The RoyalFlush System for the WMT 2022 Efficiency Task
Bo Qin, Aixin Jia, Qiang Wang, Jianning Lu, Shuqin Pan, Haibo Wang, Ming Chen
Abstract
This paper describes the submission of the RoyalFlush neural machine translation system for the WMT 2022 translation efficiency task. Unlike the commonly used autoregressive translation system, we adopted a two-stage translation paradigm called Hybrid Regression Translation (HRT) to combine the advantages of autoregressive and non-autoregressive translation. Specifically, HRT first autoregressively generates a discontinuous sequence (e.g., make a prediction every k tokens, k1) and then fills in all previously skipped tokens at once in a non-autoregressive manner. Thus, we can easily trade off the translation quality and speed by adjusting k. In addition, by integrating other modeling techniques (e.g., sequence-level knowledge distillation and deep-encoder-shallow-decoder layer allocation strategy) and a mass of engineering efforts, HRT improves 80% inference speed and achieves equivalent translation performance with the same-capacity AT counterpart. Our fastest system reaches 6k+ words/second on the GPU latency setting, estimated to be about 3.1x faster than the last year’s winner.- Anthology ID:
- 2022.wmt-1.65
- 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:
- 671–676
- Language:
- URL:
- https://aclanthology.org/2022.wmt-1.65
- DOI:
- Cite (ACL):
- Bo Qin, Aixin Jia, Qiang Wang, Jianning Lu, Shuqin Pan, Haibo Wang, and Ming Chen. 2022. The RoyalFlush System for the WMT 2022 Efficiency Task. In Proceedings of the Seventh Conference on Machine Translation (WMT), pages 671–676, Abu Dhabi, United Arab Emirates (Hybrid). Association for Computational Linguistics.
- Cite (Informal):
- The RoyalFlush System for the WMT 2022 Efficiency Task (Qin et al., WMT 2022)
- PDF:
- https://preview.aclanthology.org/aacl-23-doi-ingestion/2022.wmt-1.65.pdf