jezi?nih korpusov Semi … Cited by 1 Related articles

Artificial Conversations for Chatter Bots Using Knowledge Representation, Learning, and Pragmatics C Chakrabarti – 2014 – … 22 2.2 The Syntactic Approach . . . . . 26 2.3 The Semantic Approach . . . . . 27 2.4 Dialogue systems . . . . . 27 viii Page 9. Contents 2.5 Limitations of existing approaches . . . . . 29 … Cited by 1 Related articles All 5 versions

Songrecommend: From summarization to recommendation S Tata, B Di Eugenio – Natural Language Engineering, 2014 – Cambridge Univ Press … pertinent text segment discusses. This task roughly corresponds to identifying the flow of topics in a review. In principle, it could benefit from sophisticated topic models or from reference resolution algorithms. However, given the still … Cited by 2 Related articles All 3 versions

Topical Structure in Long Informal Documents A Kazantseva – 2014 – … informative, alternative. To date, models based on topical segments have been used in information extraction, essay analysis and scoring, automatic assessment of coherence of text, automatic dialogue systems, etc. [Webber et al., 2012]. On the other side of the issue … Cited by 1 Related articles All 7 versions

Automatically generating reading lists JG Jardine – … of Cambridge, Computer Laboratory, Technical Report, 2014 – … reading lists. It combines Latent Topic Models with Personalised PageRank and Age Adjustment in a novel way to generate reading lists that are of better quality than those generated by state- of-the-art search engines. TPR … Cited by 1 Related articles All 4 versions

Foundations and Trends in Signal Processing L Deng, Y Dong – Signal Processing, 2014 – Page 1. the essence of knowledge FnT SIG 7:3-4 Deep Learning; Methods and Applications Li Deng and Dong Y u Foundations and Trends® in Signal Processing 7:3-4 Deep Learning Methods and Applications Li Deng and Dong Yu now now Page 2. 7.1. … Cited by 3 Related articles All 12 versions

Combining visual recognition and computational linguistics: linguistic knowledge for visual recognition and natural language descriptions of visual content M Rohrbach – 2014 – Page 1. Combining Visual Recognition and Computational Linguistics Linguistic Knowledge for Visual Recognition and Natural Language Descriptions of Visual Content Thesis for obtaining the title of Doctor of Engineering Science (Dr.-Ing.) … Related articles All 4 versions

Position Papers, 2014 Specialist Meeting—Spatial Search A Franklin, R Hardy, L McDonald – … Search Weighted keyword matching, topic models, similarity Colocation queries, query-by-place … [5] H. Cuayáhuitl, N. Dethlefs, K.-F. Richter, T. Tenbrink, and J. Bateman, “A dialogue system for indoor wayfinding using text-based natural language,” Int. J. Comput. Linguist. Appl. … Related articles