It-disambiguation and source-aware language models for cross-lingual pronoun prediction

Sharid Loáiciga; Liane Guillou; Christian Hardmeier

doi:10.18653/v1/W16-2351

It-disambiguation and source-aware language models for cross-lingual pronoun prediction

Sharid Loáiciga
, Liane Guillou
, Christian Hardmeier

Research output: Conference Article in Proceeding or Book/Report chapter › Article in proceedings › Research › peer-review

Abstract

We present our systems for the WMT 2016 shared task on cross-lingual pronoun prediction. The main contribution is a classifier used to determine whether an instance of the ambiguous English pronoun “it” functions as an anaphoric, pleonastic or event reference pronoun. For the English-to-French task the classifier is incorporated in an extended baseline, which takes the form of a source-aware language model. An implementation of the sourceaware language model is also provided for each of the remaining language pairs

Original language	English
Title of host publication	Proceedings of the First Conference on Machine Translation: Volume 2, Shared Task Papers
Publication date	12 Aug 2016
Pages	581-588
DOIs	https://doi.org/10.18653/v1/W16-2351
Publication status	Published - 12 Aug 2016
Externally published	Yes

Keywords

cross-lingual pronoun prediction
anaphora resolution
pleonastic pronoun
source-aware language model
machine translation

Access to Document

10.18653/v1/W16-2351

Cite this

@inproceedings{025674ba8601408eb3cf17b004733360,

title = "It-disambiguation and source-aware language models for cross-lingual pronoun prediction",

abstract = "We present our systems for the WMT 2016 shared task on cross-lingual pronoun prediction. The main contribution is a classifier used to determine whether an instance of the ambiguous English pronoun “it” functions as an anaphoric, pleonastic or event reference pronoun. For the English-to-French task the classifier is incorporated in an extended baseline, which takes the form of a source-aware language model. An implementation of the sourceaware language model is also provided for each of the remaining language pairs",

keywords = "cross-lingual pronoun prediction, anaphora resolution, pleonastic pronoun, source-aware language model, machine translation",

author = "Sharid Lo{\'a}iciga and Liane Guillou and Christian Hardmeier",

year = "2016",

month = aug,

day = "12",

doi = "10.18653/v1/W16-2351",

language = "English",

pages = "581--588",

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

}

It-disambiguation and source-aware language models for cross-lingual pronoun prediction. / Loáiciga, Sharid; Guillou, Liane; Hardmeier, Christian.
Proceedings of the First Conference on Machine Translation: Volume 2, Shared Task Papers . 2016. p. 581-588.

Research output: Conference Article in Proceeding or Book/Report chapter › Article in proceedings › Research › peer-review

TY - GEN

T1 - It-disambiguation and source-aware language models for cross-lingual pronoun prediction

AU - Loáiciga, Sharid

AU - Guillou, Liane

AU - Hardmeier, Christian

PY - 2016/8/12

Y1 - 2016/8/12

N2 - We present our systems for the WMT 2016 shared task on cross-lingual pronoun prediction. The main contribution is a classifier used to determine whether an instance of the ambiguous English pronoun “it” functions as an anaphoric, pleonastic or event reference pronoun. For the English-to-French task the classifier is incorporated in an extended baseline, which takes the form of a source-aware language model. An implementation of the sourceaware language model is also provided for each of the remaining language pairs

AB - We present our systems for the WMT 2016 shared task on cross-lingual pronoun prediction. The main contribution is a classifier used to determine whether an instance of the ambiguous English pronoun “it” functions as an anaphoric, pleonastic or event reference pronoun. For the English-to-French task the classifier is incorporated in an extended baseline, which takes the form of a source-aware language model. An implementation of the sourceaware language model is also provided for each of the remaining language pairs

KW - cross-lingual pronoun prediction

KW - anaphora resolution

KW - pleonastic pronoun

KW - source-aware language model

KW - machine translation

U2 - 10.18653/v1/W16-2351

DO - 10.18653/v1/W16-2351

M3 - Article in proceedings

SP - 581

EP - 588

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

ER -

It-disambiguation and source-aware language models for cross-lingual pronoun prediction

Abstract

Keywords

Access to Document

Fingerprint

Cite this