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

Christian Hardmeier

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract / Description of output

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 languageEnglish
Title of host publicationProceedings of the Third Workshop on Discourse in Machine Translation
Place of PublicationCopenhagen, Denmark
PublisherAssociation for Computational Linguistics
Pages58-62
Number of pages5
ISBN (Electronic)978-1-945626-87-6
DOIs
Publication statusPublished - 7 Sept 2017
EventThird Workshop on Discourse in Machine Translation 2017 - Copenhagen, Denmark
Duration: 8 Sept 20178 Sept 2017
https://www.idiap.ch/workshop/DiscoMT

Workshop

WorkshopThird Workshop on Discourse in Machine Translation 2017
Abbreviated titleDiscoMT
Country/TerritoryDenmark
CityCopenhagen
Period8/09/178/09/17
Internet address

Fingerprint

Dive into the research topics of 'Predicting Pronouns with a Convolutional Network and an N-gram Model'. Together they form a unique fingerprint.

Cite this