CASIA OpenIR  > 模式识别国家重点实验室  > 自然语言处理
Addressing the Under-translation Problem from the Entropy Perspective
Zhao, Yang1; Zhang, Jiajun1; Zong, Chengqing1; He, Zhongjun2; Wu, Hua2
Conference NameAAAI
Conference Date2019
Conference PlaceHonolulu, Hawaii, USA

Neural Machine Translation (NMT) has drawn much attention
due to its promising translation performance in recent
years. However, the under-translation problem still remains a
big challenge. In this paper, we focus on the under-translation
problem and attempt to find out what kinds of words are
more likely to be ignored. Through analysis, we observe that
a source word with a larger translation entropy is more inclined
to be dropped. To address this problem, we proposed
a coarse-to-fine framework, in which we first introduce a
simple strategy to reduce the entropy of high-entropy words
through constructing the pseudo target sentences. Then we
propose three methods, including pre-training method, multitask
method and two-pass method, to encourage the neural
model to focus on these high-entropy words. Experimental
results on various translation tasks show that our method can
significantly improve the translation quality and substantially
reduce the under-translation cases of high-entropy words.

Document Type会议论文
First Author AffilicationInstitute of Automation, Chinese Academy of Sciences
Recommended Citation
GB/T 7714
Zhao, Yang,Zhang, Jiajun,Zong, Chengqing,et al. Addressing the Under-translation Problem from the Entropy Perspective[C],2019.
Files in This Item: Download All
File Name/Size DocType Version Access License
AAAI-ZhaoY.2930.pdf(483KB)会议论文 开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Zhao, Yang]'s Articles
[Zhang, Jiajun]'s Articles
[Zong, Chengqing]'s Articles
Baidu academic
Similar articles in Baidu academic
[Zhao, Yang]'s Articles
[Zhang, Jiajun]'s Articles
[Zong, Chengqing]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Zhao, Yang]'s Articles
[Zhang, Jiajun]'s Articles
[Zong, Chengqing]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: AAAI-ZhaoY.2930.pdf
Format: Adobe PDF
All comments (0)
No comment.

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.