ML p(r)ior | A Hybrid Reasoning Model for Indirect Answers

A Hybrid Reasoning Model for Indirect Answers

9406014 | cmp-lg
This paper presents our implemented computational model for interpreting and generating indirect answers to Yes-No questions. Its main features are 1) a discourse-plan-based approach to implicature, 2) a reversible architecture for generation and interpretation, 3) a hybrid reasoning model that employs both plan inference and logical inference, and 4) use of stimulus conditions to model a speaker's motivation for providing appropriate, unrequested information. The model handles a wider range of types of indirect answers than previous computational models and has several significant advantages.

Highlights - Most important sentences from the article

Login to like/save this paper, take notes and configure your recommendations