Hierarchical Conversation Structure Prediction in Multi-Party Chat

Conversational practices do not occur at a single unit of analysis. To understand the interplay between social positioning, information sharing, and rhetorical strategy in language, various granularities are necessary. In this work we present a machine learning model for multi-party chat which predicts conversation structure across differing units of analysis. First, we mark sentence-level behavior using an information sharing annotation scheme. By taking advantage of Integer Linear Programming and a sociolinguistic framework, we enforce structural relationships between sentence-level annotations and sequences of interaction. Then, we show that clustering these sequences can effectively disentangle the threads of conversation. This model is highly accurate, performing near human accuracy, and performs analysis on-line, opening the door to real-time analysis of the discourse of conversation.

[1]  Mark G. Core,et al.  Coding Dialogs with the DAMSL Annotation Scheme , 1997 .

[2]  Takashi Kusumi,et al.  Analysis of Community Development using Chat Logs: A Virtual Support Group of Cancer Patients , 2008, 2008 Second International Symposium on Universal Communication.

[3]  Timothy Baldwin,et al.  Classifying Dialogue Acts in One-on-One Live Chats , 2010, EMNLP.

[4]  Ming-Wei Chang,et al.  Learning and Inference with Constraints , 2008, AAAI.

[5]  Tomek Strzalkowski,et al.  Modeling Socio-Cultural Phenomena in Online Multi-Party Discourse , 2011, Analyzing Microtext.

[6]  Jacki O'Neill,et al.  Text chat in action , 2003, GROUP.

[7]  Dan Roth,et al.  Learning Based Java for Rapid Development of NLP Systems , 2010, LREC.

[8]  Paige Adams,et al.  Conversation Thread Extraction and Topic Detection in Text-Based Chat , 2010 .

[9]  Carolyn Penstein Rosé,et al.  An Interactive Tool for Supporting Error Analysis for Text Mining , 2010, NAACL.

[10]  Andrei Popescu-Belis.  An empirical analysis of large corpora , 2008 .

[11]  James F. Allen,et al.  TRIPS: An Integrated Intelligent Problem-Solving Assistant , 1998, AAAI/IAAI.

[12]  Chih-Jen Lin,et al.  LIBLINEAR: A Library for Large Linear Classification , 2008, J. Mach. Learn. Res..

[13]  Carolyn Penstein Rosé,et al.  Data-Driven Interaction Patterns: Authority and Information Sharing in Dialogue , 2011, AAAI Fall Symposium: Building Representations of Common Ground with Intelligent Agents.

[14]  Dan Klein,et al.  Feature-Rich Part-of-Speech Tagging with a Cyclic Dependency Network , 2003, NAACL.

[15]  C. Rosé,et al.  Missing Something? Authority in Collaborative Learning , 2011, CSCL.

[16]  Qiang Yang,et al.  Thread detection in dynamic text message streams , 2006, SIGIR.

[17]  David R Traum,et al.  Towards a Computational Theory of Grounding in Natural Language Conversation , 1991 .

[18]  Alan Ritter,et al.  Unsupervised Modeling of Twitter Conversations , 2010, NAACL.

[19]  Elizabeth Shriberg,et al.  The ICSI Meeting Recorder Dialog Act (MRDA) Corpus , 2004, SIGDIAL Workshop.

[20]  Victoria Sharp,et al.  Provider-patient Adherence Dialogue in HIV Care: Results of a Multisite Study , 2012, AIDS and Behavior.

[21]  Massimo Poesio,et al.  The predictive power of game structure in dialogue act recognition: experimental results using maximum entropy estimation , 1998, ICSLP.

[22]  Alexander I. Rudnicky,et al.  Computational representation of discourse practices across populations in task-based dialogue , 2012, ICIC.

[23]  Jean Carletta,et al.  Multimodal Signal Processing , 2012 .

[24]  Andrei Popescu-Belis.  Dimensionality of dialogue act tagsets , 2008, Lang. Resour. Evaluation.

[25]  Julia Hirschberg,et al.  Identifying Agreement and Disagreement in Conversational Speech: Use of Bayesian Networks to Model Pragmatic Dependencies , 2004, ACL.

[26]  Igor Malioutov,et al.  Minimum Cut Model for Spoken Lecture Segmentation , 2006, ACL.

[27]  Edward Gibson,et al.  Representing Discourse Coherence: A Corpus-Based Study , 2005, CL.

[28]  Eric Horvitz,et al.  Multiparty Turn Taking in Situated Dialog: Study, Lessons, and Directions , 2011, SIGDIAL Conference.

[29]  Carolyn Penstein Rosé,et al.  Discovering habits of effective online support group chatrooms , 2012, GROUP.

[30]  David Rose,et al.  Working with Discourse: Meaning Beyond the Clause , 2003 .

[31]  Anton Leuski,et al.  Using information state to improve dialogue move identification in a spoken dialogue system , 2007, INTERSPEECH.

[32]  WolfFlorian,et al.  Representing Discourse Coherence: A Corpus-Based Study , 2005 .

[33]  Ata Kabán,et al.  Topic Identification in Dynamical Text by Complexity Pursuit , 2003, Neural Processing Letters.

[34]  Micha Elsner,et al.  Disentangling Chat , 2010, CL.

[35]  Rieks op den Akker,et al.  A comparison of addressee detection methods for multiparty conversations , 2009 .

[36]  Micha Elsner,et al.  Disentangling Chat with Local Coherence Models , 2011, ACL.

[37]  Claire Cardie,et al.  Annotating Expressions of Opinions and Emotions in Language , 2005, Lang. Resour. Evaluation.

[38]  Carolyn Penstein Rosé,et al.  Recognizing Authority in Dialogue with an Integer Linear Programming Constrained Model , 2011, ACL.

[39]  Harry Bunt,et al.  Multifunctionality in dialogue , 2011, Comput. Speech Lang..

[40]  Lauri Carlson.  Dialogue Games: An Approach to Discourse Analysis , 1982 .