Pronoun-Focused MT and Cross-Lingual Pronoun Prediction: Findings of the 2015 DiscoMT Shared Task on Pronoun Translation

Christian Hardmeier; Qatar Computing Institute; Sara Stymne; Jörg Tiedemann; Yannick Versley; Mauro Cettolo

Pronoun-Focused MT and Cross-Lingual Pronoun Prediction: Findings of the 2015 DiscoMT Shared Task on Pronoun Translation

Christian Hardmeier, Qatar Computing Institute, Sara Stymne, Jörg Tiedemann, Yannick Versley, Mauro Cettolo

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

Abstract

We describe the design, the evaluation setup, and the results of the DiscoMT 2015 shared task, which included two subtasks, relevant to both the machine translation (MT) and the discourse communities: (i) pronoun-focused translation, a practical MT task, and (ii) cross-lingual pronoun prediction, a classification task that requires no specific MT expertise and is interesting as a machine learning task in its own right. We focused on the English–French language pair, for which MT output is generally of high quality, but has visible issues with pronoun translation due
to differences in the pronoun systems of the two languages. Six groups participated in the pronoun-focused translation task and eight groups in the cross-lingual pronoun prediction task

Original language	Other/Unknown
Title of host publication	Proceedings of the Second Workshop on Discourse in Machine Translation (DiscoMT),
Number of pages	16
Publisher	The Association for Computational Linguistics
Publication date	1 Sept 2015
Pages	1-16
ISBN (Print)	978-1-94163-32-7
Publication status	Published - 1 Sept 2015
Externally published	Yes
MoE publication type	A4 Article in conference proceedings
Event	Workshop on Discourse in Machine Translation (DiscoMT), - Lisbon, Portugal Duration: 17 Sept 2015 → 17 Sept 2015 Conference number: 2

Fields of Science

6121 Languages

Access to Document

http://aclweb.org/anthology/W15-2501

DiscoMT: Discourse-Oriented Statistical Machine Translation
Tiedemann, J. (Project manager), Hardmeier, C. (Principal Investigator), Loáiciga, S. (Participant) & Scherrer, Y. (Participant)
01/01/2012 → 31/12/2017
Project: Research project

DiscoMT 2015 Shared Task on Pronoun Translation
Tiedemann, J. (Creator), LINDAT/CLARIN, 31 Jan 2016
DOI: http://hdl.handle.net/11372/LRT-1611, http://hdl.handle.net/11372/LRT-1611
Dataset

Cite this

Hardmeier, C., Institute, Q. C., Stymne, S., Tiedemann, J., Versley, Y., & Cettolo, M. (2015). Pronoun-Focused MT and Cross-Lingual Pronoun Prediction: Findings of the 2015 DiscoMT Shared Task on Pronoun Translation. In Proceedings of the Second Workshop on Discourse in Machine Translation (DiscoMT), (pp. 1-16). The Association for Computational Linguistics. http://aclweb.org/anthology/W15-2501

@inproceedings{c78925bbd70047c49776daebced8004b,

title = "Pronoun-Focused MT and Cross-Lingual Pronoun Prediction: Findings of the 2015 DiscoMT Shared Task on Pronoun Translation",

abstract = "We describe the design, the evaluation setup, and the results of the DiscoMT 2015 shared task, which included two subtasks, relevant to both the machine translation (MT) and the discourse communities: (i) pronoun-focused translation, a practical MT task, and (ii) cross-lingual pronoun prediction, a classification task that requires no specific MT expertise and is interesting as a machine learning task in its own right. We focused on the English–French language pair, for which MT output is generally of high quality, but has visible issues with pronoun translation dueto differences in the pronoun systems of the two languages. Six groups participated in the pronoun-focused translation task and eight groups in the cross-lingual pronoun prediction task",

keywords = "6121 Spr{\aa}kvetenskaper",

author = "Christian Hardmeier and Institute, {Qatar Computing} and Sara Stymne and J{\"o}rg Tiedemann and Yannick Versley and Mauro Cettolo",

year = "2015",

month = sep,

day = "1",

language = "odefinierat/ok{\"a}nt",

isbn = "978-1-94163-32-7",

pages = "1--16",

booktitle = "Proceedings of the Second Workshop on Discourse in Machine Translation (DiscoMT),",

publisher = "The Association for Computational Linguistics",

address = "F{\"o}renta Staterna (USA)",

note = "Workshop on Discourse in Machine Translation (DiscoMT), ; Conference date: 17-09-2015 Through 17-09-2015",

}

Hardmeier, C, Institute, QC, Stymne, S, Tiedemann, J, Versley, Y & Cettolo, M 2015, Pronoun-Focused MT and Cross-Lingual Pronoun Prediction: Findings of the 2015 DiscoMT Shared Task on Pronoun Translation. in Proceedings of the Second Workshop on Discourse in Machine Translation (DiscoMT),. The Association for Computational Linguistics, pp. 1-16, Workshop on Discourse in Machine Translation (DiscoMT), Lisbon, Portugal, 17/09/2015. <http://aclweb.org/anthology/W15-2501>

Pronoun-Focused MT and Cross-Lingual Pronoun Prediction: Findings of the 2015 DiscoMT Shared Task on Pronoun Translation. / Hardmeier, Christian; Institute, Qatar Computing; Stymne, Sara et al.
Proceedings of the Second Workshop on Discourse in Machine Translation (DiscoMT),. The Association for Computational Linguistics, 2015. p. 1-16.

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

TY - GEN

T1 - Pronoun-Focused MT and Cross-Lingual Pronoun Prediction

T2 - Workshop on Discourse in Machine Translation (DiscoMT),

AU - Hardmeier, Christian

AU - Institute, Qatar Computing

AU - Stymne, Sara

AU - Tiedemann, Jörg

AU - Versley, Yannick

AU - Cettolo, Mauro

N1 - Conference code: 2

PY - 2015/9/1

Y1 - 2015/9/1

N2 - We describe the design, the evaluation setup, and the results of the DiscoMT 2015 shared task, which included two subtasks, relevant to both the machine translation (MT) and the discourse communities: (i) pronoun-focused translation, a practical MT task, and (ii) cross-lingual pronoun prediction, a classification task that requires no specific MT expertise and is interesting as a machine learning task in its own right. We focused on the English–French language pair, for which MT output is generally of high quality, but has visible issues with pronoun translation dueto differences in the pronoun systems of the two languages. Six groups participated in the pronoun-focused translation task and eight groups in the cross-lingual pronoun prediction task

AB - We describe the design, the evaluation setup, and the results of the DiscoMT 2015 shared task, which included two subtasks, relevant to both the machine translation (MT) and the discourse communities: (i) pronoun-focused translation, a practical MT task, and (ii) cross-lingual pronoun prediction, a classification task that requires no specific MT expertise and is interesting as a machine learning task in its own right. We focused on the English–French language pair, for which MT output is generally of high quality, but has visible issues with pronoun translation dueto differences in the pronoun systems of the two languages. Six groups participated in the pronoun-focused translation task and eight groups in the cross-lingual pronoun prediction task

KW - 6121 Språkvetenskaper

M3 - Konferensbidrag

SN - 978-1-94163-32-7

SP - 1

EP - 16

BT - Proceedings of the Second Workshop on Discourse in Machine Translation (DiscoMT),

PB - The Association for Computational Linguistics

Y2 - 17 September 2015 through 17 September 2015

ER -

Pronoun-Focused MT and Cross-Lingual Pronoun Prediction: Findings of the 2015 DiscoMT Shared Task on Pronoun Translation

Abstract

Fields of Science

Access to Document

Projects

DiscoMT: Discourse-Oriented Statistical Machine Translation

Datasets

DiscoMT 2015 Shared Task on Pronoun Translation

Cite this