Latent Anaphora Resolution for Cross-Lingual Pronoun Prediction
2013 (English)In: Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing, Association for Computational Linguistics, 2013, 380-391 p.Conference paper (Refereed)
This paper addresses the task of predicting the correct French translations of third-person subject pronouns in English discourse, a problem that is relevant as a prerequisite for machine translation and that requires anaphora resolution. We present an approach based on neural networks that models anaphoric links as latent variables and show that its performance is competitive with that of a system with separate anaphora resolution while not requiring any coreference-annotated training data. This demonstrates that the information contained in parallel bitexts can successfully be used to acquire knowledge about pronominal anaphora in an unsupervised way.
Place, publisher, year, edition, pages
Association for Computational Linguistics, 2013. 380-391 p.
Coreference resolution, SMT, Cross-sentence SMT
Language Technology (Computational Linguistics)
Research subject Computational Linguistics
IdentifiersURN: urn:nbn:se:uu:diva-213737OAI: oai:DiVA.org:uu-213737DiVA: diva2:683314
EMNLP 2013; Conference on Empirical Methods in Natural Language Processing; 18-21 October 2013; Seattle, WA, USA