Filling Gender & Number Gaps in Neural Machine Translation with Black-box Context Injection

When translating from a language that does not morphologically mark information such as gender and number into a language that does, translation systems must "guess" this missing information, often leading to incorrect translations in the given context. We propose a black-box approach for injecting the missing information to a pre-trained neural machine translation system, allowing to control the morphological variations in the generated translations without changing the underlying model or training data. We evaluate our method on an English to Hebrew translation task, and show that it is effective in injecting the gender and number information and that supplying the correct information improves the translation accuracy in up to 2.3 BLEU on a female-speaker test set for a state-of-the-art online black-box system. Finally, we perform a fine-grained syntactic analysis of the generated translations that shows the effectiveness of our method.

[1]  Philipp Koehn,et al.  Europarl: A Parallel Corpus for Statistical Machine Translation , 2005, MTSUMMIT.

[2]  Yoav Goldberg,et al.  Controlling Linguistic Style Aspects in Neural Language Generation , 2017, ArXiv.

[3]  Jörg Tiedemann,et al.  Neural Machine Translation with Extended Context , 2017, DiscoMT@EMNLP.

[4]  Mikko Kurimo,et al.  Extending hybrid word-character neural machine translation with multi-task learning of morphological analysis , 2017, WMT.

[5]  Andy Way,et al.  Getting Gender Right in Neural MT , 2018, EMNLP.

[6]  Yonatan Belinkov,et al.  Understanding and Improving Morphological Learning in the Neural Machine Translation Decoder , 2017, IJCNLP.

[7]  Rico Sennrich,et al.  Evaluating Discourse Phenomena in Neural Machine Translation , 2017, NAACL.

[8]  Salim Roukos,et al.  Bleu: a Method for Automatic Evaluation of Machine Translation , 2002, ACL.

[9]  François Yvon,et al.  Evaluating the morphological competence of Machine Translation Systems , 2017, WMT.

[10]  Rico Sennrich,et al.  Context-Aware Neural Machine Translation Learns Anaphora Resolution , 2018, ACL.

[11]  Rico Sennrich,et al.  Controlling Politeness in Neural Machine Translation via Side Constraints , 2016, NAACL.

[12]  Lucia Specia,et al.  Personalized Machine Translation: Preserving Original Author Traits , 2016, EACL.

[13]  Philipp Koehn,et al.  Moses: Open Source Toolkit for Statistical Machine Translation , 2007, ACL.

[14]  J. Nichols Head-marking and dependent-marking grammar , 1986 .