Improving Massively Multilingual Neural Machine Translation and Zero-Shot Translation

Biao Zhang, Philip Williams, Ivan Titov, Rico Sennrich

Abstract Paper Share

Machine Translation Long Paper

Session 2B: Jul 6 (09:00-10:00 GMT)
Session 3A: Jul 6 (12:00-13:00 GMT)
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.
You can open the pre-recorded video in a separate window.
NOTE: The SlidesLive video may display a random order of the authors. The correct author list is shown at the top of this webpage.

Similar Papers

Leveraging Monolingual Data with Self-Supervision for Multilingual Neural Machine Translation
Aditya Siddhant, Ankur Bapna, Yuan Cao, Orhan Firat, Mia Chen, Sneha Kudugunta, Naveen Arivazhagan, Yonghui Wu,
A representative figure from paper main.252
Language-aware Interlingua for Multilingual Neural Machine Translation
Changfeng Zhu, Heng Yu, Shanbo Cheng, Weihua Luo,
A representative figure from paper main.150
Knowledge Distillation for Multilingual Unsupervised Neural Machine Translation
Haipeng Sun, Rui Wang, Kehai Chen, Masao Utiyama, Eiichiro Sumita, Tiejun Zhao,
A representative figure from paper main.324
Zero-Shot Transfer Learning with Synthesized Data for Multi-Domain Dialogue State Tracking
Giovanni Campagna, Agata Foryciarz, Mehrad Moradshahi, Monica Lam,
A representative figure from paper main.12