Cross-lingual Pronoun Prediction for English, French and German with Maximum Entropy Classification

Dominikus Wetzel

Cross-lingual Pronoun Prediction for English, French and German with Maximum Entropy Classification

Dominikus Wetzel

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

Abstract

We present our submission to the crosslingual pronoun prediction (CLPP) shared task for English-German and EnglishFrench at the First Conference on Machine Translation (WMT16). We trained a Maximum Entropy (MaxEnt) classifier based on features from Wetzel et al. (2015),that we ada pted to the new task and applied to a new language pair. Additional features such as n-grams of the pronoun context and prediction of NULLtranslations proved helpful to a varying degree. Experiments with a sequence classifier over pronoun sequences did not show any improvements. Our submission is among the top three systems for English-French (61.62% macro-averaged recall) and in the middle range for EnglishGerman (48.72%) out of nine submissions.

Original language	English
Title of host publication	Proceedings of the First Conference on Machine Translation, Volume 2: Shared Task Papers
Place of Publication	Berlin, Germany
Publisher	Association for Computational Linguistics
Pages	620–626
Number of pages	7
ISBN (Print)	978-1-945626-10-4
Publication status	Published - 12 Aug 2016
Externally published	Yes
Event	First Conference on Machine Translation - Berlin, Germany Duration: 11 Aug 2016 → 12 Aug 2016 http://www.statmt.org/wmt16/

Conference

Conference	First Conference on Machine Translation
Abbreviated title	WMT16
Country/Territory	Germany
City	Berlin
Period	11/08/16 → 12/08/16
Internet address	http://www.statmt.org/wmt16/

Access to Document

W16-2357Accepted author manuscript, 160 KB

http://www.aclweb.org/anthology/W/W16/W16-2357.pdfLicence: Creative Commons: Attribution (CC-BY)

Cite this

@inproceedings{738ad23fe76e4fc9a2dfd6f34e4623ee,

title = "Cross-lingual Pronoun Prediction for English, French and German with Maximum Entropy Classification",

abstract = "We present our submission to the crosslingual pronoun prediction (CLPP) shared task for English-German and EnglishFrench at the First Conference on Machine Translation (WMT16). We trained a Maximum Entropy (MaxEnt) classifier based on features from Wetzel et al. (2015),that we ada pted to the new task and applied to a new language pair. Additional features such as n-grams of the pronoun context and prediction of NULLtranslations proved helpful to a varying degree. Experiments with a sequence classifier over pronoun sequences did not show any improvements. Our submission is among the top three systems for English-French (61.62\% macro-averaged recall) and in the middle range for EnglishGerman (48.72\%) out of nine submissions.",

author = "Dominikus Wetzel",

year = "2016",

month = aug,

day = "12",

language = "English",

isbn = "978-1-945626-10-4",

pages = "620–626",

booktitle = "Proceedings of the First Conference on Machine Translation, Volume 2: Shared Task Papers",

publisher = "Association for Computational Linguistics",

note = "First Conference on Machine Translation, WMT16 ; Conference date: 11-08-2016 Through 12-08-2016",

url = "http://www.statmt.org/wmt16/",

}

Wetzel, D 2016, Cross-lingual Pronoun Prediction for English, French and German with Maximum Entropy Classification. in Proceedings of the First Conference on Machine Translation, Volume 2: Shared Task Papers. Association for Computational Linguistics, Berlin, Germany, pp. 620–626, First Conference on Machine Translation, Berlin, Germany, 11/08/16. <http://www.aclweb.org/anthology/W/W16/W16-2357.pdf>

Cross-lingual Pronoun Prediction for English, French and German with Maximum Entropy Classification. / Wetzel, Dominikus.
Proceedings of the First Conference on Machine Translation, Volume 2: Shared Task Papers. Berlin, Germany: Association for Computational Linguistics, 2016. p. 620–626.

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

TY - GEN

T1 - Cross-lingual Pronoun Prediction for English, French and German with Maximum Entropy Classification

AU - Wetzel, Dominikus

PY - 2016/8/12

Y1 - 2016/8/12

N2 - We present our submission to the crosslingual pronoun prediction (CLPP) shared task for English-German and EnglishFrench at the First Conference on Machine Translation (WMT16). We trained a Maximum Entropy (MaxEnt) classifier based on features from Wetzel et al. (2015),that we ada pted to the new task and applied to a new language pair. Additional features such as n-grams of the pronoun context and prediction of NULLtranslations proved helpful to a varying degree. Experiments with a sequence classifier over pronoun sequences did not show any improvements. Our submission is among the top three systems for English-French (61.62% macro-averaged recall) and in the middle range for EnglishGerman (48.72%) out of nine submissions.

AB - We present our submission to the crosslingual pronoun prediction (CLPP) shared task for English-German and EnglishFrench at the First Conference on Machine Translation (WMT16). We trained a Maximum Entropy (MaxEnt) classifier based on features from Wetzel et al. (2015),that we ada pted to the new task and applied to a new language pair. Additional features such as n-grams of the pronoun context and prediction of NULLtranslations proved helpful to a varying degree. Experiments with a sequence classifier over pronoun sequences did not show any improvements. Our submission is among the top three systems for English-French (61.62% macro-averaged recall) and in the middle range for EnglishGerman (48.72%) out of nine submissions.

M3 - Conference contribution

SN - 978-1-945626-10-4

SP - 620

EP - 626

BT - Proceedings of the First Conference on Machine Translation, Volume 2: Shared Task Papers

PB - Association for Computational Linguistics

CY - Berlin, Germany

T2 - First Conference on Machine Translation

Y2 - 11 August 2016 through 12 August 2016

ER -

Cross-lingual Pronoun Prediction for English, French and German with Maximum Entropy Classification

Abstract

Conference

Access to Document

Fingerprint

Cite this