Soft Contextual Data Augmentation for Neural Machine Translation

Fei Gao, Jinhua Zhu, Lijun Wu, Yingce Xia, Tao Qin, Xueqi Cheng, Wengang Zhou, Tie-Yan Liu


Abstract
While data augmentation is an important trick to boost the accuracy of deep learning methods in computer vision tasks, its study in natural language tasks is still very limited. In this paper, we present a novel data augmentation method for neural machine translation. Different from previous augmentation methods that randomly drop, swap or replace words with other words in a sentence, we softly augment a randomly chosen word in a sentence by its contextual mixture of multiple related words. More accurately, we replace the one-hot representation of a word by a distribution (provided by a language model) over the vocabulary, i.e., replacing the embedding of this word by a weighted combination of multiple semantically similar words. Since the weights of those words depend on the contextual information of the word to be replaced, the newly generated sentences capture much richer information than previous augmentation methods. Experimental results on both small scale and large scale machine translation data sets demonstrate the superiority of our method over strong baselines.
Anthology ID:
P19-1555
Volume:
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
Month:
July
Year:
2019
Address:
Florence, Italy
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
5539–5544
Language:
URL:
https://aclanthology.org/P19-1555
DOI:
10.18653/v1/P19-1555
Bibkey:
Cite (ACL):
Fei Gao, Jinhua Zhu, Lijun Wu, Yingce Xia, Tao Qin, Xueqi Cheng, Wengang Zhou, and Tie-Yan Liu. 2019. Soft Contextual Data Augmentation for Neural Machine Translation. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 5539–5544, Florence, Italy. Association for Computational Linguistics.
Cite (Informal):
Soft Contextual Data Augmentation for Neural Machine Translation (Gao et al., ACL 2019)
Copy Citation:
PDF:
https://aclanthology.org/P19-1555.pdf
Code
 teslacool/SCA
Terminologies: