Learning Generalized Features for Semantic Role Labeling

doi:10.1145/2890496

CASIA OpenIR > 多模态人工智能系统全国重点实验室 > 自然语言处理

	Learning Generalized Features for Semantic Role Labeling
	Yang, Haitong; Zong, Chengqing
发表期刊	ACM TRANSACTIONS ON ASIAN AND LOW-RESOURCE LANGUAGE INFORMATION PROCESSING
	2016-06-01
卷号	15 期号:4 页码:28:1-28:16
文章类型	Article
摘要	This article makes an effort to improve Semantic Role Labeling (SRL) through learning generalized features. The SRL task is usually treated as a supervised problem. Therefore, a huge set of features are crucial to the performance of SKL systems. But these features often lack generalization powers when predicting an unseen argument. This article proposes a simple approach to relieve the issue. A strong intuition is that arguments occurring in similar syntactic positions are likely to bear the same semantic role, and, analogously, arguments that are lexically similar are likely to represent the same semantic role. Therefore, it will be informative to SRL if syntactic or lexical similar arguments can activate the same feature. Inspired by this, we embed the information of lexicalization and syntax into a feature vector for each argument and then use K -means to make clustering for all feature vectors of training set. For an unseen argument to be predicted, it will belong: to the same cluster as its similar arguments of training set. Therefore, the clusters can be thought of as a kind of generalized feature. We evaluate our method on several benchmarks. The experimental results show that our approach can significantly improve the SRL performance.
关键词	Algorithms Languages Experimentation Performance Semantic Role Labeling Generalized Features Similar Arguments K-means
WOS标题词	Science & Technology ; Technology
DOI	10.1145/2890496
收录类别	SCI
语种	英语
WOS研究方向	Computer Science
WOS类目	Computer Science, Artificial Intelligence
WOS记录号	WOS:000377298900008
引用统计	被引频次：6[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/40821
专题	多模态人工智能系统全国重点实验室_自然语言处理
通讯作者	Zong, Chengqing
推荐引用方式 GB/T 7714	Yang, Haitong,Zong, Chengqing. Learning Generalized Features for Semantic Role Labeling[J]. ACM TRANSACTIONS ON ASIAN AND LOW-RESOURCE LANGUAGE INFORMATION PROCESSING,2016,15(4):28:1-28:16.
APA	Yang, Haitong,&Zong, Chengqing.(2016).Learning Generalized Features for Semantic Role Labeling.ACM TRANSACTIONS ON ASIAN AND LOW-RESOURCE LANGUAGE INFORMATION PROCESSING,15(4),28:1-28:16.
MLA	Yang, Haitong,et al."Learning Generalized Features for Semantic Role Labeling".ACM TRANSACTIONS ON ASIAN AND LOW-RESOURCE LANGUAGE INFORMATION PROCESSING 15.4(2016):28:1-28:16.