SemFace: Pre-training Encoder and Decoder with a Semantic Interface for Neural Machine Translation
Shuo Ren, Long Zhou, Shujie Liu, Furu Wei, Ming Zhou, Shuai Ma
Abstract
While pre-training techniques are working very well in natural language processing, how to pre-train a decoder and effectively use it for neural machine translation (NMT) still remains a tricky issue. The main reason is that the cross-attention module between the encoder and decoder cannot be pre-trained, and the combined encoder-decoder model cannot work well in the fine-tuning stage because the inputs of the decoder cross-attention come from unknown encoder outputs. In this paper, we propose a better pre-training method for NMT by defining a semantic interface (SemFace) between the pre-trained encoder and the pre-trained decoder. Specifically, we propose two types of semantic interfaces, including CL-SemFace which regards cross-lingual embeddings as an interface, and VQ-SemFace which employs vector quantized embeddings to constrain the encoder outputs and decoder inputs in the same language-independent space. We conduct massive experiments on six supervised translation pairs and three unsupervised pairs. Experimental results demonstrate that our proposed SemFace can effectively connect the pre-trained encoder and decoder, and achieves significant improvement by 3.7 and 1.5 BLEU points on the two tasks respectively compared with previous pre-training-based NMT models.- Anthology ID:
- 2021.acl-long.348
- Volume:
- Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
- Month:
- August
- Year:
- 2021
- Address:
- Online
- Venues:
- ACL | IJCNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 4518–4527
- Language:
- URL:
- https://aclanthology.org/2021.acl-long.348
- DOI:
- 10.18653/v1/2021.acl-long.348
- Cite (ACL):
- Shuo Ren, Long Zhou, Shujie Liu, Furu Wei, Ming Zhou, and Shuai Ma. 2021. SemFace: Pre-training Encoder and Decoder with a Semantic Interface 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 (Volume 1: Long Papers), pages 4518–4527, Online. Association for Computational Linguistics.
- Cite (Informal):
- SemFace: Pre-training Encoder and Decoder with a Semantic Interface for Neural Machine Translation (Ren et al., ACL-IJCNLP 2021)
- PDF:
- https://preview.aclanthology.org/remove-xml-comments/2021.acl-long.348.pdf