A Generative Joint, Additive, Sequential Model of Topics and Speech Acts in Patient-Doctor Communication

We develop a novel generative model of conversation that jointly captures both the topical content and the speech act type associated with each utterance. Our model expresses both token emission and state transition probabilities as log-linear functions of separate components corresponding to topics and speech acts (and their interactions). We apply this model to a dataset comprising annotated patient-physician visits and show that the proposed joint approach outperforms a baseline univariate model.

[1]  Michael J. Paul.  Mixed Membership Markov Models for Unsupervised Conversation Modeling , 2012, EMNLP.

[2]  G. Makoul,et al.  Essential Elements of Communication in Medical Encounters: The Kalamazoo Consensus Statement , 2001, Academic medicine : journal of the Association of American Medical Colleges.

[3]  J. Morley.  The Medical clinics of North America , 2012 .

[4]  Alex Pentland,et al.  Coupled hidden Markov models for complex action recognition , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[5]  Timothy Baldwin,et al.  Classifying Dialogue Acts in Multi-party Live Chats , 2012, PACLIC.

[6]  Andrew E. Smith,et al.  Visualising Conversation Structure across Time: Insights into Effective Doctor-Patient Consultations , 2012, PloS one.

[7]  George Forman,et al.  Apples-to-apples in cross-validation studies: pitfalls in classifier performance measurement , 2010, SKDD.

[8]  Oliver Ferschke,et al.  Behind the Article: Recognizing Dialog Acts in Wikipedia Talk Pages , 2012, EACL.

[9]  Wenjie Li,et al.  Towards Scalable Speech Act Recognition in Twitter: Tackling Insufficient Training Data , 2012 .

[10]  Michael I. Jordan,et al.  Factorial Hidden Markov Models , 1995, Machine Learning.

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

[12]  Ellen Riloff,et al.  Classifying Sentences as Speech Acts in Message Board Posts , 2011, EMNLP.

[13]  Johanna D. Moore,et al.  AUTOMATIC TOPIC SEGMENTATION AND LABELING IN MULTIPARTY DIALOGUE , 2006, 2006 IEEE Spoken Language Technology Workshop.

[14]  Mark Dredze,et al.  What Affects Patient (Dis)satisfaction? Analyzing Online Doctor Ratings with a Joint Topic-Sentiment Model , 2013, AAAI 2013.

[15]  J. de Haes,et al.  Doctor-patient communication: a review of the literature. , 1995, Social science & medicine.

[16]  C. Teutsch.  Patient-doctor communication. , 2003, The Medical clinics of North America.

[17]  JurafskyDaniel,et al.  Dialogue act modeling for automatic tagging and recognition of conversational speech , 2000 .

[18]  Regina Barzilay,et al.  Bayesian Unsupervised Topic Segmentation , 2008, EMNLP.

[19]  Elizabeth Shriberg,et al.  Automatic dialog act segmentation and classification in multiparty meetings , 2005, Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005..

[20]  Tom M. Mitchell,et al.  Learning to Classify Email into “Speech Acts” , 2004, EMNLP.

[21]  Yee Whye Teh,et al.  The Infinite Factorial Hidden Markov Model , 2008, NIPS.

[22]  Andreas Stolcke,et al.  Dialogue act modeling for automatic tagging and recognition of conversational speech , 2000, CL.

[23]  J. Searle.  Expression and Meaning: Studies in the Theory of Speech Acts , 1979 .

[24]  William Coady,et al.  Provider-Focused Intervention Increases Adherence-Related Dialogue but Does Not Improve Antiretroviral Therapy Adherence in Persons With HIV , 2010, Journal of acquired immune deficiency syndromes.

[25]  M. Leezenberg.  John R. Searle , 2000 .

[26]  A. Koller,et al.  Speech Acts: An Essay in the Philosophy of Language , 1969 .

[27]  Andrew McCallum,et al.  Dynamic conditional random fields: factorized probabilistic models for labeling and segmenting sequence data , 2004, J. Mach. Learn. Res..

[28]  David Traum,et al.  The Information State Approach to Dialogue Management , 2003 .

[29]  C. Raymond Perrault,et al.  A Plan-Based Analysis of Indirect Speech Act , 1980, CL.

[30]  Dan Jurafsky,et al.  Dialog Act Modeling for Conversational Speech , 1998 .

[31]  J. Austin.  How to do things with words , 1962 .

[32]  Csr Young,et al.  How to Do Things With Words , 2009 .

[33]  A. Stolcke,et al.  Dialog act modelling for conversational speech , 1998 .

[34]  Eric Fosler-Lussier,et al.  Discourse Segmentation of Multi-Party Conversation , 2003, ACL.

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

[36]  D. Roter,et al.  The Roter interaction analysis system (RIAS): utility and flexibility for analysis of medical interactions. , 2002, Patient education and counseling.

[37]  J. O. Urmson,et al.  How to Do Things with Words@@@The William James Lectures , 1963 .

[38]  Jade Goldstein-Stewart,et al.  Annotating Subsets of the Enron Email Corpus , 2006, CEAS.

[39]  Michael Barton Laws,et al.  The association of visit length and measures of patient-centered communication in HIV care: a mixed methods study. , 2011, Patient education and counseling.

[40]  Andrei Popescu-Belis,et al.  Multi-level Dialogue Act Tags , 2004, SIGDIAL Workshop.

[41]  J. Ford,et al.  The Role Of Conversations in Producing Intentional Change in Organizations , 1995 .

[42]  Alex Bateman,et al.  An introduction to hidden Markov models. , 2007, Current protocols in bioinformatics.

[43]  Eric P. Xing,et al.  Sparse Additive Generative Models of Text , 2011, ICML.

[44]  Steven A. Safren,et al.  Discussion of Sexual Risk Behavior in HIV Care is Infrequent and Appears Ineffectual: A Mixed Methods Study , 2011, AIDS and Behavior.

[45]  Andrew E. Smith,et al.  Conversations Between Carers and People With Schizophrenia: A Qualitative Analysis Using Leximancer , 2010, Qualitative health research.

[46]  Mark Kaplan.  John Langshaw Austin , 2010 .

[47]  Mark Dredze,et al.  Factorial LDA: Sparse Multi-Dimensional Text Models , 2012, NIPS.