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

Christian Hardmeier


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.
Anthology ID:
W17-4807
Volume:
Proceedings of the Third Workshop on Discourse in Machine Translation
Month:
September
Year:
2017
Address:
Copenhagen, Denmark
Venues:
DiscoMT | WS
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
58–62
Language:
URL:
https://www.aclweb.org/anthology/W17-4807
DOI:
10.18653/v1/W17-4807
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
http://aclanthology.lst.uni-saarland.de/W17-4807.pdf