Tencent AI Lab - Shanghai Jiao Tong University Low-Resource Translation System for the WMT22 Translation Task

Zhiwei He, Xing Wang, Zhaopeng Tu, Shuming Shi, Rui Wang


Abstract
This paper describes Tencent AI Lab - Shanghai Jiao Tong University (TAL-SJTU) Low-Resource Translation systems for the WMT22 shared task. We participate in the general translation task on English-Livonian.Our system is based on M2M100 with novel techniques that adapt it to the target language pair.(1) Cross-model word embedding alignment: inspired by cross-lingual word embedding alignment, we successfully transfer a pre-trained word embedding to M2M100, enabling it to support Livonian.(2) Gradual adaptation strategy: we exploit Estonian and Latvian as auxiliary languages for many-to-many translation training and then adapt to English-Livonian.(3) Data augmentation: to enlarge the parallel data for English-Livonian, we construct pseudo-parallel data with Estonian and Latvian as pivot languages.(4) Fine-tuning: to make the most of all available data, we fine-tune the model with the validation set and online back-translation, further boosting the performance. In model evaluation: (1) We find that previous work underestimated the translation performance of Livonian due to inconsistent Unicode normalization, which may cause a discrepancy of up to 14.9 BLEU score.(2) In addition to the standard validation set, we also employ round-trip BLEU to evaluate the models, which we find more appropriate for this task. Finally, our unconstrained system achieves BLEU scores of 17.0 and 30.4 for English to/from Livonian.
Anthology ID:
2022.wmt-1.18
Volume:
Proceedings of the Seventh Conference on Machine Translation (WMT)
Month:
December
Year:
2022
Address:
Abu Dhabi, United Arab Emirates (Hybrid)
Editors:
Philipp Koehn, Loïc Barrault, Ondřej Bojar, Fethi Bougares, Rajen Chatterjee, Marta R. Costa-jussà, Christian Federmann, Mark Fishel, Alexander Fraser, Markus Freitag, Yvette Graham, Roman Grundkiewicz, Paco Guzman, Barry Haddow, Matthias Huck, Antonio Jimeno Yepes, Tom Kocmi, André Martins, Makoto Morishita, Christof Monz, Masaaki Nagata, Toshiaki Nakazawa, Matteo Negri, Aurélie Névéol, Mariana Neves, Martin Popel, Marco Turchi, Marcos Zampieri
Venue:
WMT
SIG:
SIGMT
Publisher:
Association for Computational Linguistics
Note:
Pages:
260–267
Language:
URL:
https://aclanthology.org/2022.wmt-1.18
DOI:
Bibkey:
Cite (ACL):
Zhiwei He, Xing Wang, Zhaopeng Tu, Shuming Shi, and Rui Wang. 2022. Tencent AI Lab - Shanghai Jiao Tong University Low-Resource Translation System for the WMT22 Translation Task. In Proceedings of the Seventh Conference on Machine Translation (WMT), pages 260–267, Abu Dhabi, United Arab Emirates (Hybrid). Association for Computational Linguistics.
Cite (Informal):
Tencent AI Lab - Shanghai Jiao Tong University Low-Resource Translation System for the WMT22 Translation Task (He et al., WMT 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.wmt-1.18.pdf