AUGVIC: Exploiting BiText Vicinity for Low-Resource NMT

Tasnim Mohiuddin, M. Saiful Bari, Shafiq Joty

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

4 Citations (Scopus)

Abstract

The success of Neural Machine Translation (NMT) largely depends on the availability of large bitext training corpora. Due to the lack of such large corpora in low-resource language pairs, NMT systems often exhibit poor performance. Extra relevant monolingual data often helps, but acquiring it could be quite expensive, especially for low-resource languages. Moreover, domain mismatch between bitext (train/test) and monolingual data might degrade the performance. To alleviate such issues, we propose AUGVIC, a novel data augmentation framework for low-resource NMT which exploits the vicinal samples of the given bitext without using any extra monolingual data explicitly. It can diversify the in-domain bitext data with finer level control. Through extensive experiments on four low-resource language pairs comprising data from different domains, we have shown that our method is comparable to the traditional back-translation that uses extra in-domain monolingual data. When we combine the synthetic parallel data generated from AUGVIC with the ones from the extra monolingual data, we achieve further improvements. We show that AUGVIC helps to attenuate the discrepancies between relevant and distant-domain monolingual data in traditional back-translation. To understand the contributions of different components of AUGVIC, we perform an in-depth framework analysis.

Original languageEnglish
Title of host publicationFindings of the Association for Computational Linguistics
Subtitle of host publicationACL-IJCNLP 2021
EditorsChengqing Zong, Fei Xia, Wenjie Li, Roberto Navigli
PublisherAssociation for Computational Linguistics (ACL)
Pages3034-3045
Number of pages12
ISBN (Electronic)9781954085541
Publication statusPublished - 2021
Externally publishedYes
EventFindings of the Association for Computational Linguistics: ACL-IJCNLP 2021 - Virtual, Online
Duration: 1 Aug 20216 Aug 2021

Publication series

NameFindings of the Association for Computational Linguistics: ACL-IJCNLP 2021

Conference

ConferenceFindings of the Association for Computational Linguistics: ACL-IJCNLP 2021
CityVirtual, Online
Period1/08/216/08/21

Fingerprint

Dive into the research topics of 'AUGVIC: Exploiting BiText Vicinity for Low-Resource NMT'. Together they form a unique fingerprint.

Cite this