Improving sentence compression by learning to predict gaze

Sigrid Klerke; Yoav Goldberg; Anders Søgaard

Improving sentence compression by learning to predict gaze

Sigrid Klerke, Yoav Goldberg, Anders Søgaard

Department of Nordic Studies and Linguistics

41 Citations (Scopus)

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 language	English
Title of host publication	Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics : Human Language Technologies
Number of pages	6
Publisher	Association for Computational Linguistics
Publication date	2016
Pages	1528-1533
ISBN (Electronic)	978-1-941643-91-4
Publication status	Published - 2016
Event	NAACL - San Diego, San Diego, United States Duration: 12 Jun 2016 → 17 Jun 2016

Conference

Conference	NAACL
Location	San Diego
Country/Territory	United States
City	San Diego
Period	12/06/2016 → 17/06/2016

Access to Document

http://aclweb.org/anthology/N/N16/N16-1179.pdf

Cite this

Improving sentence compression by learning to predict gaze. / Klerke, Sigrid; Goldberg, Yoav; Søgaard, Anders.

Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Association for Computational Linguistics, 2016. p. 1528-1533.

Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

Klerke, S, Goldberg, Y & Søgaard, A 2016, Improving sentence compression by learning to predict gaze. in Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Association for Computational Linguistics, pp. 1528-1533, NAACL, San Diego, United States, 12/06/2016. <http://aclweb.org/anthology/N/N16/N16-1179.pdf>

@inproceedings{e8cde86139524bcf8f0670395d739d52,

title = "Improving sentence compression by learning to predict gaze",

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.",

author = "Sigrid Klerke and Yoav Goldberg and Anders S{\o}gaard",

year = "2016",

language = "English",

pages = "1528--1533",

booktitle = "Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics",

publisher = "Association for Computational Linguistics",

note = "NAACL, NAACL ; Conference date: 12-06-2016 Through 17-06-2016",

}

TY - GEN

T1 - Improving sentence compression by learning to predict gaze

AU - Klerke, Sigrid

AU - Goldberg, Yoav

AU - Søgaard, Anders

PY - 2016

Y1 - 2016

N2 - 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.

AB - 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.

M3 - Article in proceedings

SP - 1528

EP - 1533

BT - Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics

PB - Association for Computational Linguistics

T2 - NAACL

Y2 - 12 June 2016 through 17 June 2016

ER -

Improving sentence compression by learning to predict gaze

Abstract

Conference

Access to Document

Fingerprint

Cite this