An Empirical Study of Encoders and Decoders in Graph-Based Dependency Parsing

doi:10.1109/ACCESS.2020.2974109

	An Empirical Study of Encoders and Decoders in Graph-Based Dependency Parsing
	Ge Wang1,2,3 ; Ziyuan Hu1 ; Zechuan Hu1 ; Kewei Tu1
	2020
发表期刊	IEEE ACCESS
ISSN	2169-3536
卷号	8
DOI	10.1109/ACCESS.2020.2974109
摘要	Graph-based dependency parsing consists of two steps: first, an encoder produces a feature representation for each parsing substructure of the input sentence, which is then used to compute a score for the substructure; and second, a decoder finds the parse tree whose substructures have the largest total score. Over the past few years, powerful neural techniques have been introduced into the encoding step which substantially increases parsing accuracies. However, advanced decoding techniques, in particular high-order decoding, have seen a decline in usage. It is widely believed that contextualized features produced by neural encoders can help capture high-order decoding information and hence diminish the need for a high-order decoder. In this paper, we empirically evaluate the combinations of different neural and non-neural encoders with first- and second-order decoders and provide a comprehensive analysis about the effectiveness of these combinations with varied training data sizes. We find that: first, when there is large training data, a strong neural encoder with first-order decoding is sufficient to achieve high parsing accuracy and only slightly lags behind the combination of neural encoding and second-order decoding; second, with small training data, a non-neural encoder with a second-order decoder outperforms the other combinations in most cases.
URL	查看原文
收录类别	SCI ; EI ; SCIE
来源库	IEEE
引用统计
文献类型	期刊论文
条目标识符	https://kms.shanghaitech.edu.cn/handle/2MSLDSTB/114832
专题	信息科学与技术学院_博士生信息科学与技术学院_PI研究组_屠可伟组信息科学与技术学院_硕士生信息科学与技术学院_本科生
作者单位	1.School of Information Science and Technology, ShanghaiTech University, Shanghai, China 2.Shanghai Institute of Microsystem and Information Technology, Chinese Academy of Sciences, Shanghai, China 3.University of Chinese Academy of Sciences, Beijing, China
第一作者单位	信息科学与技术学院
第一作者的第一单位	信息科学与技术学院
推荐引用方式 GB/T 7714	Ge Wang,Ziyuan Hu,Zechuan Hu,et al. An Empirical Study of Encoders and Decoders in Graph-Based Dependency Parsing[J]. IEEE ACCESS,2020,8.
APA	Ge Wang,Ziyuan Hu,Zechuan Hu,&Kewei Tu.(2020).An Empirical Study of Encoders and Decoders in Graph-Based Dependency Parsing.IEEE ACCESS,8.
MLA	Ge Wang,et al."An Empirical Study of Encoders and Decoders in Graph-Based Dependency Parsing".IEEE ACCESS 8(2020).