Improving sentence compression by learning to predict gaze

Sigrid Klerke, Yoav Goldberg, Anders Søgaard

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

74 Scopus citations

Abstract

We show how eye-tracking corpora can be used to improve sentence compression models, presenting a novel multi-task learning algorithm based on multi-layer LSTMs. We obtain performance competitive with or better than state-of-the-art approaches.

Original languageEnglish
Title of host publication2016 Conference of the North American Chapter of the Association for Computational Linguistics
Subtitle of host publicationHuman Language Technologies, NAACL HLT 2016 - Proceedings of the Conference
PublisherAssociation for Computational Linguistics (ACL)
Pages1528-1533
Number of pages6
ISBN (Electronic)9781941643914
DOIs
StatePublished - 2016
Event15th Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2016 - San Diego, United States
Duration: 12 Jun 201617 Jun 2016

Publication series

Name2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2016 - Proceedings of the Conference

Conference

Conference15th Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2016
Country/TerritoryUnited States
CitySan Diego
Period12/06/1617/06/16

Bibliographical note

Publisher Copyright:
©2016 Association for Computational Linguistics.

Funding

Yoav Goldberg was supported by the Israeli Science Foundation Grant No. 1555/15. Anders Søgaard was supported by ERC Starting Grant No. 313695. Thanks to Joachim Bingel and Maria Barrett for preparing data and for helpful discussions, and to the anonymous reviewers for their suggestions for improving the paper.

FundersFunder number
European Commission313695
Israel Science Foundation1555/15

    Fingerprint

    Dive into the research topics of 'Improving sentence compression by learning to predict gaze'. Together they form a unique fingerprint.

    Cite this