Towards string-to-Tree neural machine translation

Roee Aharoni; Yoav Goldberg

doi:10.18653/v1/P17-2021

Towards string-to-Tree neural machine translation

Roee Aharoni
, Yoav Goldberg

Department of Computer Science

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

103 Scopus citations

Abstract

We present a simple method to incorporate syntactic information about the target language in a neural machine translation system by translating into linearized, lexicalized constituency trees. Experiments on the WMT16 German-English news translation task shown improved BLEU scores when compared to a syntax-agnostic NMT baseline trained on the same dataset. An analysis of the translations from the syntax-aware system shows that it performs more reordering during translation in comparison to the baseline. A small-scale human evaluation also showed an advantage to the syntax-aware system.

Original language	English
Title of host publication	ACL 2017 - 55th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Short Papers)
Publisher	Association for Computational Linguistics (ACL)
Pages	132-140
Number of pages	9
ISBN (Electronic)	9781945626760
DOIs	https://doi.org/10.18653/v1/P17-2021
State	Published - 2017
Event	55th Annual Meeting of the Association for Computational Linguistics, ACL 2017 - Vancouver, Canada Duration: 30 Jul 2017 → 4 Aug 2017

Publication series

Name	ACL 2017 - 55th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers)
Volume	2

Conference

Conference	55th Annual Meeting of the Association for Computational Linguistics, ACL 2017
Country/Territory	Canada
City	Vancouver
Period	30/07/17 → 4/08/17

Bibliographical note

Publisher Copyright:
© 2017 Association for Computational Linguistics.

Funding

This work was supported by the Intel Collaborative Research Institute for Computational Intelligence (ICRI-CI), and The Israeli Science Foundation (grant number 1555/15).

Funders	Funder number
Intel Collaborative Research Institute for Computational Intelligence
Israeli Science Foundation	1555/15
Institut Claudius Regaud

Access to Document

10.18653/v1/P17-2021

Cite this

Aharoni, R., & Goldberg, Y. (2017). Towards string-to-Tree neural machine translation. In ACL 2017 - 55th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Short Papers) (pp. 132-140). (ACL 2017 - 55th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers); Vol. 2). Association for Computational Linguistics (ACL). https://doi.org/10.18653/v1/P17-2021

Aharoni, Roee ; Goldberg, Yoav. / Towards string-to-Tree neural machine translation. ACL 2017 - 55th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Short Papers). Association for Computational Linguistics (ACL), 2017. pp. 132-140 (ACL 2017 - 55th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers)).

@inproceedings{6db37e217ddf440f85a3a6d34904f8d3,

title = "Towards string-to-Tree neural machine translation",

abstract = "We present a simple method to incorporate syntactic information about the target language in a neural machine translation system by translating into linearized, lexicalized constituency trees. Experiments on the WMT16 German-English news translation task shown improved BLEU scores when compared to a syntax-agnostic NMT baseline trained on the same dataset. An analysis of the translations from the syntax-aware system shows that it performs more reordering during translation in comparison to the baseline. A small-scale human evaluation also showed an advantage to the syntax-aware system.",

author = "Roee Aharoni and Yoav Goldberg",

note = "Publisher Copyright: {\textcopyright} 2017 Association for Computational Linguistics.; 55th Annual Meeting of the Association for Computational Linguistics, ACL 2017 ; Conference date: 30-07-2017 Through 04-08-2017",

year = "2017",

doi = "10.18653/v1/P17-2021",

language = "אנגלית",

series = "ACL 2017 - 55th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers)",

publisher = "Association for Computational Linguistics (ACL)",

pages = "132--140",

booktitle = "ACL 2017 - 55th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Short Papers)",

address = "ארצות הברית",

}

Aharoni, R & Goldberg, Y 2017, Towards string-to-Tree neural machine translation. in ACL 2017 - 55th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Short Papers). ACL 2017 - 55th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers), vol. 2, Association for Computational Linguistics (ACL), pp. 132-140, 55th Annual Meeting of the Association for Computational Linguistics, ACL 2017, Vancouver, Canada, 30/07/17. https://doi.org/10.18653/v1/P17-2021

Towards string-to-Tree neural machine translation. / Aharoni, Roee; Goldberg, Yoav.
ACL 2017 - 55th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Short Papers). Association for Computational Linguistics (ACL), 2017. p. 132-140 (ACL 2017 - 55th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers); Vol. 2).

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

TY - GEN

T1 - Towards string-to-Tree neural machine translation

AU - Aharoni, Roee

AU - Goldberg, Yoav

PY - 2017

Y1 - 2017

N2 - We present a simple method to incorporate syntactic information about the target language in a neural machine translation system by translating into linearized, lexicalized constituency trees. Experiments on the WMT16 German-English news translation task shown improved BLEU scores when compared to a syntax-agnostic NMT baseline trained on the same dataset. An analysis of the translations from the syntax-aware system shows that it performs more reordering during translation in comparison to the baseline. A small-scale human evaluation also showed an advantage to the syntax-aware system.

AB - We present a simple method to incorporate syntactic information about the target language in a neural machine translation system by translating into linearized, lexicalized constituency trees. Experiments on the WMT16 German-English news translation task shown improved BLEU scores when compared to a syntax-agnostic NMT baseline trained on the same dataset. An analysis of the translations from the syntax-aware system shows that it performs more reordering during translation in comparison to the baseline. A small-scale human evaluation also showed an advantage to the syntax-aware system.

UR - https://www.scopus.com/pages/publications/85040567328

U2 - 10.18653/v1/P17-2021

DO - 10.18653/v1/P17-2021

M3 - ???researchoutput.researchoutputtypes.contributiontobookanthology.conference???

AN - SCOPUS:85040567328

T3 - ACL 2017 - 55th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers)

SP - 132

EP - 140

BT - ACL 2017 - 55th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Short Papers)

PB - Association for Computational Linguistics (ACL)

T2 - 55th Annual Meeting of the Association for Computational Linguistics, ACL 2017

Y2 - 30 July 2017 through 4 August 2017

ER -

Aharoni R, Goldberg Y. Towards string-to-Tree neural machine translation. In ACL 2017 - 55th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Short Papers). Association for Computational Linguistics (ACL). 2017. p. 132-140. (ACL 2017 - 55th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers)). doi: 10.18653/v1/P17-2021

Towards string-to-Tree neural machine translation

Abstract

Publication series

Conference

Bibliographical note

Funding

Access to Document

Other files and links

Fingerprint

Cite this