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.
Originalsprog | Engelsk |
---|---|
Titel | Proceedings of the Third Workshop on Discourse in Machine Translation |
Publikationsdato | 7 sep. 2017 |
ISBN (Trykt) | 978-1-945626-87-6 |
DOI | |
Status | Udgivet - 7 sep. 2017 |
Udgivet eksternt | Ja |