CASIA OpenIR  > 模式识别国家重点实验室  > 自然语言处理
Bilingual Semantic Role Labeling Inference via Dual Decomposition
Yang, Haitong1,2; Zhou, Yu1,2; Zong, Chengqing1,2; Zong Chengqing
Source PublicationACM TRANSACTIONS ON ASIAN AND LOW-RESOURCE LANGUAGE INFORMATION PROCESSING
2016-03-01
Volume15Issue:3Pages:15:1-15:21
SubtypeArticle
Abstract
; This article focuses on bilingual Semantic Role Labeling (SRL); its goal is to annotate semantic roles on both sides of the parallel bilingual texts (bi-texts). Since rich bilingual information is encoded, bilingual SRL has been applied in many natural-language processing (NLP) tasks such as machine translation (MT), cross-lingual information retrieval (IR), and the like. A feasible way of performing bilingual SRL is using monolingual SRL systems to perform SRL on each side of bi-texts separately. However, it is difficult to obtain consistent SRL results on both sides of bi-texts in this way. Some works have tried to jointly infer bilingual SRL because there are many complementary language cues on both sides of bi-texts and they reported better performance than monolingual systems. However, there are two limits in the existing methods. First, the existing methods often require high inference costs due to the complex objective function. Second, the existing methods fully adopt the candidates generated by monolingual SRL systems, but many candidates are discarded in the argument pruning or identification stage of monolingual systems. In this article, we propose two strategies to overcome these limits. We utilize a simple but efficient technique: Dual Decomposition to search for consistent results for both sides of bi-texts. On the other hand, we propose a method called Bi-Directional Projection (BDP) to recover arguments discarded in monolingual SRL systems.
KeywordAlgorithms Languages Experimentation Performance Semantic Role Labeling Bi-texts Lagrange Dual Decomposition Bi-directional Projection
WOS HeadingsScience & Technology ; Technology
DOI10.1145/2835493
Indexed BySCI
Language英语
Funding OrganizationNatural Science Foundation of China(61333018 ; West Light Foundation of Chinese Academy of Sciences(LHXZ201301) ; 61403379)
WOS Research AreaComputer Science
WOS SubjectComputer Science, Artificial Intelligence
WOS IDWOS:000373913600005
Citation statistics
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/11854
Collection模式识别国家重点实验室_自然语言处理
Corresponding AuthorZong Chengqing
Affiliation1.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100864, Peoples R China
2.Intelligence Bldg 95,Zhongguancun East Rd, Beijing 100190, Peoples R China
Recommended Citation
GB/T 7714
Yang, Haitong,Zhou, Yu,Zong, Chengqing,et al. Bilingual Semantic Role Labeling Inference via Dual Decomposition[J]. ACM TRANSACTIONS ON ASIAN AND LOW-RESOURCE LANGUAGE INFORMATION PROCESSING,2016,15(3):15:1-15:21.
APA Yang, Haitong,Zhou, Yu,Zong, Chengqing,&Zong Chengqing.(2016).Bilingual Semantic Role Labeling Inference via Dual Decomposition.ACM TRANSACTIONS ON ASIAN AND LOW-RESOURCE LANGUAGE INFORMATION PROCESSING,15(3),15:1-15:21.
MLA Yang, Haitong,et al."Bilingual Semantic Role Labeling Inference via Dual Decomposition".ACM TRANSACTIONS ON ASIAN AND LOW-RESOURCE LANGUAGE INFORMATION PROCESSING 15.3(2016):15:1-15:21.
Files in This Item: Download All
File Name/Size DocType Version Access License
a15-yang.pdf(624KB)期刊论文作者接受稿开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Yang, Haitong]'s Articles
[Zhou, Yu]'s Articles
[Zong, Chengqing]'s Articles
Baidu academic
Similar articles in Baidu academic
[Yang, Haitong]'s Articles
[Zhou, Yu]'s Articles
[Zong, Chengqing]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Yang, Haitong]'s Articles
[Zhou, Yu]'s Articles
[Zong, Chengqing]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: a15-yang.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

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