Enhancing Lexical Translation Consistency for Document-Level Neural Machine Translation

doi:10.1145/3485469

CORC > 自动化研究所 > 中国科学院自动化研究所 > 模式识别国家重点实验室 > 自然语言处理

	Enhancing Lexical Translation Consistency for Document-Level Neural Machine Translation
	Kang, Xiaomian 2,3; Zhao, Yang 2,3; Zhang, Jiajun 2,3; Zong, Chengqing 1,2
刊名	ACM TRANSACTIONS ON ASIAN AND LOW-RESOURCE LANGUAGE INFORMATION PROCESSING
	2022-05-01
卷号	21 期号:3 页码:21
关键词	Document-level translation neural machine translation lexical consistency discourse phenomena
ISSN号	2375-4699
DOI	10.1145/3485469
通讯作者	Kang, Xiaomian(xiaomian.kang@nlpr.ia.ac.cn)
英文摘要	Document-level neural machine translation (DocNMT) has yielded attractive improvements. In this article, we systematically analyze the discourse phenomena in Chinese-to-English translation, and focus on the most obvious ones, namely lexical translation consistency. To alleviate the lexical inconsistency, we propose an effective approach that is aware of the words which need to be translated consistently and constrains themodel to produce more consistent translations. Specifically, we first introduce a global context extractor to extract the document context and consistency context, respectively. Then, the two types of global context are integrated into a encoder enhancer and a decoder enhancer to improve the lexical translation consistency. We create a test set to evaluate the lexical consistency automatically. Experiments demonstrate that our approach can significantly alleviate the lexical translation inconsistency. In addition, our approach can also substantially improve the translation quality compared to sentence-level Transformer.
资助项目	Natural Science Foundation of China[62006224]
WOS研究方向	Computer Science
语种	英语
出版者	ASSOC COMPUTING MACHINERY
WOS记录号	WOS:000778450600017
资助机构	Natural Science Foundation of China
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/48261]
专题	模式识别国家重点实验室_自然语言处理
通讯作者	Kang, Xiaomian
作者单位	1.Chinese Acad Sci, Inst Automat, CAS Ctr Excellence Brain Sci & Intelligence Techn, Natl Lab Pattern Recognit, Beijing, Peoples R China 2.Univ Chinese Acad Sci, Sch Artificial Intelligence, Intelligence Bldg,95 Zhongguancun East Rd, Beijing 100190, Peoples R China 3.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Intelligence Bldg,95 Zhongguancun East Rd, Beijing 100190, Peoples R China
推荐引用方式 GB/T 7714	Kang, Xiaomian,Zhao, Yang,Zhang, Jiajun,et al. Enhancing Lexical Translation Consistency for Document-Level Neural Machine Translation[J]. ACM TRANSACTIONS ON ASIAN AND LOW-RESOURCE LANGUAGE INFORMATION PROCESSING,2022,21(3):21.
APA	Kang, Xiaomian,Zhao, Yang,Zhang, Jiajun,&Zong, Chengqing.(2022).Enhancing Lexical Translation Consistency for Document-Level Neural Machine Translation.ACM TRANSACTIONS ON ASIAN AND LOW-RESOURCE LANGUAGE INFORMATION PROCESSING,21(3),21.
MLA	Kang, Xiaomian,et al."Enhancing Lexical Translation Consistency for Document-Level Neural Machine Translation".ACM TRANSACTIONS ON ASIAN AND LOW-RESOURCE LANGUAGE INFORMATION PROCESSING 21.3(2022):21.