Predicting Pronouns with a Convolutional Network and an N-gram Model
- Uppsala University
Research Output:
Conference Article in Proceeding or Book/Report chapter
Article in proceedings
Peer-review
Open access
Publication Information
Output type
Research Output:
Conference Article in Proceeding or Book/Report chapter
Article in proceedings
Peer-reviewOriginal language
EnglishPublication milestones
- Published - 07/09/2017
Publication status
Published - 07/09/2017
ISBN (Print)
978-1-945626-87-6Publication IDs
- ORCID: /0000-0002-6103-7275/work/106363241
- Scopus: 85058218173
Host publication title
Proceedings of the Third Workshop on Discourse in Machine TranslationAbstract
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.
Publication metrics
PlumX, opens in new tab
Captures
64
Citations
5