Classifying Sentences as Speech Acts in Message Board Posts

This research studies the text genre of message board forums, which contain a mixture of expository sentences that present factual information and conversational sentences that include communicative acts between the writer and readers. Our goal is to create sentence classifiers that can identify whether a sentence contains a speech act, and can recognize sentences containing four different speech act classes: Commissives, Directives, Expressives, and Representatives. We conduct experiments using a wide variety of features, including lexical and syntactic features, speech act word lists from external resources, and domain-specific semantic class features. We evaluate our results on a collection of message board posts in the domain of veterinary medicine.

[1]  Ellen Riloff,et al.  Learning subjective nouns using extraction pattern bootstrapping , 2003, CoNLL.

[2]  William W. Cohen,et al.  Improving “Email Speech Acts” Analysis via N-gram Selection , 2006, HLT-NAACL 2006.

[3]  Jean Carletta,et al.  Assessing Agreement on Classification Tasks: The Kappa Statistic , 1996, CL.

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

[5]  Anna Maria Di Sciullo,et al.  Natural Language Understanding , 2009, SoMeT.

[6]  Jade Goldstein-Stewart,et al.  Using Speech Acts to Categorize Email and Identify Email Genres , 2006, Proceedings of the 39th Annual Hawaii International Conference on System Sciences (HICSS'06).

[7]  Vitor R. Carvalho.  Email “Speech Acts” , 2011 .

[8]  Jorge Peña,et al.  The Construction of Away Messages: A Speech Act Analysis , 2006, J. Comput. Mediat. Commun..

[9]  Jan Noyes,et al.  Toward a stochastic speech act model of email behavior , 2008, CEAS.

[10]  Ellen Riloff,et al.  Inducing Domain-Specific Semantic Class Taggers from (Almost) Nothing , 2010, ACL.

[11]  J. Searle.  A classification of illocutionary acts , 1976, Language in Society.

[12]  Jay F. Nunamaker,et al.  Using Speech Act Theory to Model Conversations for Automated Classification and Retrieval , 2004 .

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

[14]  Jihie Kim,et al.  Profiling Student Interactions in Threaded Discussions with Speech Act Classifiers , 2007, AIED.

[15]  Ellen Riloff,et al.  A Bootstrapping Method for Learning Semantic Lexicons using Extraction Pattern Contexts , 2002, EMNLP.

[16]  Cécile Paris,et al.  Classifying Speech Acts using Verbal Response Modes , 2006, ALTA.

[17]  Jay F. Nunamaker,et al.  Speech act profiling: a probabilistic method for analyzing persistent conversations and their participants , 2004, 37th Annual Hawaii International Conference on System Sciences, 2004. Proceedings of the.

[18]  A. Wierzbicka.  English Speech Act Verbs: A Semantic Dictionary , 1987 .

[19]  Gary Geunbae Lee,et al.  Semi-supervised Speech Act Recognition in Emails and Forums , 2009, EMNLP.

[20]  James F. Allen.  Natural language understanding (2nd ed.) , 1995 .

[21]  Tara McIntosh,et al.  Unsupervised Discovery of Negative Categories in Lexicon Bootstrapping , 2010, EMNLP.

[22]  Ian H. Witten,et al.  The WEKA data mining software: an update , 2009, SKDD.

[23]  William W. Cohen,et al.  On the collective classification of email "speech acts" , 2005, SIGIR '05.