Leveraging discourse rewards for document-level neural machine translation

Inigo Jauregi Unanue, Nazanin Esmaili, Reza Haffari, Massimo Piccardi

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review

Abstract

Document-level machine translation focuses on the translation of entire documents from a source to a target language. It is widely regarded as a challenging task since the translation of the individual sentences in the document needs to retain aspects of the discourse at document level. However, document-level translation models are usually not trained to explicitly ensure discourse quality. Therefore, in this paper we propose a training approach that explicitly optimizes two established discourse metrics, lexical cohesion and coherence, by using a reinforcement learning objective. Experiments over four different language pairs and three translation domains have shown that our training approach has been able to achieve more cohesive and coherent document translations than other competitive approaches, yet without compromising the faithfulness to the reference translation. In the case of the Zh-En language pair, our method has achieved an improvement of 2.46 percentage points (pp) in LC and 1.17 pp in COH over the runner-up, while at the same time improving 0.63 pp in BLEU score and 0.47 pp in F-BERT.
Original languageEnglish
Title of host publicationCOLING 2020
Subtitle of host publicationThe 28th International Conference on Computational Linguistics, Proceedings of the Conference
EditorsNuria Bel, Chengquing Zong
Place of PublicationStroudsburg PA USA
PublisherAssociation for Computational Linguistics (ACL)
Pages4467–4482
Number of pages16
ISBN (Electronic)9781952148279
DOIs
Publication statusPublished - 2020
EventInternational Conference on Computational Linguistics 2020 - Virtual, Barcelona, Spain
Duration: 8 Dec 202013 Dec 2020
Conference number: 28th
https://coling2020.org (Website)
https://www.aclweb.org/anthology/volumes/2020.coling-main/ (Proceedings)

Conference

ConferenceInternational Conference on Computational Linguistics 2020
Abbreviated titleCOLING 2020
Country/TerritorySpain
CityBarcelona
Period8/12/2013/12/20
Internet address

Cite this