Scaling up Dialogue Systems
Throughout my research, I look for opportunities to design machine learning and annotation frameworks that make it easier to scale up a dialogue system’s linguistic competence to larger conversational domains.
Selected Publications
Dialogue Policy Learning
-
An Evaluation of Alternative Strategies for Implementing Dialogue Policies Using Statistical Classification and Hand-Authored Rules David DeVault, Anton Leuski, Kenji Sagae, in the 5th International Joint Conference on Natural Language Processing (IJCNLP 2011) .
-
Toward Learning and Evaluation of Dialogue Policies with Text Examples David DeVault, Anton Leuski, and Kenji Sagae, in the 12th annual SIGdial Meeting on Discourse and Dialogue (SigDial 2011).
Natural Language Generation
-
Practical Grammar-Based NLG from Examples David DeVault, David Traum, and Ron Artstein, The Fifth International Natural Language Generation Conference (INLG 2008), Ohio, June, 2008.
-
Making Grammar-Based Generation Easier to Deploy in Dialogue Systems David DeVault, David Traum, and Ron Artstein, The 9th SIGdial Workshop on Discourse and Dialogue (SIGdial 2008), Ohio, June, 2008.
Semantic Annotation
-
IORelator: A Graphical User Interface to Enable Rapid Semantic Annotation for Data-Driven Natural Language Understanding David DeVault, Susan Robinson, and David Traum, in Fifth Joint ISO-ACL/SIGSEM Workshop on Interoperable Semantic Annotation (ISA-5), Hong Kong, January 2010.
Acquiring Natural Language Understanding Models from Dialogue
-
Learning to Interpret Utterances Using Dialogue History David DeVault and Matthew Stone, The 12th Conference of the European Chapter of the Association for Computational Linguistics (EACL-09), Athens, Greece