Pronoun Language Model and Grammatical Heuristics for Aiding Pronoun Prediction

The cross-lingual pronoun prediction task at WMT 2016 requires to restore the missing target pronouns from source text and target lemmatized and POS-tagged translations. We study the benefits for this task of a specific Pronoun Language Model (PLM), which captures the likelihood of a pronoun given the gender and number of the nouns or pronouns preceding it, on the target-side only. Experimenting with the English-to-French subtask, we select the best candidate pronoun by applying the PLM and additional heuristics based on French grammar rules to the target-side texts provided in the subtask. Although the PLM helps to outperform a random baseline, it still scores far lower than sys-tem using both source and target texts.

• Publication year

  2016

• Venue

  Conference on Machine Translation

• Publication date

  Unknown publication date

• Fields of study

  Linguistics, Computer Science

• Identifiers
  DOI 10.18653/v1/W16-2352
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Findings of the 2016 WMT Shared Task on Cross-lingual Pronoun Prediction

  2019influential reference
• Incorporating pronoun function into statistical machine translation

  2016influential reference
• A Contextual Language Model to Improve Machine Translation of Pronouns by Re-ranking Translation Hypotheses

  2016cited by this paper
• Baseline Models for Pronoun Prediction and Pronoun-Aware Translation

  2015cited by this paper
• Pronoun-Focused MT and Cross-Lingual Pronoun Prediction: Findings of the 2015 DiscoMT Shared Task on Pronoun Translation

  2015influential reference
• Pronoun Translation and Prediction with or without Coreference Links

  2015cited by this paper
• Part-of-Speech Driven Cross-Lingual Pronoun Prediction with Feed-Forward Neural Networks

  2015cited by this paper
• WIT3: Web Inventory of Transcribed and Translated Talks

  2012cited by this paper
• Discourse in Statistical Machine Translation

  2012influential reference
• Aiding Pronoun Translation with Co-Reference Resolution

  2010cited by this paper
• Modelling pronominal anaphora in statistical machine translation

  2010cited by this paper
• Learning Morphology with Morfette

  2008cited by this paper
• SRILM - an extensible language modeling toolkit

  2002cited by this paper

• Findings of the 2016 WMT Shared Task on Cross-lingual Pronoun Prediction

  2019cites this paper
• Going beyond the sentence: Contextual Machine Translation of Dialogue. (Au-delà de la phrase: traduction automatique de dialogue en contexte)

  2018cites this paper