Abstract
This tutorial provides a comprehensive guide to make the most of pre-training for neural machine translation. Firstly, we will briefly introduce the background of NMT, pre-training methodology, and point out the main challenges when applying pre-training for NMT. Then we will focus on analysing the role of pre-training in enhancing the performance of NMT, how to design a better pre-training model for executing specific NMT tasks and how to better integrate the pre-trained model into NMT system. In each part, we will provide examples, discuss training techniques and analyse what is transferred when applying pre-training.- Anthology ID:
- 2021.acl-tutorials.4
- Volume:
- Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing: Tutorial Abstracts
- Month:
- August
- Year:
- 2021
- Address:
- Online
- Editors:
- David Chiang, Min Zhang
- Venues:
- ACL | IJCNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 21–25
- Language:
- URL:
- https://aclanthology.org/2021.acl-tutorials.4
- DOI:
- 10.18653/v1/2021.acl-tutorials.4
- Cite (ACL):
- Mingxuan Wang and Lei Li. 2021. Pre-training Methods for Neural Machine Translation. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing: Tutorial Abstracts, pages 21–25, Online. Association for Computational Linguistics.
- Cite (Informal):
- Pre-training Methods for Neural Machine Translation (Wang & Li, ACL-IJCNLP 2021)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-1/2021.acl-tutorials.4.pdf