End-task oriented textual entailment via deep explorations of inter-sentence interactions

Wenpeng Yin, Hinrich Schütze, Dan Roth

Research output: Chapter in Book/Report/Conference proceedingConference contribution

10 Scopus citations

Abstract

This work deals with SCITAIL, a natural entailment challenge derived from a multi-choice question answering problem. The premises and hypotheses in SCITAIL were generated with no awareness of each other, and did not specifically aim at the entailment task. This makes it more challenging than other entailment data sets and more directly useful to the end-task – question answering. We propose DEISTE (deep explorations of inter-sentence interactions for textual entailment) for this entailment task. Given word-to-word interactions between the premise-hypothesis pair (P, H), DEISTE consists of: (i) a parameter-dynamic convolution to make important words in P and H play a dominant role in learnt representations; and (ii) a position-aware attentive convolution to encode the representation and position information of the aligned word pairs. Experiments show that DEISTE gets ≈5% improvement over prior state of the art and that the pretrained DEISTE on SCITAIL generalizes well on RTE-5.1

Original languageEnglish (US)
Title of host publicationACL 2018 - 56th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Short Papers)
PublisherAssociation for Computational Linguistics (ACL)
Pages540-545
Number of pages6
ISBN (Electronic)9781948087346
DOIs
StatePublished - 2018
Event56th Annual Meeting of the Association for Computational Linguistics, ACL 2018 - Melbourne, Australia
Duration: Jul 15 2018Jul 20 2018

Publication series

NameACL 2018 - 56th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers)
Volume2

Conference

Conference56th Annual Meeting of the Association for Computational Linguistics, ACL 2018
Country/TerritoryAustralia
CityMelbourne
Period7/15/187/20/18

All Science Journal Classification (ASJC) codes

  • Software
  • Computational Theory and Mathematics

Fingerprint

Dive into the research topics of 'End-task oriented textual entailment via deep explorations of inter-sentence interactions'. Together they form a unique fingerprint.

Cite this