Abstract
In this paper we describe Answery, a rule-based system that
allows authors to specify game characters' background stories in natural
language. The system parses these background stories, applies transfor-
mation rules to turn them into semantic content, and generates dialogue
during gameplay by posing it as a question-answering problem. By the
means of simple categorization combined with rule inference engine, our
system can generate answers eciently. Our initial pilot study shows that
this approach is promising.
allows authors to specify game characters' background stories in natural
language. The system parses these background stories, applies transfor-
mation rules to turn them into semantic content, and generates dialogue
during gameplay by posing it as a question-answering problem. By the
means of simple categorization combined with rule inference engine, our
system can generate answers eciently. Our initial pilot study shows that
this approach is promising.
| Originalsprog | Engelsk |
|---|---|
| Titel | GAMNLP 12. Proceedings of the first Workshop on Games and NLP, JapTAL 2012. : In connection with the 8th International Conference on Natural Language Processing |
| Antal sider | 7 |
| Publikationsdato | 2013 |
| Status | Udgivet - 2013 |
| Begivenhed | CfP: 1st Workshop on Games and Natural Language Processing: http://www.digra.org/cfp-1st-workshop-on-games-and-natural-language-processing-gamnlp-12/ - Kanazawa, Japan Varighed: 23 okt. 2012 → 23 okt. 2012 http://www.digra.org/cfp-1st-workshop-on-games-and-natural-language-processing-gamnlp-12/ |
Workshop
| Workshop | CfP: 1st Workshop on Games and Natural Language Processing |
|---|---|
| Land/Område | Japan |
| By | Kanazawa |
| Periode | 23/10/2012 → 23/10/2012 |
| Internetadresse |