Open Peer Review. Open Publishing. Open Access. Open Discussion. Open Directory. Open Recommendations. Open API. Open Source.
Ask the Right Questions: Active Question Reformulation with Reinforcement Learning
Nov 03, 2017 (modified: Nov 03, 2017)ICLR 2018 Conference Blind Submissionreaders: everyoneShow Bibtex
Abstract:We frame Question Answering as a Reinforcement Learning task, an approach that
we call Active Question Answering. We propose an agent that sits between
the user and a black box question-answering system and which learns to
reformulate questions to elicit the best possible answers. The agent probes the
system with, potentially many, natural language reformulations of an initial
question and aggregates the returned evidence to yield the best answer.
The reformulation system is trained end-to-end to maximize answer quality using
We evaluate on SearchQA, a dataset of complex questions
extracted from Jeopardy!.
Our agent improves F1 by 11.4% over a state-of-the-art base model that
uses the original question/answer pairs. Based on a qualitative analysis of
the language that the agent has learned while interacting with the
question answering system, we propose that the agent has discovered basic
information retrieval techniques such as term re-weighting and stemming.
TL;DR:We propose an agent that sits between the user and a black box question-answering system and which learns to reformulate questions to elicit the best possible answers