Semi-automated dialogue act classification for situated social agents in games
Name
Roy_Semi-Automated.pdf
Size
241.34 KB
Format
Adobe PDF
Checksum (MD5)
09c37fd9c250a856b2c1b8f38f4c6f83
Author(s)
Orkin, Jeffrey David
Roy, Deb K.
Date Issued
January 2011
Journal
Agents for Games and Simulations II: Trends in Techniques, Concepts and Design
Publisher
Springer Berlin / Heidelberg
Citation
Orkin, Jeff, and Deb Roy. “Semi-Automated Dialogue Act Classification for Situated Social Agents in Games.” Agents for Games and Simulations II. Ed. Frank Dignum. Berlin, Heidelberg: Springer Berlin Heidelberg, 2011. 148-162.
Version
Author's final manuscript
Abstract
As a step toward simulating dynamic dialogue between agents and humans in virtual environments, we describe learning a model of social behavior composed of interleaved utterances and physical actions. In our model, utterances are abstracted as {speech act, propositional content, referent} triples. After training a classifier on 100 gameplay logs from The Restaurant Game annotated with dialogue act triples, we have automatically classified utterances in an additional 5,000 logs. A quantitative evaluation of statistical models learned from the gameplay logs demonstrates that semi-automatically classified dialogue acts yield significantly more predictive power than automatically clustered utterances, and serve as a better common currency for modeling interleaved actions and utterances.
MIT Department
Massachusetts Institute of Technology. Media Laboratory
Terms of Use
Creative Commons Attribution-Noncommercial-Share Alike 3.0
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1007/978-3-642-18181-8_11
