Textual entailment has mainly focused on infer- ence from written text in monologue. Recent years also observed an increasing amount of conversa- tional data such as conversation scripts of meetings, call center records, court proceedings, as well as on- line chatting. Although conversation is a form of language, it is different from monologue text with several unique characteristics. The key distinctive features include turn-taking between participants, grounding between participants, different linguistic phenomena of utterances, and conversation impli- catures. Traditional approaches dealing with tex- tual entailment were not designed to handle these unique conversation behaviors and thus to support automated entailment from conversation scripts. This projects intends to address this limitation.
- Natural Language Inference: from Textual Entailment to Conversation Entailment . C. Zhang, Ph.D. Dissertation, 2010.
- An Investigation of Semantic Representation in Conversation Entailment. C. Zhang and J. Y. Chai. Conference on Empirical Methods in Natural Language Processing (EMNLP), MIT, MA, October, 2010.
- What do We Know about Conversation Participants: Experiments on Conversation Entailment. C. Zhang and J. Y. Chai. The 10th Annual SIGDIAL Meeting on Discourse and Dialogue, London, UK, September, 2009.
The data used in EMNLP 2010 paper can be downloaded here.