Finding Generalizable Evidence by Learning to Convince Q&A Models
EMNLP/IJCNLP (1), pp. 2402-2411, 2019.
We propose a system that finds the strongest supporting evidence for a given answer to a question, using passage-based question-answering (QA) as a testbed. We train evidence agents to select the passage sentences that most convince a pretrained QA model of a given answer, if the QA model received those sentences instead of the full pas...More
PPT (Upload PPT)