ITU

Exploring the importance of source text in automatic post-editing for context-aware machine translation

Research output: Conference Article in Proceeding or Book/Report chapterArticle in proceedingsResearchpeer-review

View graph of relations

Accurate translation requires documentlevel information, which is ignored by sentence-level machine translation. Recent work has demonstrated that document-level consistency can be improved with automatic post-editing (APE) using only targetlanguage (TL) information. We study an extended APE model that additionally integrates source context. A human evaluation of fluency and adequacy in EnglishRussian translation reveals that the model with access to source context significantly outperforms monolingual APE in terms of adequacy, an effect largely ignored by automatic evaluation metrics. Our results show that TL-only modelling increases fluency without improving adequacy, demonstrating the need for conditioning on source text for automatic post-editing. They also highlight blind spots in automatic methods for targeted evaluation and demonstrate the need for human assessment to evaluate document-level translation quality reliably.
Original languageEnglish
Title of host publicationProceedings of the 23rd Nordic Conference on Computational Linguistics (NODALIDA)
PublisherLinköping University Electronic Press
Publication date2021
Pages326-335
Publication statusPublished - 2021

ID: 86415153