Latent Anaphora Resolution for Cross-Lingual Pronoun Prediction

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.

[1]  Hwee Tou Ng,et al.  A Machine Learning Approach to Coreference Resolution of Noun Phrases , 2001, CL.

[2]  Hermann Ney,et al.  A Systematic Comparison of Various Statistical Alignment Models , 2003, CL.

[3]  Vincent Ng,et al.  Translation-Based Projection for Multilingual Coreference Resolution , 2012, NAACL.

[4]  NeyHermann,et al.  A systematic comparison of various statistical alignment models , 2003 .

[5]  Holger Schwenk,et al.  Continuous space language models , 2007, Comput. Speech Lang..

[6]  Michael Collins,et al.  Head-Driven Statistical Models for Natural Language Parsing , 2003, CL.

[7]  Liane Guillou,et al.  Improving Pronoun Translation for Statistical Machine Translation , 2012, EACL.

[8]  Christian Hardmeier,et al.  Discourse in Statistical Machine Translation : A Survey and a Case Study , 2012 .

[9]  Dan Klein,et al.  Accurate Unlexicalized Parsing , 2003, ACL.

[10]  Colin Cherry,et al.  An Expectation Maximization Approach to Pronoun Resolution , 2005, CoNLL.

[11]  Micha Elsner,et al.  EM Works for Pronoun Anaphora Resolution , 2009, EACL.

[12]  Michal Novák,et al.  Using Czech-English Parallel Corpora in Automatic Identification of It , 2012 .

[13]  Ruslan Mitkov,et al.  Using bilingual corpora to improve pronoun resolution , 2004 .

[14]  Jason Weston,et al.  Natural Language Processing (Almost) from Scratch , 2011, J. Mach. Learn. Res..

[15]  Yannick Versley,et al.  BART: A Multilingual Anaphora Resolution System , 2010, *SEMEVAL.

[16]  Benoît Sagot,et al.  The Lefff 2 syntactic lexicon for French: architecture, acquisition, use , 2006, LREC.

[17]  Alexandre Allauzen,et al.  Continuous Space Translation Models with Neural Networks , 2012, NAACL.

[18]  Philipp Koehn,et al.  Aiding Pronoun Translation with Co-Reference Resolution , 2010, WMT@ACL.

[19]  Marcello Federico,et al.  Modelling pronominal anaphora in statistical machine translation , 2010, IWSLT.

[20]  Yoshua Bengio,et al.  A Neural Probabilistic Language Model , 2003, J. Mach. Learn. Res..

[21]  Constantin Orasan,et al.  Transferring Coreference Chains through Word Alignment , 2006, LREC.

[22]  Roland Stuckardt,et al.  Applying Backpropagation Networks to Anaphor Resolution , 2007, DAARC.

[23]  Mauro Cettolo,et al.  WIT3: Web Inventory of Transcribed and Translated Talks , 2012, EAMT.

[24]  Constantin Orasan,et al.  Can Projected Chains in Parallel Corpora Help Coreference Resolution? , 2011, DAARC.

[25]  Pedro M. Domingos,et al.  Joint Unsupervised Coreference Resolution with Markov Logic , 2008, EMNLP.