Feature Exploration for Cross-Lingual Pronoun Prediction
2016 (English)In: Proceedings of the First Conference on Machine Translation, 2016, 609-615 p.Conference paper (Refereed)
We explore a large number of featuresfor cross-lingual pronoun prediction for translation between English and German/French. We find that features related to German/French are more informative than features related to English, regardless of the translation direction. Our most useful features are local context, dependency head features, and source pronouns. We also find that it is sometimes more successful to employ a 2-step procedure that first makes a binary choice between pronouns and other, then classifies pronouns.For the pronoun/other distinction POS n-grams were very useful.
Place, publisher, year, edition, pages
2016. 609-615 p.
Language Technology (Computational Linguistics)
Research subject Computational Linguistics
IdentifiersURN: urn:nbn:se:uu:diva-310321OAI: oai:DiVA.org:uu-310321DiVA: diva2:1056100
The First Conference on Machine Translation
FundereSSENCE - An eScience Collaboration