Elements of a computational model for multi-party discourse: The turn-taking behavior of Supreme Court justices

This paper explores computational models of multi-party discourse, using transcripts from U.S. Supreme Court oral arguments. The turn-taking behavior of participants is treated as a supervised sequence labeling problem and modeled using firstand secondorder Conditional Random Fields. We specifically explore the hypothesis that discourse markers and personal references provide important features in such models. Results from a sequence prediction experiment demonstrate that incorporating these two types of features yields significant improvements in performance. This work is couched in the broader context of developing tools to support legal scholarship, although we see other NLP applications as well. Publication Date: January 14, 2008

[1]  Steve J. Young,et al.  Partially observable Markov decision processes for spoken dialog systems , 2007, Comput. Speech Lang..

[2]  E. S. Pearson,et al.  THE USE OF CONFIDENCE OR FIDUCIAL LIMITS ILLUSTRATED IN THE CASE OF THE BINOMIAL , 1934 .

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

[4]  Philip Resnik,et al.  Spin: lexical semantics, transitivity, and the identification of implicit sentiment , 2007 .

[5]  Timothy R. Johnson,et al.  The Influence of Oral Arguments on the U.S. Supreme Court , 2006, American Political Science Review.

[6]  Christopher Cieri,et al.  Talkbank: Building an Open Unified Multimodal Database of Communicative Interaction , 2004, LREC.

[7]  Jeffrey A. Segal,et al.  Supreme Court Decision Making , 1975 .

[8]  Matt Thomas,et al.  Get out the vote: Determining support or opposition from Congressional floor-debate transcripts , 2006, EMNLP.

[9]  Cindy K. Chung,et al.  Winning words: Individual differences in linguistic style among U.S. presidential and vice presidential candidates , 2007 .

[10]  I. Lancashire.  Empirically Determining Shakespeare's Idolect , 1997 .

[11]  Rieks op den Akker,et al.  Towards Automatic Addressee Identification in Multi-party Dialogues , 2004, SIGDIAL Workshop.

[12]  Burr Settles,et al.  Biomedical Named Entity Recognition using Conditional Random Fields and Rich Feature Sets , 2004, NLPBA/BioNLP.

[13]  T. Johnson.  Information, Oral Arguments, and Supreme Court Decision Making , 2001 .

[14]  Jimmy J. Lin,et al.  Recounting the Courts? Applying Automated Content Analysis to Enhance Empirical Legal Research , 2006 .

[15]  M. Laver,et al.  Extracting Policy Positions from Political Texts Using Words as Data , 2003, American Political Science Review.

[16]  F. Mosteller,et al.  Inference and Disputed Authorship: The Federalist , 1966 .

[17]  Fernando Pereira,et al.  Shallow Parsing with Conditional Random Fields , 2003, NAACL.

[18]  Sarah Levien Shullman,et al.  The Illusion of Devil's Advocacy: How the Justices of the Supreme Court Foreshadow Their Decisions During Oral Argument , 2004 .

[19]  Michael H. Coen,et al.  Design Principles for Intelligent Environments , 1998, AAAI/IAAI.

[20]  Hugh Craig.  Stylistic Analysis and Authorship Studies , 2007 .

[21]  Andrei Popescu-Belis,et al.  What are discourse markers ? , 2003 .

[22]  Martial Michel,et al.  The NIST Smart Space and Meeting Room projects: signals, acquisition annotation, and metrics , 2003, 2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03)..

[23]  Simon H. Corston-Oliver.  Identifying the Linguistic Correlates of Rhetorical Relations , 1998 .