TY - GEN
T1 - DEEP
T2 - 60th Annual Meeting of the Association for Computational Linguistics, ACL 2022
AU - Hu, Junjie
AU - Hayashi, Hiroaki
AU - Cho, Kyunghyun
AU - Neubig, Graham
N1 - Publisher Copyright:
© 2022 Association for Computational Linguistics.
PY - 2022
Y1 - 2022
N2 - It has been shown that machine translation models usually generate poor translations for named entities that are infrequent in the training corpus. Earlier named entity translation methods mainly focus on phonetic transliteration, which ignores the sentence context for translation and is limited in domain and language coverage. To address this limitation, we propose DEEP, a DEnoising Entity Pretraining method that leverages large amounts of monolingual data and a knowledge base to improve named entity translation accuracy within sentences. Besides, we investigate a multi-task learning strategy that finetunes a pre-trained neural machine translation model on both entity-augmented monolingual data and parallel data to further improve entity translation. Experimental results on three language pairs demonstrate that DEEP results in significant improvements over strong denoising auto-encoding baselines, with a gain of up to 1.3 BLEU and up to 9.2 entity accuracy points for English-Russian translation.
AB - It has been shown that machine translation models usually generate poor translations for named entities that are infrequent in the training corpus. Earlier named entity translation methods mainly focus on phonetic transliteration, which ignores the sentence context for translation and is limited in domain and language coverage. To address this limitation, we propose DEEP, a DEnoising Entity Pretraining method that leverages large amounts of monolingual data and a knowledge base to improve named entity translation accuracy within sentences. Besides, we investigate a multi-task learning strategy that finetunes a pre-trained neural machine translation model on both entity-augmented monolingual data and parallel data to further improve entity translation. Experimental results on three language pairs demonstrate that DEEP results in significant improvements over strong denoising auto-encoding baselines, with a gain of up to 1.3 BLEU and up to 9.2 entity accuracy points for English-Russian translation.
UR - http://www.scopus.com/inward/record.url?scp=85136102296&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85136102296&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:85136102296
T3 - Proceedings of the Annual Meeting of the Association for Computational Linguistics
SP - 1753
EP - 1766
BT - ACL 2022 - 60th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers)
A2 - Muresan, Smaranda
A2 - Nakov, Preslav
A2 - Villavicencio, Aline
PB - Association for Computational Linguistics (ACL)
Y2 - 22 May 2022 through 27 May 2022
ER -