Framing QA as Building and Ranking Intersentence Answer Justifications
We propose a question answering (QA) approach for standardized science exams that both identifies correct answers and produces compelling human-readable justifications for why those answers are correct. Our method first identifies the actual information needed in a question using psycholinguistic co...
Main Authors: | , , , |
---|---|
Other Authors: | |
Language: | en |
Published: |
MIT PRESS
2017
|
Online Access: | http://hdl.handle.net/10150/625062 http://arizona.openrepository.com/arizona/handle/10150/625062 |