Beyond Error Propagation in Neural Machine Translation: Characteristics of Language Also Matter

Lijun Wu, Xu Tan, Di He, Fei Tian, Tao Qin, Jianhuang Lai, Tie-Yan Liu

[How to correct problems with metadata yourself]


Abstract
Neural machine translation usually adopts autoregressive models and suffers from exposure bias as well as the consequent error propagation problem. Many previous works have discussed the relationship between error propagation and the accuracy drop (i.e., the left part of the translated sentence is often better than its right part in left-to-right decoding models) problem. In this paper, we conduct a series of analyses to deeply understand this problem and get several interesting findings. (1) The role of error propagation on accuracy drop is overstated in the literature, although it indeed contributes to the accuracy drop problem. (2) Characteristics of a language play a more important role in causing the accuracy drop: the left part of the translation result in a right-branching language (e.g., English) is more likely to be more accurate than its right part, while the right part is more accurate for a left-branching language (e.g., Japanese). Our discoveries are confirmed on different model structures including Transformer and RNN, and in other sequence generation tasks such as text summarization.
Anthology ID:
D18-1396
Volume:
Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing
Month:
October-November
Year:
2018
Address:
Brussels, Belgium
Editors:
Ellen Riloff, David Chiang, Julia Hockenmaier, Jun’ichi Tsujii
Venue:
EMNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
3602–3611
Language:
URL:
https://aclanthology.org/D18-1396
DOI:
10.18653/v1/D18-1396
Bibkey:
Cite (ACL):
Lijun Wu, Xu Tan, Di He, Fei Tian, Tao Qin, Jianhuang Lai, and Tie-Yan Liu. 2018. Beyond Error Propagation in Neural Machine Translation: Characteristics of Language Also Matter. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 3602–3611, Brussels, Belgium. Association for Computational Linguistics.
Cite (Informal):
Beyond Error Propagation in Neural Machine Translation: Characteristics of Language Also Matter (Wu et al., EMNLP 2018)
Copy Citation:
PDF:
https://preview.aclanthology.org/teach-a-man-to-fish/D18-1396.pdf
Attachment:
 D18-1396.Attachment.pdf
Video:
 https://preview.aclanthology.org/teach-a-man-to-fish/D18-1396.mp4