Predicting and Using Target Length in Neural Machine Translation

Zijian Yang, Yingbo Gao, Weiyue Wang, Hermann Ney


Abstract
Attention-based encoder-decoder models have achieved great success in neural machine translation tasks. However, the lengths of the target sequences are not explicitly predicted in these models. This work proposes length prediction as an auxiliary task and set up a sub-network to obtain the length information from the encoder. Experimental results show that the length prediction sub-network brings improvements over the strong baseline system and that the predicted length can be used as an alternative to length normalization during decoding.
Anthology ID:
2020.aacl-main.41
Volume:
Proceedings of the 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 10th International Joint Conference on Natural Language Processing
Month:
December
Year:
2020
Address:
Suzhou, China
Editors:
Kam-Fai Wong, Kevin Knight, Hua Wu
Venue:
AACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
389–395
Language:
URL:
https://preview.aclanthology.org/build-pipeline-with-new-library/2020.aacl-main.41/
DOI:
10.18653/v1/2020.aacl-main.41
Bibkey:
Cite (ACL):
Zijian Yang, Yingbo Gao, Weiyue Wang, and Hermann Ney. 2020. Predicting and Using Target Length in Neural Machine Translation. In Proceedings of the 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 10th International Joint Conference on Natural Language Processing, pages 389–395, Suzhou, China. Association for Computational Linguistics.
Cite (Informal):
Predicting and Using Target Length in Neural Machine Translation (Yang et al., AACL 2020)
Copy Citation:
PDF:
https://preview.aclanthology.org/build-pipeline-with-new-library/2020.aacl-main.41.pdf