Latent Semantic & Dialog Systems 2016


Notes:

  • Conversational informatics
  • Topic generation

Resources:

  • deeptutor.org .. advanced intelligent tutoring system for deep understanding of complex science topics
  • nlplab.org .. virtual lab, natural language processing laboratory

Wikipedia:

See also:

Dialog Systems Meta Guide


How NOT to evaluate your dialogue system: An empirical study of unsupervised evaluation metrics for dialogue response generation
CW Liu, R Lowe, IV Serban, M Noseworthy… – arXiv preprint arXiv …, 2016 – arxiv.org
How NOT To Evaluate Your Dialogue System: An Empirical Study of Unsupervised Evaluation Metrics for Dialogue Response Generation … We investigate evaluation metrics for end- to-end dialogue systems where supervised labels, such as task completion, are not available. …

Counter-fitting word vectors to linguistic constraints
N Mrkši?, DO Séaghdha, B Thomson, M Gaši?… – arXiv preprint arXiv …, 2016 – arxiv.org
… systems. The modelling work closest to ours are Liu et al. (2015), who use antonymy and WordNet hierarchy information to modify the heavyweight Word2Vec training objective; Yih et al. (2012), who use a Siamese neural network to improve the qual- ity of Latent Semantic …

Multi-Domain Joint Semantic Frame Parsing Using Bi-Directional RNN-LSTM.
D Hakkani-Tür, G Tür, A Celikyilmaz… – …, 2016 – pdfs.semanticscholar.org
… The last hidden layer of the query is supposed to contain a latent semantic repre- sentation of the whole input utterance, so that it can be … [4] Y.-N. Chen, WY Wang, and AI Rudnicky, “Unsupervised in- duction and filling of semantic slots for spoken dialogue systems using frame …

Zero-shot learning of intent embeddings for expansion by convolutional deep structured semantic models
YN Chen, D Hakkani-Tür, X He – Acoustics, Speech and Signal …, 2016 – ieeexplore.ieee.org
… 2015, ACL. [8] Giuseppe Di Fabbrizio, Gokhan Tur, and Dilek Hakkani-Tür, “Bootstrapping spoken dialog systems with data reuse,” in … IEEE, 2014, pp. 584–589. [17] Yelong Shen, Xiaodong He, Jianfeng Gao, Li Deng, and Gre- goire Mesnil, “A latent semantic model with …

Conversations with AutoTutor help students learn
AC Graesser – International Journal of Artificial Intelligence in …, 2016 – Springer
… We have evaluated many semantic matchers over the years. The best results are a combination of latent semantic analysis (LSA) (Landauer et al. … Researchers who have developed tutorial dialogue systems with deep syntactic parsers (eg, BEETLE II, Dzikovska et al. …

Adobe-MIT submission to the DSTC 4 Spoken Language Understanding pilot task
F Dernoncourt, JY Lee, TH Bui, HH Bui – arXiv preprint arXiv:1605.02129, 2016 – arxiv.org
… The Fourth Dialog State Tracking Challenge. In Proceedings of the 7th International Workshop on Spoken Dialogue Systems (IWSDS), 2016. … IEEE, 1999. 16. R. Serafin and B. Di Eugenio. Flsa: Extending latent semantic analysis with features for dialogue act classification. …

Squeezing bottlenecks: exploring the limits of autoencoder semantic representation capabilities
P Gupta, RE Banchs, P Rosso – Neurocomputing, 2016 – Elsevier
… dimensionality reduction techniques is to transform high dimensional data (R n R n ) into a much lower dimension representation (R m R m ) pertaining the inherent structure of the original data where m?n m ? n . One such widely used approach is latent semantic indexing (LSI …

Topic detection and tracking for conversational content by using conceptual dynamic latent Dirichlet allocation
JF Yeh, YS Tan, CH Lee – Neurocomputing, 2016 – Elsevier
… to learn and recognize scenes and places [5]. Considering industrial applications, Contreras-Pina and Rios provided an empirical comparison of latent semantic models [6 … A multidomain conversational dialogue system focuses on processing goal-oriented dialogue and …

Multi-modal variational encoder-decoders
IV Serban, II Ororbia, G Alexander, J Pineau… – arXiv preprint arXiv …, 2016 – arxiv.org
… Thus, for complex, multi-modal distributions — such as the distribution over topics in a text corpus, or natural language responses in a dialogue system — the uni-modal Gaussian prior inhibits the model’s ability to ex- tract and represent important structure in the data. …

Predicting humor response in dialogues from TV sitcoms
D Bertero, P Fung – Acoustics, Speech and Signal Processing …, 2016 – ieeexplore.ieee.org
… 6. Latent semantic features: we take the cosine similari- ties between latent semantic vector representations of each utterance with the four previous … In future work we plan to integrate humor generation and response prediction into a dialog system with the objective for a more …

GeoSRS: A hybrid social recommender system for geolocated data
J Capdevila, M Arias, A Arratia – Information Systems, 2016 – Elsevier
… Several text modeling techniques are assessed under our recommendation scheme, such as Latent Dirichlet Allocation (LDA) [6], Latent Semantic Analysis (LSA) [10], or TF–IDF [46] and [41]. … Reschke et al. [40] propose a recommendation dialog system built upon narrow …

The dialport portal: Grouping diverse types of spoken dialog systems
T Zhao, K Lee, M Eskenazi – Workshop on Chatbots and …, 2016 – workshop.colips.org
… taking a spoken dialog system to the real world. In: in Proc. of Interspeech 2005. Citeseer (2005) 13. Shen, Y., He, X., Gao, J., Deng, L., Mesnil, G.: A latent semantic model with convolutional- pooling structure for information retrieval. …

Improving neural language models with a continuous cache
E Grave, A Joulin, N Usunier – arXiv preprint arXiv:1612.04426, 2016 – arxiv.org
… PAMI, 1983. Jerome R Bellegarda. Exploiting latent semantic information in statistical language modeling. Proceedings of the IEEE, 2000. … Evaluating prerequisite qualities for learning end-to-end dialog systems. arXiv preprint arXiv:1511.06931, 2015. …

Semantic language models with deep neural networks
AO Bayer, G Riccardi – Computer Speech & Language, 2016 – Elsevier
… Bellegarda, 2000a and Bellegarda, 2000b uses latent semantic analysis (LSA) to extend the trigger pairs approach. … This may lead to problems especially for spoken dialog systems, where one of the main goals of these systems is to extract user intentions and the meaning of …

A novel density-based clustering method using word embedding features for dialogue intention recognition
J Jang, Y Lee, S Lee, D Shin, D Kim, H Rim – Cluster Computing, 2016 – Springer
… In: Proceedings of EACL, pp. 482–491 (2012). 17. Kang, S., Park, H., Seo, J.: Emotion classification of user’s utterance for a dialogue system. Korean J. Cognit. Sci. … 3–33. Academic Press, New York (1980)CrossRefGoogle Scholar. 20. Dumais, ST: Latent semantic analysis. Ann. …

An architecture for telenoid robot as empathic conversational android companion for elderly people
R Sorbello, A Chella, M Giardina, S Nishio… – … Autonomous Systems 13, 2016 – Springer
… this paper was illustrated a humanoid robotic system capable of exploiting a knowledge base through the use of latent semantic analysis technique … In particular, the Telenoid Dialogue System generated the right questions to submit to elderly people in according to the focus of …

Crowd-sourcing NLG Data: Pictures Elicit Better Data
J Novikova, O Lemon, V Rieser – arXiv preprint arXiv:1608.00339, 2016 – arxiv.org
… MRs into pictorial representations as used in, eg (Black et al., 2011; Williams and Young, 2007) for evaluating spoken dialogue systems. … This measure is based on dis- tributional similarity and Latent Semantic Analysis (LSA), and is further complemented with semantic relations …

DialPort: Connecting the spoken dialog research community to real user data
T Zhao, K Lee, M Eskenazi – Spoken Language Technology …, 2016 – ieeexplore.ieee.org
… Matsuyama, Kotaro Funakoshi, and Hiroshi G Okuno, “A two-stage domain selection framework for extensible multi-domain spoken dialogue systems,” in Proceedings of … [15] Yelong Shen, Xiaodong He, Jianfeng Gao, Li Deng, and Grégoire Mesnil, “A latent semantic model with …

Recent Advances on Human-Computer Dialogue
X Wang, C Yuan – CAAI Transactions on Intelligence Technology, 2016 – Elsevier
… Abstract. Human-Computer dialogue systems provide a natural language based interface between human and computers. They are widely demanded in network information services, intelligent accompanying robots, and so on. … 2. Frames of goal-driven dialogue systems. Fig. …

Fostering parent–child dialog through automated discussion suggestions
A Boteanu, S Chernova, D Nunez… – User Modeling and User …, 2016 – Springer
… ignored. Another popular algorithm is latent semantic indexing (LSI) (Deerwester et al. 1990), predating LDA. … occurrences. Latent semantic analysis (LSA) (Hofmann 1999) improves on LSI by introducing an EM step in place of SVD. …

An intelligent tutoring system for teaching the grammar of the Arabic language
MH Mahmoud, SHA El-Hamayed – Journal of Electrical Systems and …, 2016 – Elsevier
… To handle this input, the Auto Tutor project uses computational linguistics algorithms including latent semantic analysis, regular expression matching … d) Beetle II System: is a tutorial dialog system designed to accept unrestricted language input with two different tutorial planning …

Thematic fit evaluation: an aspect of selectional preferences
A Sayeed, C Greenberg, V Demberg – ACL 2016, 2016 – anthology.aclweb.org
… This is particularly important as dialog systems grow steadily less task-specific. … 2000. Random indexing of text samples for latent semantic analysis. In Proceedings of the 22nd annual conference of the cognitive sci- ence society. Citeseer, volume 1036. Alessandro Lenci. 2011. …

Learning interactive behavior for service robots the challenge of mixed-initiative interaction
P Liu, DF Glas, T Kanda, H Ishiguro – Proceedings of the Workshop on …, 2016 – irc.atr.jp
… and gaze behaviors were recognized in an imitative game using a hidden Markov model [8]. Data-driven dialogue systems have been … common text-processing techniques such as removal of stop words, stemming, enumeration of n-grams, and Latent Semantic Analysis, as well …

Continuously Improving Natural Language Understanding for Robotic Systems through Semantic Parsing, Dialog, and Multi-modal Perception
J Thomason – 2016 – pdfs.semanticscholar.org
Page 1. Continuously Improving Natural Language Understanding for Robotic Systems through Semantic Parsing, Dialog, and Multi-modal Perception Jesse Thomason The University of Texas at Austin jesse@cs.utexas.edu Doctoral Dissertation Proposal November 23, 2016 …

Learning dialogue dynamics with the method of moments
M Barlier, R Laroche, O Pietquin – … Technology Workshop (SLT) …, 2016 – ieeexplore.ieee.org
… and dialogues are considered as sequences of dialogue acts, represented by their Latent Dirichlet Alloca- tion (LDA) and Latent Semantic Analysis (LSA). … case, the learned model is not directly usable for planning algorithms, which rely at the heart of dialogue systems since [18 …

Modeling user’s decision process through gaze behavior
K Shimonishi – Proceedings of the 18th ACM International Conference …, 2016 – dl.acm.org
… Misu et al. [10] proposed a spoken dialogue system based on introducing user … The proposed model is based on probabilistic Latent Semantic Analysis (pLSA) [9]. Using this model, aspects can be learned from gaze data in a data-driven fashion as a parameter estimation. …

A Study on Image Semantic Analysis Algorithm for Natural Language Understanding
J LUO, HUAJUN WANG, YANMEI LI… – Journal of Residuals …, 2016 – dpi-journals.com
… different scales, and on the other hand, a density adaptive selection algorithm can be used to obtain the optimal probabilistic latent semantic analysis results. … this field, do we make full use of the great function of big data to build a data-driven natural language dialogue system? …

Continuous expressive speaking styles synthesis based on CVSM and MR-HMM
J Lorenzo-Trueba, R Barra-Chicote… – … of COLING 2016, the …, 2016 – aclweb.org
… The problem appears when one needs to develop applications such as dialogue systems or robotic interfaces, for which a more expressive … With that consideration in mind Latent Semantic Analysis (LSA) (Deerwester et al., 1990; Landauer et al., 2013), nowadays referred to as …

Deep Learning+ Student Modeling+ Clustering: a Recipe for Effective Automatic Short Answer Grading.
Y Zhang, R Shah, M Chi – EDM, 2016 – pdfs.semanticscholar.org
… Then the text similarity is calculated by weighting the similarities of general words simw(s, c) and those of domain specific words simd(s, c). • Latent Semantic Analysis (LSA, Landauer and Du- mais, 1997): is a computational … Beetle ii: an adaptable tutorial dialogue system. …

Combining Memory and Emotion With Dialog on Social Companion: A Review
J Zhang, NM Thalmann, J Zheng – Proceedings of the 29th International …, 2016 – dl.acm.org
… ”Hello Emily, how are you today?”: personalised dialogue in a toy to engage children. In Proceedings of the Workshop on Companionable Dialogue Systems, pages 19–24. Association for Computational Linguistics, 2010. … Indexing by latent semantic analysis. …

Study on Optimal Spoken Dialogue System for Robust Information Search in the Real World
?? – 2016 – eprints.lib.hokudai.ac.jp
… Page 2. DOCTORAL THESIS Study on Optimal Spoken Dialogue System for Robust Information Search in the Real World Author: … Key Technologies of Spoken Dialogue Systems and Related Works In this chapter, the key technologies of spoken dialogue systems are described. …

Text classification for spoken dialogue systems
R Sergienko – 2016 – oparu.uni-ulm.de
… 2.2. Text Classification Applied for Spoken Dialogue Systems…………… 19 2.3. … Self-adjusting Genetic Algorithm…………… 44 2.5.5. Principal Component Analysis…………… 46 2.5.6. Latent Semantic Analysis…………… 47 …

Dead Man Tweeting
D Nilsson, M Sahlgren, J Karlgren – Workshop on Collecting and …, 2016 – diva-portal.org
… Landauer, TK and Dumais, ST (1997). A solution to Plato’s problem: The latent semantic analysis theory of acquisition, induction, and representation of knowledge. … Semantically conditioned lstm- based natural language generation for spoken dialogue systems. …

Nonparametric Bayesian Models for Spoken Language Understanding.
K Wakabayashi, J Takeuchi, K Funakoshi, M Nakano – EMNLP, 2016 – aclweb.org
Page 1. Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, pages 2144–2152, Austin, Texas, November 1-5, 2016. c 2016 Association for Computational Linguistics Nonparametric …

Rational Decision Support with a Natural Language Dialogue System
D Mäurer – 2016 – tuprints.ulb.tu-darmstadt.de
… Dialogue System Vom Fachbereich Informatik der Technischen Universität Darmstadt genehmigte Dissertation … Therefore, we have developed VPINO, a text-based dialogue system, intended for holding structured coaching conversations in German language. …

Question answering in conversations: Query refinement using contextual and semantic information
M Habibi, P Mahdabi, A Popescu-Belis – Data & Knowledge Engineering, 2016 – Elsevier
This paper introduces a query refinement method applied to questions asked by users to a system during a meeting or a conversation that they have with other use.

Knowledge Enhanced Hybrid Neural Network for Text Matching
Y Wu, W Wu, Z Li, M Zhou – arXiv preprint arXiv:1611.04684, 2016 – arxiv.org
Page 1. Knowledge Enhanced Hybrid Neural Network for Text Matching Yu Wu†? , Wei Wu‡ , Zhoujun Li† , Ming Zhou‡ †State Key Lab of Software Development Environment, Beihang University, Beijing, China ‡ Microsoft …

Sentence Level Recurrent Topic Model: Letting Topics Speak for Themselves
F Tian, B Gao, D He, TY Liu – arXiv preprint arXiv:1604.02038, 2016 – arxiv.org
Page 1. Sentence Level Recurrent Topic Model: Letting Topics Speak for Themselves Fei Tian? University of Science and Technology of China tianfei@mail.ustc.edu.cn Bin Gao Microsoft Research bingao@microsoft.com Di He Microsoft Research dihe@microsoft.com …

Comparative studies of AIML
Y Wei, X Zhu, B Sun, B Sun – Systems and Informatics (ICSAI) …, 2016 – ieeexplore.ieee.org
… Three experimental systems have been constructed (one is a pure natural language dialogue system, one is a related domain knowledge … the Chinese word segmentation, latent semantic analysis, semantic matching and TTS technology to give the structure design and function …

Shall I Be Your Chat Companion?: Towards an Online Human-Computer Conversation System
R Yan, Y Song, X Zhou, H Wu – … of the 25th ACM International on …, 2016 – dl.acm.org
Page 1. “Shall I Be Your Chat Companion?” Towards an Online Human-Computer Conversation System Rui Yan1,3 1Institute of Computer Science and Technology (ICST) Peking University Beijing 100871, China yanrui02@baidu.com …

Spoken Language Understanding
M McTear, Z Callejas, D Griol – The Conversational Interface, 2016 – Springer
… Dialog act Intent Tokenization Bag of words Latent semantic analysis Regular expression Part-of-speech tagging Information extraction Semantic role Semantic grammar Context-free grammar Dependency grammar Statistical spoken … 3. Tell me about spoken dialog systems. 4. …

a~ îáÇ= RÉáííÉê
PI CRII – 2016 – pdfs.semanticscholar.org
… 2007 FASiL: A multimodal dialogue system for E-Mail. Institute of Linguistics, U. Potsdam, Germany 2005 … Ben Hachey, Gabriel Murray, and DR. The Embra system: Query-oriented multi-document summarization with a very large latent semantic space. …

Topic Augmented Neural Network for Short Text Conversation.
Y Wu, W Wu, Z Li, M Zhou – CoRR, 2016 – pdfs.semanticscholar.org
Page 1. Topic Augmented Neural Network for Short Text Conversation Yu Wu†? , Wei Wu‡ , Zhoujun Li† , Ming Zhou‡ †State Key Lab of Software Development Environment, Beihang University, Beijing, China ‡ Microsoft Research …

Collaborative Review in Writing Analytics: N-Gram Analysis of Instructor and Student Comments.
A Rudniy, N Elliot – EDM (Workshops), 2016 – pdfs.semanticscholar.org
… [25] determines that the n-gram model in conjunction with latent semantic analysis produce … pedagogically-based applications using bigram analysis, Forbes-Riley and Litman [40] have developed approaches for adapting student affect in intelligent tutoring dialogue systems. …

A Few Words on Topic Modeling
H Chinaei, B Chaib-draa – Building Dialogue POMDPs from Expert …, 2016 – Springer
… 2.3 (a) Unigram model. (b) Mixture of unigrams. (c) Probabilistic latent semantic analysis (PLSA). Figure 2.3a shows the unigram model. … 4 In the following chapter, we introduce the sequential decision making domain and its application on spoken dialogue systems. References. …

Response Selection with Topic Clues for Retrieval-based Chatbots
Y Wu, W Wu, Z Li, M Zhou – arXiv preprint arXiv:1605.00090, 2016 – arxiv.org
… message-response matching. Introduction Human-computer conversation is a challenging task in AI and NLP. Existing conversation systems include task ori- ented dialog systems and non task oriented chatbots. The former aims …

Detecting affective states from text based on a multi-component emotion model
Y Gao, W Zhu – Computer Speech & Language, 2016 – Elsevier
A multi-component emotion model is proposed to describe the affective states comprehensively and provide more details about emotion for the application of expre.

An Information Reinstatement Dealing with Machine Learning
F Parwej, H Alquhayz – Transactions on Machine Learning …, 2016 – scholarpublishing.org
… documents). Large-scale retrieval systems, such as the Lockheed Dialog system, came into use early in the 1970s. … function. In latent semantic analysis (LSA) aims at modeling term correlation [25], to overcome the term mismatch problem. …

Analysis, optimization and development of an answer scoring system
I Lopez-Gazpio – 2016 – addi.ehu.es
… 7 sponse classes1. The corpora has been created out of two established sources: the BEETLE corpus, a data set collected and annotated during the evalu- ation of the BEETLE II tutorial dialogue system [Dzikovska et al., 2010]; and the SCIENTSBANK corpus, a set of student …

Text analytics in industry: Challenges, desiderata and trends
A Ittoo, LM Nguyen, A van den Bosch – Computers in Industry, 2016 – Elsevier
The recent decades have witnessed an unprecedented expansion in the volume of unstructured data in digital textual formats. Companies are now starting to recogn.

A Survey on Cross-Language Information Retrieval
SK Dwivedi, G Chandra – … Journal on Cybernetics & Informatics (IJCI) Vol – researchgate.net
… ST, Letsche, TA, Littman, ML, & Landauer, TK, (1997, March) “Automatic cross- language retrieval using latent semantic indexing”, In … workshop on Language-Enabled educational technology and Development and evaluation of Robust Spoken Dialogue Systems, Germany, pp. …

Coreference applications to summarization
J Steinberger, M Kabadjov, M Poesio – Anaphora Resolution, 2016 – Springer
… The discussion follows the summarization framework based on Latent Semantic Analysis (LSA), however, the ideas can be applied to any sentence-scoring approach. … Keywords. Coreference applications to summarization Applications of coreference Latent semantic analysis. …

Summarizing Meeting Transcripts Based on Functional Segmentation
MH Bokaei, H Sameti, Y Liu – IEEE/ACM Transactions on Audio …, 2016 – ieeexplore.ieee.org
Page 1. IEEE/ACM TRANSACTIONS ON AUDIO, SPEECH, AND LANGUAGE PROCESSING, VOL. 24, NO. 10, OCTOBER 2016 1831 Summarizing Meeting Transcripts Based on Functional Segmentation Mohammad Hadi Bokaei, Hossein Sameti, and Yang Liu …

Designing a Personal Assistant for Life-Long Learning (PAL3).
WR Swartout, BD Nye, A Hartholt, A Reilly… – FLAIRS Conference, 2016 – aaai.org
… 493 Page 4. natural language processing techniques, including latent semantic analysis and pattern matching, AutoTutor com- pares students’ answers with the good and bad exemplars and provides feedback. … International Workshop on Spoken Dialogue Systems. …

PersoNER: Persian Named-Entity Recognition
H Poostchi, E Zare Borzeshi, M Abdous… – The 26th International …, 2016 – opus.lib.uts.edu.au
… Applications Tim Baldwin Maria Liakata Dialog Processing and Dialog Systems, Multimodal Interfaces Nina Dethlefs Simon Keizer Giuseppe Riccardi Speech Recognition, Text-To-Speech, Spoken Language Understanding Florian Metze Chung-Hsien Wu …

Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers
Y Matsumoto, R Prasad – Proceedings of COLING 2016, the 26th …, 2016 – aclweb.org
… Applications Tim Baldwin Maria Liakata Dialog Processing and Dialog Systems, Multimodal Interfaces Nina Dethlefs Simon Keizer Giuseppe Riccardi Speech Recognition, Text-To-Speech, Spoken Language Understanding Florian Metze Chung-Hsien Wu …

Affective analysis and Modeling of Spoken Dialogue Transcripts
E Palogiannidi – 2016 – researchgate.net
… Jose Lopes, Arodami Chorianopoulou, Elisavet Palogiannidi, Helena Moniz, Alberto Abad, Katerina Louka, Elias Iosif and Aleandros Potamianos “The SpeDial Datasets: Datasets for Spoken Dialogue Systems Analytics”, in Proceedings of the 10th edition of the Language …

Solving Verbal Questions in IQ Test by Knowledge-Powered Word Embedding.
H Wang, F Tian, B Gao, C Zhu, J Bian, TY Liu – EMNLP, 2016 – aclweb.org
Page 1. Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, pages 541–550, Austin, Texas, November 1-5, 2016. c 2016 Association for Computational Linguistics Solving Verbal Questions in IQ Test by Knowledge-Powered Word …

Exploiting Semantic and Topic Context to Improve Recognition of Proper Names in Diachronic Audio Documents
I Sheikh – 2016 – tel.archives-ouvertes.fr
… 63 3.1.1 Distributional Semantics . . . . . 64 3.1.2 Distributional Modelling Approaches and Our Choice . . . 66 3.2 Latent Semantic Analysis (LSA) . . . . 68 3.3 Latent Dirichlet Allocation (LDA) Topic Model . . . . . 69 …

Transfer learning for cross-lingual sentiment classification with weakly shared deep neural networks
G Zhou, Z Zeng, JX Huang, T He – … of the 39th International ACM SIGIR …, 2016 – dl.acm.org
Page 1. Transfer Learning for Cross-Lingual Sentiment Classification with Weakly Shared Deep Neural Networks Guangyou Zhou1, Zhao Zeng1, Jimmy Xiangji Huang2, and Tingting He1 1 School of Computer, Central China …

The conversational interface
M McTear, Z Callejas, D Griol – New York: Springer, 2016 – Springer
… With the evolution of speech recognition and natural language technologies, IVR systems rapidly became more sophisticated and enabled the creation of complex dialog systems that could handle natural language queries and many turns of interaction. …

An ontology for human-like interaction systems
EA García – 2016 – core.ac.uk
… concepts in the ontology. Thus, the challenge is to develop a dialogue system able of Page 11. 11 learning new concepts and semantic relations by itself, enriching its ontology for improving future interactions. What usually hinders …

An ontology for human-like interaction systems
E Albacete García – 2016 – e-archivo.uc3m.es
… concepts in the ontology. Thus, the challenge is to develop a dialogue system able of Page 12. 11 learning new concepts and semantic relations by itself, enriching its ontology for improving future interactions. What usually hinders …

Building Dialogue POMDPs from Expert Dialogues: An End-to-end Approach
H Chinaei, B Chaib-draa – 2016 – books.google.com
… Chapter 1 Introduction Spoken dialog systems (SDSs) are the systems that help the human user to accomplish a task using the spoken … such as unigrams and mixture of unigrams (Bishop 2006; Manning and Schütze 1999), as well as probabilistic latent semantic analysis (PLSA …

Question Similarity Modeling with Bidirectional Long Short-Term Memory Neural Network
C An, J Huang, S Chang… – Data Science in …, 2016 – ieeexplore.ieee.org
… distributional model, latent semantic analysis, mapping textual high-dimensional features to lower-dimensional latent semantic space for … Semantically conditioned lstm-based natural language generation for spoken dialogue systems[J]. arXiv preprint arXiv:1508.01745, 2015. …

An Iterative Transfer Learning Based Ensemble Technique for Automatic Short Answer Grading
S Roy, HS Bhatt, Y Narahari – arXiv preprint arXiv:1609.04909, 2016 – arxiv.org
… LSA and W2V: These are the measures in vector space similarity category. In this category we first chose the most popular measure for measuring semantic similarity viz. Latent Semantic Analysis Page 6. Fig. 1. The block diagram of the proposed technique. …

A New Perspective of Negotiation-Based Dialog to Enhance Metacognitive Skills in the Context of Open Learner Models
RM Suleman, R Mizoguchi, M Ikeda – International Journal of Artificial …, 2016 – Springer
… studies. The first evaluation study focuses on the dialogue management capabilities of our system and demonstrates that our dialog system works satisfactorily to realize meaningful and natural interactions for negotiation. The …

How fashionable is each street?: Quantifying road characteristics using social media
T Nishimura, K Nishida, H Toda… – Advances in Social …, 2016 – ieeexplore.ieee.org
… any of several input methods may be used, such as a user’s direct input via a search box and automatic extraction from interaction with dialogue system [2]. To satisfy both user set length and characteristics by existing multi-criteria path finding algorithms (eg, [3]), we need the …

A study of the use of natural language processing for conversational agents
RS Wilkens – 2016 – lume.ufrgs.br
… tools necessary to build a conversational agent. A dialogue system in general has six basic com- ponents, such as shown in Figure 1.1. … Thus approaches such as Latent Semantic Analysis (LSA), Naive Bayes and Markov models calculate the co- occurrence of terms in texts. …

Computer Vision and Natural Language Processing: Recent Approaches in Multimedia and Robotics
P Wiriyathammabhum, D Summers-Stay… – ACM Computing …, 2016 – dl.acm.org
Page 1. 71 Computer Vision and Natural Language Processing: Recent Approaches in Multimedia and Robotics PERATHAM WIRIYATHAMMABHUM, University of Maryland, College Park DOUGLAS SUMMERS-STAY, US …

A data mining approach to ontology learning for automatic content-related question-answering in MOOCs.
S Shatnawi – 2016 – openair.rgu.ac.uk
… 20 2.6.1 Probabilistic Latent Semantic Analysis (PLSA) . . . . … Another method in text preprocessing is feature transformation which aims to improve the quality of document representations. These methods include latent semantic indexing, Non-Matrix factorisation, and …

Automated fictional ideation via knowledge base manipulation
MT Llano, S Colton, R Hepworth, J Gow – Cognitive computation, 2016 – Springer
… physician. We use the UMBC semantic similarity service 7 [9], which uses Latent Semantic Analysis to identify words occurring in the same contexts, in order to provide a measure of relatedness. Fig. 4 Scope scenarios flowchart. …

Prominent feature extraction for sentiment analysis
B Agarwal, N Mittal – 2016 – Springer
… manifestations of affect (facial expressions, posture, behavior, physiology), and affective interfaces and applications (dialogue systems, games, learning etc … gain IMDb Internet Movie Database IT Information technology KNN K-nearest neighbor LSA Latent semantic analysis ME …

Data-Driven HRI: Learning Social Behaviors by Example From Human–Human Interaction
P Liu, DF Glas, T Kanda… – IEEE Transactions on …, 2016 – ieeexplore.ieee.org
… Data-driven dialogue systems have been demonstrated in robots that infer meanings from spoken utterances. … Our approach represents interaction data via several abstractions, as follows: 1) Customer speech is vectorized using latent semantic anal- ysis (LSA) and other text …

A Corpus Driven Computational Intelligence Framework for Deception Detection in Financial Text
SZ Minhas – 2016 – dspace.stir.ac.uk
… 5.1 Introduction ….. 166 5.2 Latent Semantic Analysis (LSA) …. 171 … kNN: k-Nearest Neighbors LSA: Latent Semantic Analysis LDA: Latent Drichlet Allocation …

Automatic Processing of Text Responses in Large-Scale Assessments
F Zehner – 2016 – mediatum.ub.tum.de
… Semantic spaces can be computed by, for instance, Latent Semantic Analysis (LSA; Deerwester, Dumais, … (II) automatic opposed to none and manual spelling correction (III) Latent Semantic Analysis (LSA) opposed to Explicit Semantic Analysis (ESA) …

Automatic estimation of users’ verbal intelligence
K Zablotskaya – 2016 – oparu.uni-ulm.de
… Brief Intelligence Test kNN k-Nearest Neighbours LIWC Linguistic Inquiry and Word Count LOO-CV Leave-One-Out Cross Validation LSA Latent Semantic Analysis LSM Language Style Model NB Naive Bayes SQ Social Quotient SDS Spoken Dialogue System SVM Support …

Linguistic Knowledge in Data-Driven Natural Language Processing
Y Tsvetkov – 2016 – cs.cmu.edu
… driven models underperform in low-resource settings: they are inadequate, for example, to translate African languages, to detect metaphors in Russian and Persian, to grammatically parse Cantonese, to model Latin or Hebrew morphology, to build dialog systems for indigenous …

Effective Dimensionality Reduction of Payload-Based Anomaly Detection in TMAD Model for HTTP Payload.
M Kakavand, N Mustapha, A Mustapha, MT Abdullah – TIIS, 2016 – kpubs.org
… The most popular feature extraction approaches include the principal component analysis (PCA) and particularly multidimensional scaling (MDS), latent semantic analysis (LSA), learning vector quantization (LVQ), local linear embedding (LLE) and self- organizing maps (SOM …

Metaphor: A computational perspective
T Veale, E Shutova… – Synthesis Lectures on …, 2016 – morganclaypool.com
… Semantic Role Labeling Martha Palmer, Daniel Gildea, and Nianwen Xue 2010 Spoken Dialogue Systems Kristiina Jokinen and Michael McTear 2009 Introduction to Chinese Natural Language Processing Kam-Fai Wong, Wenjie Li, Ruifeng Xu, and Zheng-sheng Zhang 2009 …

Using linguistic knowledge for improving automatic speech recognition accuracy in air traffic control
VN Nguyen – 2016 – brage.bibsys.no
Page 1. Using Linguistic Knowledge for Improving Automatic Speech Recognition Accuracy in Air Traffic Control Master’s Thesis in Computer Science Van Nhan Nguyen May 18, 2016 Halden, Norway Page 2. Page 3. Abstract …

Automating Language Sample Analysis
E Morley – 2016 – digitalcommons.ohsu.edu
… of language sample analysis. Language sample analysis (LSA, not to be confused with latent semantic analysis, which is not discussed in this thesis) is the practice of eliciting, tran- scribing, and analyzing samples of spoken language. At present, LSA is used for …

From predictive to interactive multimodal language learning
A Lazaridou – 2016 – eprints-phd.biblio.unitn.it
Page 1. From predictive to interactive multimodal language learning by Angeliki Lazaridou Submitted to the Center for Mind and Brain Sciences (CiMeC) in partial fulfillment of the requirements for the degree of Doctor of Philosophy at the UNIVERSITY OF TRENTO …

Machine Learning: The New AI
E Alpaydin – 2016 – books.google.com
Page 1. MACHINE LEARNING ETHEM ALPAYDIN