Learning translations via matrix completion

Derry Wijaya; Brendan Callahan; John Hewitt; Jie Gao; Xiao Ling; Marianna Apidianaki; Chris Callison-Burch

doi:10.18653/v1/d17-1152

Learning translations via matrix completion

Derry Wijaya, Brendan Callahan, John Hewitt, Jie Gao, Xiao Ling, Marianna Apidianaki, Chris Callison-Burch

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

15 Citations (Scopus)

Abstract

Bilingual Lexicon Induction is the task of learning word translations without bilingual parallel corpora. We model this task as a matrix completion problem, and present an effective and extendable framework for completing the matrix. This method harnesses diverse bilingual and monolingual signals, each of which may be incomplete or noisy. Our model achieves state-of-the-art performance for both high and low resource languages.

Original language	English
Title of host publication	EMNLP 2017 - The Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference
Editors	Rebecca Hwa, Sebastian Riedel
Place of Publication	Stroudsburg PA USA
Publisher	Association for Computational Linguistics (ACL)
Pages	1452-1463
Number of pages	12
ISBN (Electronic)	9781945626838
DOIs	https://doi.org/10.18653/v1/d17-1152
Publication status	Published - 2017
Externally published	Yes
Event	Empirical Methods in Natural Language Processing 2017 - Copenhagen, Denmark Duration: 9 Sept 2017 → 11 Sept 2017 http://www.aclweb.org/anthology/D/D17/

Conference

Conference	Empirical Methods in Natural Language Processing 2017
Abbreviated title	EMNLP 2017
Country/Territory	Denmark
City	Copenhagen
Period	9/09/17 → 11/09/17
Internet address	http://www.aclweb.org/anthology/D/D17/

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 9 Industry, Innovation, and Infrastructure
SDG 10 Reduced Inequalities

Access to Document

10.18653/v1/d17-1152

420088552-oaFinal published version, 963 KB

Cite this

Wijaya, D., Callahan, B., Hewitt, J., Gao, J., Ling, X., Apidianaki, M., & Callison-Burch, C. (2017). Learning translations via matrix completion. In R. Hwa, & S. Riedel (Eds.), EMNLP 2017 - The Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference (pp. 1452-1463). Association for Computational Linguistics (ACL). https://doi.org/10.18653/v1/d17-1152

@inproceedings{bd8a292652774e59a1d29dff52c9a21d,

title = "Learning translations via matrix completion",

abstract = "Bilingual Lexicon Induction is the task of learning word translations without bilingual parallel corpora. We model this task as a matrix completion problem, and present an effective and extendable framework for completing the matrix. This method harnesses diverse bilingual and monolingual signals, each of which may be incomplete or noisy. Our model achieves state-of-the-art performance for both high and low resource languages.",

author = "Derry Wijaya and Brendan Callahan and John Hewitt and Jie Gao and Xiao Ling and Marianna Apidianaki and Chris Callison-Burch",

note = "Funding Information: This material is based in part on research sponsored by DARPA under grant number HR0011-15-C-0115 (the LORELEI program). The U.S. Government is authorized to reproduce and distribute reprints for Governmental purposes. The views and conclusions contained in this publication are those of the authors and should not be interpreted as representing official policies or endorsements of DARPA and the U.S. Government. This work was also supported by the French National Research Agency under project ANR-16-CE33-0013, and by Amazon through the Amazon Academic Research Awards (AARA) program. Funding Information: This material is based in part on research sponsored by DARPA under grant number HR0011-15-C-0115 (the LORELEI program). The U.S. Government is authorized to reproduce and distribute reprints for Governmental purposes. The views and conclusions contained in this publication are those of the authors and should not be interpreted as representing official policies or endorsements of DARPA and the U.S. Government. Funding Information: This work was also supported by the French National Research Agency under project ANR-16-CE33-0013, and by Amazon through the Amazon Academic Research Awards (AARA) program. Publisher Copyright: {\textcopyright} 2017 Association for Computational Linguistics.; Empirical Methods in Natural Language Processing 2017, EMNLP 2017 ; Conference date: 09-09-2017 Through 11-09-2017",

year = "2017",

doi = "10.18653/v1/d17-1152",

language = "English",

pages = "1452--1463",

editor = "Rebecca Hwa and Sebastian Riedel",

booktitle = "EMNLP 2017 - The Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference",

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

url = "http://www.aclweb.org/anthology/D/D17/",

}

Wijaya, D, Callahan, B, Hewitt, J, Gao, J, Ling, X, Apidianaki, M & Callison-Burch, C 2017, Learning translations via matrix completion. in R Hwa & S Riedel (eds), EMNLP 2017 - The Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference. Association for Computational Linguistics (ACL), Stroudsburg PA USA, pp. 1452-1463, Empirical Methods in Natural Language Processing 2017, Copenhagen, Denmark, 9/09/17. https://doi.org/10.18653/v1/d17-1152

Learning translations via matrix completion. / Wijaya, Derry; Callahan, Brendan; Hewitt, John et al.
EMNLP 2017 - The Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference. ed. / Rebecca Hwa; Sebastian Riedel. Stroudsburg PA USA: Association for Computational Linguistics (ACL), 2017. p. 1452-1463.

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

TY - GEN

T1 - Learning translations via matrix completion

AU - Wijaya, Derry

AU - Callahan, Brendan

AU - Hewitt, John

AU - Gao, Jie

AU - Ling, Xiao

AU - Apidianaki, Marianna

AU - Callison-Burch, Chris

N1 - Funding Information: This material is based in part on research sponsored by DARPA under grant number HR0011-15-C-0115 (the LORELEI program). The U.S. Government is authorized to reproduce and distribute reprints for Governmental purposes. The views and conclusions contained in this publication are those of the authors and should not be interpreted as representing official policies or endorsements of DARPA and the U.S. Government. This work was also supported by the French National Research Agency under project ANR-16-CE33-0013, and by Amazon through the Amazon Academic Research Awards (AARA) program. Funding Information: This material is based in part on research sponsored by DARPA under grant number HR0011-15-C-0115 (the LORELEI program). The U.S. Government is authorized to reproduce and distribute reprints for Governmental purposes. The views and conclusions contained in this publication are those of the authors and should not be interpreted as representing official policies or endorsements of DARPA and the U.S. Government. Funding Information: This work was also supported by the French National Research Agency under project ANR-16-CE33-0013, and by Amazon through the Amazon Academic Research Awards (AARA) program. Publisher Copyright: © 2017 Association for Computational Linguistics.

PY - 2017

Y1 - 2017

N2 - Bilingual Lexicon Induction is the task of learning word translations without bilingual parallel corpora. We model this task as a matrix completion problem, and present an effective and extendable framework for completing the matrix. This method harnesses diverse bilingual and monolingual signals, each of which may be incomplete or noisy. Our model achieves state-of-the-art performance for both high and low resource languages.

AB - Bilingual Lexicon Induction is the task of learning word translations without bilingual parallel corpora. We model this task as a matrix completion problem, and present an effective and extendable framework for completing the matrix. This method harnesses diverse bilingual and monolingual signals, each of which may be incomplete or noisy. Our model achieves state-of-the-art performance for both high and low resource languages.

UR - https://www.scopus.com/pages/publications/85063085507

U2 - 10.18653/v1/d17-1152

DO - 10.18653/v1/d17-1152

M3 - Conference Paper

AN - SCOPUS:85063085507

SP - 1452

EP - 1463

BT - EMNLP 2017 - The Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference

A2 - Hwa, Rebecca

A2 - Riedel, Sebastian

PB - Association for Computational Linguistics (ACL)

CY - Stroudsburg PA USA

T2 - Empirical Methods in Natural Language Processing 2017

Y2 - 9 September 2017 through 11 September 2017

ER -

Learning translations via matrix completion

Abstract

Conference

UN SDGs

Access to Document

Other files and links

Cite this