Part-of-Speech Driven Cross-Lingual Pronoun Prediction with Feed-Forward Neural Networks

Jimmy Callin; Christian Hardmeier; Jörg Tiedemann

doi:10.18653/v1/W15-2508

Part-of-Speech Driven Cross-Lingual Pronoun Prediction with Feed-Forward Neural Networks

Jimmy Callin, Christian Hardmeier, Jörg Tiedemann

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

Abstract / Description of output

For some language pairs, pronoun translation is a discourse-driven task which requires information that lies beyond its local context. This motivates the task of predicting the correct pronoun given a source sentence and a target translation, where the translated pronouns have been replaced with placeholders. For cross-lingual pronoun prediction, we suggest a neural network-based model using preceding nouns and determiners as features for suggesting antecedent candidates. Our model scores on par with similar models while having a simpler architecture.

Original language	English
Title of host publication	Proceedings of the Second Workshop on Discourse in Machine Translation
Place of Publication	Lisbon, Portugal
Publisher	Association for Computational Linguistics
Pages	59-64
Number of pages	6
ISBN (Electronic)	978-1-941643-32-7
DOIs	https://doi.org/10.18653/v1/W15-2508
Publication status	Published - 21 Sept 2015
Event	Second Workshop on Discourse in Machine Translation - Lisbon, Portugal Duration: 17 Sept 2015 → 17 Sept 2015 http://www.emnlp2015.org/proceedings/DiscoMT/index.html

Workshop

Workshop	Second Workshop on Discourse in Machine Translation
Abbreviated title	DiscoMT 2015
Country/Territory	Portugal
City	Lisbon
Period	17/09/15 → 17/09/15
Internet address	http://www.emnlp2015.org/proceedings/DiscoMT/index.html

Access to Document

10.18653/v1/W15-2508Licence: Creative Commons: Attribution-NonCommercial-ShareAlike (CC BY-NC-SA)

Part-of-Speech Driven_CALLIN_DOA26072015_VOR_CC-BYFinal published version, 170 KBLicence: Creative Commons: Attribution-NonCommercial-ShareAlike (CC BY-NC-SA)

https://www.aclweb.org/anthology/W15-2508Licence: Creative Commons: Attribution-NonCommercial-ShareAlike (CC BY-NC-SA)

Cite this

@inproceedings{dacd96070671421197555636aa667d7b,

title = "Part-of-Speech Driven Cross-Lingual Pronoun Prediction with Feed-Forward Neural Networks",

abstract = "For some language pairs, pronoun translation is a discourse-driven task which requires information that lies beyond its local context. This motivates the task of predicting the correct pronoun given a source sentence and a target translation, where the translated pronouns have been replaced with placeholders. For cross-lingual pronoun prediction, we suggest a neural network-based model using preceding nouns and determiners as features for suggesting antecedent candidates. Our model scores on par with similar models while having a simpler architecture.",

author = "Jimmy Callin and Christian Hardmeier and J{\"o}rg Tiedemann",

year = "2015",

month = sep,

day = "21",

doi = "10.18653/v1/W15-2508",

language = "English",

pages = "59--64",

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

publisher = "Association for Computational Linguistics",

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

url = "http://www.emnlp2015.org/proceedings/DiscoMT/index.html",

}

Callin, J, Hardmeier, C & Tiedemann, J 2015, Part-of-Speech Driven Cross-Lingual Pronoun Prediction with Feed-Forward Neural Networks. in Proceedings of the Second Workshop on Discourse in Machine Translation. Association for Computational Linguistics, Lisbon, Portugal, pp. 59-64, Second Workshop on Discourse in Machine Translation , Lisbon, Portugal, 17/09/15. https://doi.org/10.18653/v1/W15-2508

Part-of-Speech Driven Cross-Lingual Pronoun Prediction with Feed-Forward Neural Networks. / Callin, Jimmy; Hardmeier, Christian; Tiedemann, Jörg.
Proceedings of the Second Workshop on Discourse in Machine Translation. Lisbon, Portugal: Association for Computational Linguistics, 2015. p. 59-64.

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

TY - GEN

T1 - Part-of-Speech Driven Cross-Lingual Pronoun Prediction with Feed-Forward Neural Networks

AU - Callin, Jimmy

AU - Hardmeier, Christian

AU - Tiedemann, Jörg

PY - 2015/9/21

Y1 - 2015/9/21

N2 - For some language pairs, pronoun translation is a discourse-driven task which requires information that lies beyond its local context. This motivates the task of predicting the correct pronoun given a source sentence and a target translation, where the translated pronouns have been replaced with placeholders. For cross-lingual pronoun prediction, we suggest a neural network-based model using preceding nouns and determiners as features for suggesting antecedent candidates. Our model scores on par with similar models while having a simpler architecture.

AB - For some language pairs, pronoun translation is a discourse-driven task which requires information that lies beyond its local context. This motivates the task of predicting the correct pronoun given a source sentence and a target translation, where the translated pronouns have been replaced with placeholders. For cross-lingual pronoun prediction, we suggest a neural network-based model using preceding nouns and determiners as features for suggesting antecedent candidates. Our model scores on par with similar models while having a simpler architecture.

U2 - 10.18653/v1/W15-2508

DO - 10.18653/v1/W15-2508

M3 - Conference contribution

SP - 59

EP - 64

BT - Proceedings of the Second Workshop on Discourse in Machine Translation

PB - Association for Computational Linguistics

CY - Lisbon, Portugal

T2 - Second Workshop on Discourse in Machine Translation

Y2 - 17 September 2015 through 17 September 2015

ER -

Part-of-Speech Driven Cross-Lingual Pronoun Prediction with Feed-Forward Neural Networks

Abstract / Description of output

Workshop

Access to Document

Fingerprint

Cite this