Semi-automated dialogue act classification for situated social agents in games
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. A...
| Main Authors: | , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | en_US |
| Published: |
Springer Berlin / Heidelberg
2011
|
| Online Access: | http://hdl.handle.net/1721.1/66125 https://orcid.org/0000-0002-4333-7194 |
| _version_ | 1811085016969510912 |
|---|---|
| author | Orkin, Jeffrey David Roy, Deb K. |
| author2 | Massachusetts Institute of Technology. Media Laboratory |
| author_facet | Massachusetts Institute of Technology. Media Laboratory Orkin, Jeffrey David Roy, Deb K. |
| author_sort | Orkin, Jeffrey David |
| collection | MIT |
| description | 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. |
| first_indexed | 2024-09-23T13:01:39Z |
| format | Article |
| id | mit-1721.1/66125 |
| institution | Massachusetts Institute of Technology |
| language | en_US |
| last_indexed | 2024-09-23T13:01:39Z |
| publishDate | 2011 |
| publisher | Springer Berlin / Heidelberg |
| record_format | dspace |
| spelling | mit-1721.1/661252022-09-28T11:32:41Z Semi-automated dialogue act classification for situated social agents in games Orkin, Jeffrey David Roy, Deb K. Massachusetts Institute of Technology. Media Laboratory Roy, Deb K. Orkin, Jeffrey David Roy, Deb K. 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. 2011-09-30T12:33:29Z 2011-09-30T12:33:29Z 2011-01 Article http://purl.org/eprint/type/ConferencePaper 978-3-642-18180-1 http://hdl.handle.net/1721.1/66125 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. https://orcid.org/0000-0002-4333-7194 en_US http://dx.doi.org/10.1007/978-3-642-18181-8_11 Agents for Games and Simulations II: Trends in Techniques, Concepts and Design Creative Commons Attribution-Noncommercial-Share Alike 3.0 http://creativecommons.org/licenses/by-nc-sa/3.0/ application/pdf Springer Berlin / Heidelberg MIT web domain |
| spellingShingle | Orkin, Jeffrey David Roy, Deb K. Semi-automated dialogue act classification for situated social agents in games |
| title | Semi-automated dialogue act classification for situated social agents in games |
| title_full | Semi-automated dialogue act classification for situated social agents in games |
| title_fullStr | Semi-automated dialogue act classification for situated social agents in games |
| title_full_unstemmed | Semi-automated dialogue act classification for situated social agents in games |
| title_short | Semi-automated dialogue act classification for situated social agents in games |
| title_sort | semi automated dialogue act classification for situated social agents in games |
| url | http://hdl.handle.net/1721.1/66125 https://orcid.org/0000-0002-4333-7194 |
| work_keys_str_mv | AT orkinjeffreydavid semiautomateddialogueactclassificationforsituatedsocialagentsingames AT roydebk semiautomateddialogueactclassificationforsituatedsocialagentsingames |