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
Editors:
Bonnie Webber, Andrei Popescu-Belis, Jörg Tiedemann
Venue:
DiscoMT
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
58–62
Language:
URL:
https://aclanthology.org/W17-4807
DOI:
10.18653/v1/W17-4807
Bibkey:
Cite (ACL):
Christian Hardmeier. 2017. Predicting Pronouns with a Convolutional Network and an N-gram Model. In Proceedings of the Third Workshop on Discourse in Machine Translation, pages 58–62, Copenhagen, Denmark. Association for Computational Linguistics.
Cite (Informal):
Predicting Pronouns with a Convolutional Network and an N-gram Model (Hardmeier, DiscoMT 2017)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-1/W17-4807.pdf