Predicting Pronouns with a Convolutional Network and an N-gram Model

Christian Hardmeier

doi:10.18653/v1/W17-4807

Predicting Pronouns with a Convolutional Network and an N-gram Model

Christian Hardmeier

Uppsala University

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

Abstract

This paper describes the UU-Hardmeier system submitted to the DiscoMT 2017 shared task on cross-lingual pronoun prediction. The system is an ensemble of convolutional neural networks combined with a source-aware n-gram language model.

Original language	English
Title of host publication	Proceedings of the Third Workshop on Discourse in Machine Translation
Publication date	7 Sept 2017
ISBN (Print)	978-1-945626-87-6
DOIs	https://doi.org/10.18653/v1/W17-4807
Publication status	Published - 7 Sept 2017
Externally published	Yes

Keywords

cross-lingual pronoun prediction
convolutional neural networks
ensemble learning
source-aware n-gram language model
machine translation

Access to Document

10.18653/v1/W17-4807

Cite this

@inproceedings{8ca80adcd234404381e55b6c940c1ae8,

title = "Predicting Pronouns with a Convolutional Network and an N-gram Model",

abstract = "This paper describes the UU-Hardmeier system submitted to the DiscoMT 2017 shared task on cross-lingual pronoun prediction. The system is an ensemble of convolutional neural networks combined with a source-aware n-gram language model.",

keywords = "cross-lingual pronoun prediction, convolutional neural networks, ensemble learning, source-aware n-gram language model, machine translation",

author = "Christian Hardmeier",

year = "2017",

month = sep,

day = "7",

doi = "10.18653/v1/W17-4807",

language = "English",

isbn = "978-1-945626-87-6",

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

}

TY - GEN

T1 - Predicting Pronouns with a Convolutional Network and an N-gram Model

AU - Hardmeier, Christian

PY - 2017/9/7

Y1 - 2017/9/7

N2 - This paper describes the UU-Hardmeier system submitted to the DiscoMT 2017 shared task on cross-lingual pronoun prediction. The system is an ensemble of convolutional neural networks combined with a source-aware n-gram language model.

AB - This paper describes the UU-Hardmeier system submitted to the DiscoMT 2017 shared task on cross-lingual pronoun prediction. The system is an ensemble of convolutional neural networks combined with a source-aware n-gram language model.

KW - cross-lingual pronoun prediction

KW - convolutional neural networks

KW - ensemble learning

KW - source-aware n-gram language model

KW - machine translation

U2 - 10.18653/v1/W17-4807

DO - 10.18653/v1/W17-4807

M3 - Article in proceedings

SN - 978-1-945626-87-6

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

ER -

Predicting Pronouns with a Convolutional Network and an N-gram Model

Abstract

Keywords

Access to Document

Fingerprint

Cite this