Coarse-to-fine question answering for long documents

Eunsol Choi, Daniel Hewlett, Jakob Uszkoreit, Illia Polosukhin, Alexandre Lacoste, Jonathan Berant

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

We present a framework for question answering that can efficiently scale to longer documents while maintaining or even improving performance of state-of-the-art models. While most successful approaches for reading comprehension rely on recurrent neural networks (RNNs), running them over long documents is prohibitively slow because it is difficult to parallelize over sequences. Inspired by how people first skim the document, identify relevant parts, and carefully read these parts to produce an answer, we combine a coarse, fast model for selecting relevant sentences and a more expensive RNN for producing the answer from those sentences. We treat sentence selection as a latent variable trained jointly from the answer only using reinforcement learning. Experiments demonstrate the state of the art performance on a challenging subset of the WIKIREADING dataset (Hewlett et al., 2016) and on a new dataset, while speeding up the model by 3.5x-6.7x.

Original languageEnglish
Title of host publicationACL 2017 - 55th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers)
PublisherAssociation for Computational Linguistics (ACL)
Pages209-220
Number of pages12
ISBN (Electronic)9781945626753
DOIs
StatePublished - 2017
Event55th Annual Meeting of the Association for Computational Linguistics, ACL 2017 - Vancouver, Canada
Duration: 30 Jul 20174 Aug 2017

Publication series

NameACL 2017 - 55th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers)
Volume1

Conference

Conference55th Annual Meeting of the Association for Computational Linguistics, ACL 2017
Country/TerritoryCanada
CityVancouver
Period30/07/174/08/17

Fingerprint

Dive into the research topics of 'Coarse-to-fine question answering for long documents'. Together they form a unique fingerprint.

Cite this