Header

UZH-Logo

Maintenance Infos

Improving Massively Multilingual Neural Machine Translation and Zero-Shot Translation


Zhang, Biao; Williams, Philip; Titov, Ivan; Sennrich, Rico (2020). Improving Massively Multilingual Neural Machine Translation and Zero-Shot Translation. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, Online, 6 July 2020 - 10 July 2020, 1628-1639.

Abstract

Massively multilingual models for neural machine translation (NMT) are theoretically attractive, but often underperform bilingual models and deliver poor zero-shot translations. In this paper, we explore ways to improve them. We argue that multilingual NMT requires stronger modeling capacity to support language pairs with varying typological characteristics, and overcome this bottleneck via language-specific components and deepening NMT architectures. We identify the off-target translation issue (i.e. translating into a wrong target language) as the major source of the inferior zero-shot performance, and propose random online backtranslation to enforce the translation of unseen training language pairs. Experiments on OPUS-100 (a novel multilingual dataset with 100 languages) show that our approach substantially narrows the performance gap with bilingual models in both one-to-many and many-to-many settings, and improves zero-shot performance by ~10 BLEU, approaching conventional pivot-based methods.

Abstract

Massively multilingual models for neural machine translation (NMT) are theoretically attractive, but often underperform bilingual models and deliver poor zero-shot translations. In this paper, we explore ways to improve them. We argue that multilingual NMT requires stronger modeling capacity to support language pairs with varying typological characteristics, and overcome this bottleneck via language-specific components and deepening NMT architectures. We identify the off-target translation issue (i.e. translating into a wrong target language) as the major source of the inferior zero-shot performance, and propose random online backtranslation to enforce the translation of unseen training language pairs. Experiments on OPUS-100 (a novel multilingual dataset with 100 languages) show that our approach substantially narrows the performance gap with bilingual models in both one-to-many and many-to-many settings, and improves zero-shot performance by ~10 BLEU, approaching conventional pivot-based methods.

Statistics

Downloads

4 downloads since deposited on 23 Jun 2020
4 downloads since 12 months
Detailed statistics

Additional indexing

Item Type:Conference or Workshop Item (Paper), original work
Communities & Collections:06 Faculty of Arts > Institute of Computational Linguistics
Dewey Decimal Classification:000 Computer science, knowledge & systems
410 Linguistics
Language:English
Event End Date:10 July 2020
Deposited On:23 Jun 2020 11:47
Last Modified:23 Jun 2020 19:30
Publisher:Association for Computational Linguistics
OA Status:Green
Free access at:Official URL. An embargo period may apply.
Official URL:https://www.aclweb.org/anthology/2020.acl-main.148
Project Information:
  • : FunderH2020
  • : Grant ID825460
  • : Project TitleEuropean Live Translator
  • : FunderH2020
  • : Grant ID825299
  • : Project TitleGlobal Under-Resourced MEedia Translation
  • : FunderSNSF
  • : Grant IDPP00P1_176727
  • : Project TitleMulti-Task Learning with Multilingual Resources for Better Natural Language Understanding

Download

Green Open Access

Download PDF  'Improving Massively Multilingual Neural Machine Translation and Zero-Shot Translation'.
Preview
Content: Published Version
Language: English
Filetype: PDF
Size: 466kB
Licence: Creative Commons: Attribution 4.0 International (CC BY 4.0)