Topic detection and tracking for conversational content by using conceptual dynamic latent Dirichlet allocation

This study proposes a conceptual dynamic latent Dirichlet allocation (CDLDA) model for topic detection and tracking in conversational content. Topic detection and tracking is vital for conversational communication, especially for spoken interactions. Because topic transitions occur frequently during conversational communication (i.e., a conversation usually contains many topics), language processors must detect different topics in conversational content. Considering the structure of spoken dialogue, the dynamic model was employed in this study to capture the sequence of two adjacent topics in spoken content. The proposed model applies the proportions of verbs and nouns to analyze the similarity between utterances. An agglomerative clustering algorithm, based on an ontology defined in E-HowNet, clusters conversational utterances. Because the topic structure of conversational content is friable, E-HowNet uses hypernym relationships of speech acts to obtain robust solutions, even for sparse data. Compared with the traditional latent Dirichlet allocation (LDA) model, which detects topics only through a bag-of-words technique, the proposed model considers temporal features by introducing dynamic concepts. Experimental results revealed that the proposed approach outperformed the traditional DLDA and LDA and support vector machine models, in addition to achieving excellent performance for topic detection and tracking in conversations.

[1]  P ? ? ? ? ? ? ? % ? ? ? ? , 1991 .

[2]  Craig H. Martell,et al.  Topic Detection and Extraction in Chat , 2008, 2008 IEEE International Conference on Semantic Computing.

[3]  Larry Gillick,et al.  A hidden Markov model approach to text segmentation and event tracking , 1998, Proceedings of the 1998 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '98 (Cat. No.98CH36181).

[4]  Gary Geunbae Lee,et al.  CHAT AND GOAL-ORIENTED DIALOG TOGETHER: A UNIFIED EXAMPLE-BASED ARCHITECTURE FOR MULTI-DOMAIN DIALOG MANAGEMENT , 2006, 2006 IEEE Spoken Language Technology Workshop.

[5]  Yang Song,et al.  Topical Keyphrase Extraction from Twitter , 2011, ACL.

[6]  Guanghui Wang,et al.  Scene and place recognition using a hierarchical latent topic model , 2015, Neurocomputing.

[7]  Helena Moniz,et al.  Recognition of classroom lectures in european portuguese , 2006, INTERSPEECH.

[8]  Haizhou Li,et al.  IRIS: a Chat-oriented Dialogue System based on the Vector Space Model , 2012, ACL.

[9]  Xiao Liu,et al.  Learning to Track Multiple Targets , 2015, IEEE Transactions on Neural Networks and Learning Systems.

[10]  Kornel Laskowski,et al.  Advances in lecture recognition: the ISL RT-06s evaluation system , 2006, INTERSPEECH.

[11]  Ramón López-Cózar,et al.  Using knowledge on word-islands to improve the performance of spoken dialogue systems , 2015, Knowl. Based Syst..

[12]  Jun Yu,et al.  Human pose recovery by supervised spectral embedding , 2015, Neurocomputing.

[13]  Andrew Olney,et al.  An Orthonormal Basis for Topic Segmentation in Tutorial Dialogue , 2005, HLT.

[14]  James Allan,et al.  UMass at TDT 2000 , 2000 .

[15]  Matthew Purver,et al.  Meeting Structure Annotation , 2008 .

[16]  Andrzej Szalas,et al.  Paraconsistent semantics of speech acts , 2015, Neurocomputing.

[17]  Satoshi Nakamura,et al.  Out-of-Domain Utterance Detection Using Classification Confidences of Multiple Topics , 2007, IEEE Transactions on Audio, Speech, and Language Processing.

[18]  Junghoo Cho,et al.  Incorporating popularity in topic models for social network analysis , 2013, SIGIR.

[19]  Jordan L. Boyd-Graber,et al.  Efficient Tree-Based Topic Modeling , 2012, ACL.

[20]  Xujun Peng,et al.  Image color harmony modeling through neighbored co-occurrence colors , 2016, Neurocomputing.

[21]  Wenjie Li,et al.  Automatic Twitter Topic Summarization With Speech Acts , 2013, IEEE Transactions on Audio, Speech, and Language Processing.

[22]  Candace L. Sidner,et al.  Attention, Intentions, and the Structure of Discourse , 1986, CL.

[23]  Fang Wan,et al.  Collective motion pattern inference via Locally Consistent Latent Dirichlet Allocation , 2016, Neurocomputing.

[24]  M. Walker,et al.  How can you say such things?!?: Recognizing Disagreement in Informal Political Argument , 2011 .

[25]  John D. Lafferty,et al.  Dynamic topic models , 2006, ICML.

[26]  David Griol,et al.  A proposal for the development of adaptive spoken interfaces to access the Web , 2015, Neurocomputing.

[27]  Philip Resnik,et al.  SITS: A Hierarchical Nonparametric Model using Speaker Identity for Topic Segmentation in Multiparty Conversations , 2012, ACL.

[28]  Larry Gillick,et al.  Text segmentation and topic tracking on broadcast news via a hidden Markov model approach , 1998, ICSLP.

[29]  Qinghua Hu,et al.  Combining heterogeneous deep neural networks with conditional random fields for Chinese dialogue act recognition , 2015, Neurocomputing.

[30]  Xiaoming Zhang,et al.  Search engine reinforced semi-supervised classification and graph-based summarization of microblogs , 2015, Neurocomputing.

[31]  Beijun Shen,et al.  A Method of SNS Topic Models Extraction Based on Self-Adaptively LDA Modeling , 2013, 2013 Third International Conference on Intelligent System Design and Engineering Applications.

[32]  Alexander Clark,et al.  A Comparative Study of Mixture Models for Automatic Topic Segmentation of Multiparty Dialogues , 2008, IJCNLP.

[33]  Douglas W. Oard,et al.  Sentiment Polarity Automatic Detection of Human Values in Texts , 2014 .

[34]  Wen Gao,et al.  Fusing cross-media for topic detection by dense keyword groups , 2015, Neurocomputing.

[35]  Chao Li,et al.  Analysis of physiological for emotion recognition with the IRS model , 2016, Neurocomputing.

[36]  Hongfei Yan,et al.  Comparing Twitter and Traditional Media Using Topic Models , 2011, ECIR.

[37]  Sebastián A. Ríos,et al.  An empirical comparison of latent sematic models for applications in industry , 2016, Neurocomputing.

[38]  Jordan L. Boyd-Graber,et al.  Models for Dynamic Translation Model Adaptation , 2016 .

[39]  James R. Glass,et al.  Recent progress in the MIT spoken lecture processing project , 2007, INTERSPEECH.

[40]  David Bell,et al.  Microblogging as a mechanism for human-robot interaction , 2014, Knowl. Based Syst..

[41]  Haizhou Li,et al.  Towards Improving Dialogue Topic Tracking Performances with Wikification of Concept Mentions , 2015, SIGDIAL Conference.

[42]  Qi Zhao,et al.  Learning to predict eye fixations for semantic contents using multi-layer sparse network , 2014, Neurocomputing.

[43]  Peng Wang,et al.  Semantic expansion using word embedding clustering and convolutional neural network for improving short text classification , 2016, Neurocomputing.

[44]  Nayat Sanchez-Pi,et al.  A knowledge-based system approach for a context-aware system , 2012 .

[45]  Julia Hirschberg,et al.  Empirical Studies on the Disambiguation of Cue Phrases , 1993, Comput. Linguistics.

[46]  Lauren E. Scissors,et al.  Language Style Matching Predicts Relationship Initiation and Stability , 2011, Psychological science.

[47]  Lijuan Liu,et al.  Multi-level feature representations for video semantic concept detection , 2016, Neurocomputing.

[48]  Xiao Liu,et al.  Attribute-restricted latent topic model for person re-identification , 2012, Pattern Recognit..

[49]  M. Inés Torres,et al.  Extracting relevant knowledge for the detection of sarcasm and nastiness in the social web , 2014, Knowl. Based Syst..

[50]  Noémie Elhadad,et al.  An Unsupervised Aspect-Sentiment Model for Online Reviews , 2010, NAACL.

[51]  G. G. Stokes.  "J." , 1890, The New Yale Book of Quotations.

[52]  Marti A. Hearst.  Text Tiling: Segmenting Text into Multi-paragraph Subtopic Passages , 1997, CL.

[53]  Timothy J. Hazen.  MCE Training Techniques for Topic Identification of Spoken Audio Documents , 2011, IEEE Transactions on Audio, Speech, and Language Processing.

[54]  Julia Hirschberg,et al.  Acoustic indicators of topic segmentation , 1998, ICSLP.

[55]  Philip Resnik,et al.  Elements of a computational model for multi-party discourse: The turn-taking behavior of Supreme Court justices , 2009 .

[56]  Michael I. Jordan,et al.  Latent Dirichlet Allocation , 2001, J. Mach. Learn. Res..