2016 · 13 citations · 16 references
ComputingComputer ScienceFrenchComputational LinguisticsNatural Language ProcessingTranslation TheoryAnaphora ResolutionCoreference ResolutionLanguage ModelingLanguage ModelsMachine TranslationMachine Translation Post-editingEvaluation MetricsMachine-assisted TranslationPersonal PronounsPronoun RecognitionStatistical Coreference ResolutionStatistical Machine Translation
Information about the antecedents of pronouns is considered essential to solve certain translation divergencies, such as those concerning the English pronoun it when translated into gendered languages, e.g. for French into il, elle, or several other options. However, no machine translation system using anaphora resolution has so far been able to outperform a phrase-based statistical MT baseline. We address here one of the reasons for this failure: the imperfection of automatic anaphora resolution algorithms. Using parallel data, we learn probabilistic correlations between target-side pronouns and the gender and number features of their (uncertain) antecedents, as hypothesized by the Stanford Coreference Resolution system on the source side. We embody these correlations into a secondary translation model, which we invoke upon decoding with the Moses statistical phrase-based MT system. This solution outperforms a deterministic pronoun post-editing system, as well as a statistical MT baseline, on automatic and human evaluation metrics.
16
Philipp Koehn, Richard Zens, Chris Dyer et al. · 2007 · 4.9K citations · Full text
WIT3: Web Inventory of Transcribed and Translated Talks
Mauro Cettolo, Christian Girardi, Marcello Federico · 2012 · 580 citations
Findings of the 2014 Workshop on Statistical Machine Translation
Ondřej Bojar, Christian Buck, Christian Federmann et al. · 2014 · 537 citations · Full text