Context-Aware Monolingual Repair for Neural Machine Translation

Elena Voita, Rico Sennrich, Ivan Titov

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Modern sentence-level NMT systems often produce plausible translations of isolated sentences. However, when put in context, these translations may end up being inconsistent with each other. We propose a monolingual DocRepair model to correct inconsistencies between sentence-level translations. DocRepair performs automatic post-editing on a sequence of sentence-level translations, refining translations of sentences in context of each other. For training, the DocRepair model requires only monolingual document-level data in the target language. It is trained as a monolingual sequence-to-sequence model that maps inconsistent groups of sentences into consistent ones. The consistent groups come from the original training data; the inconsistent groups are obtained by sampling round-trip translations for each isolated sentence. We show that this approach successfully imitates inconsistencies we aim to fix: using contrastive evaluation, we show large improvements in the translation of several contextual phenomena in an English!Russian translation task, as well as improvements in the BLEU score. We also conduct a human evaluation and show a strong preference of the annotators to corrected translations over the baseline ones. Moreover, we analyze which discourse phenomena are hard to capture using monolingual data only.
Original languageEnglish
Title of host publicationProceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and 9th International Joint Conference on Natural Language Processing
Place of PublicationHong Kong, China
PublisherAssociation for Computational Linguistics (ACL)
Pages876-885
Number of pages10
ISBN (Print)978-1-950737-90-1
DOIs
Publication statusPublished - 3 Nov 2019
Event2019 Conference on Empirical Methods in Natural Language Processing and 9th International Joint Conference on Natural Language Processing - Hong Kong, Hong Kong
Duration: 3 Nov 20197 Nov 2019
https://www.emnlp-ijcnlp2019.org/

Conference

Conference2019 Conference on Empirical Methods in Natural Language Processing and 9th International Joint Conference on Natural Language Processing
Abbreviated titleEMNLP-IJCNLP 2019
Country/TerritoryHong Kong
CityHong Kong
Period3/11/197/11/19
Internet address

Fingerprint

Dive into the research topics of 'Context-Aware Monolingual Repair for Neural Machine Translation'. Together they form a unique fingerprint.

Cite this