Better OOV Translation with Bilingual Terminology Mining

Huck, Matthias; Hangya, Viktor und Fraser, Alexander (2019): Better OOV Translation with Bilingual Terminology Mining. In: 57Th Annual Meeting of the Association for Computational Linguistics (Acl 2019): S. 5809-5815

Abstract

Unseen words, also called out-of-vocabulary words (OOVs), are difficult for machine translation. In neural machine translation, byte-pair encoding can be used to represent OOVs, but they are still often incorrectly translated. We improve the translation of OOVs in NMT using easy-to-obtain monolingual data. We look for OOVs in the text to be translated and translate them using simple-to-construct bilingual word embeddings (BWEs). In our MT experiments we take the 5-best candidates, which is motivated by intrinsic mining experiments. Using all five of the proposed target language words as queries we mine target-language sentences. We then back-translate, forcing the back-translation of each of the five proposed target-language OOV-translation-candidates to be the original source-language OOV. We show that by using this synthetic data to finetune our system the translation of OOVs can be dramatically improved. In our experiments we use a system trained on Europarl and mine sentences containing medical terms from monolingual data.

• Dokumententyp: Zeitschriftenartikel
• Fakultätsübergreifende Einrichtungen: Centrum für Informations- und Sprachverarbeitung (CIS)
• Themengebiete: 400 Sprache > 400 Sprache
• Sprache: Englisch