How Length Prediction Influence the Performance of Non-Autoregressive Translation?

Minghan Wang, Guo Jiaxin, Yuxia Wang, Yimeng Chen, Su Chang, Hengchao Shang, Min Zhang, Shimin Tao, Hao Yang


Abstract
Length prediction is a special task in a series of NAT models where target length has to be determined before generation. However, the performance of length prediction and its influence on translation quality has seldom been discussed. In this paper, we present comprehensive analyses on length prediction task of NAT, aiming to find the factors that influence performance, as well as how it associates with translation quality. We mainly perform experiments based on Conditional Masked Language Model (CMLM) (Ghazvininejad et al., 2019), a representative NAT model, and evaluate it on two language pairs, En-De and En-Ro. We draw two conclusions: 1) The performance of length prediction is mainly influenced by properties of language pairs such as alignment pattern, word order or intrinsic length ratio, and is also affected by the usage of knowledge distilled data. 2) There is a positive correlation between the performance of the length prediction and the BLEU score.
Anthology ID:
2021.blackboxnlp-1.14
Volume:
Proceedings of the Fourth BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP
Month:
November
Year:
2021
Address:
Punta Cana, Dominican Republic
Venue:
BlackboxNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
205–213
Language:
URL:
https://aclanthology.org/2021.blackboxnlp-1.14
DOI:
10.18653/v1/2021.blackboxnlp-1.14
Bibkey:
Cite (ACL):
Minghan Wang, Guo Jiaxin, Yuxia Wang, Yimeng Chen, Su Chang, Hengchao Shang, Min Zhang, Shimin Tao, and Hao Yang. 2021. How Length Prediction Influence the Performance of Non-Autoregressive Translation?. In Proceedings of the Fourth BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP, pages 205–213, Punta Cana, Dominican Republic. Association for Computational Linguistics.
Cite (Informal):
How Length Prediction Influence the Performance of Non-Autoregressive Translation? (Wang et al., BlackboxNLP 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.blackboxnlp-1.14.pdf