Semantic Role Labeling Utilizing Valence Information

YUAN Li-chi

doi:10.3969/j.issn.0372-2112.2017.10.031

您当前的位置：

首页 >

文章列表页 >

Semantic Role Labeling Utilizing Valence Information

更新时间：2025-07-16

- Semantic Role Labeling Utilizing Valence Information
- Acta Electronica Sinica Vol. 45, Issue 10, Pages: 2533-2539(2017)
- 作者机构：
  
  1. 江西财经大学信息管理学院,江西,南昌,330013
  2. 江西财经大学信息管理学院,江西,南昌,330013
- 作者简介：
- 基金信息：
- DOI：10.3969/j.issn.0372-2112.2017.10.031
  CLC： TP391.1
- Published：2017
- 稿件说明：
移动端阅览
YUAN Li-chi. Semantic Role Labeling Utilizing Valence Information[J]. Acta Electronica Sinica, 2017, 45(10): 2533-2539.
DOI：

YUAN Li-chi. Semantic Role Labeling Utilizing Valence Information[J]. Acta Electronica Sinica, 2017, 45(10): 2533-2539. DOI： 10.3969/j.issn.0372-2112.2017.10.031.

摘要

语义角色标注是一种浅层语义分析.现有的汉语语义分析方法和语义角色标注体系没有结合汉语的特点并有效刻画出汉语的本质特性，导致目前汉语语义角色标注性能与英语相比相差较大.在汉语中，配价结构可以较好地刻画汉语句子的句法结构和语义构成关系，因此，我们在考察配价语法的基础上适当修改了语义角色标注体系并将谓词本身的配价信息融入语义角色标注.实验结果表明，配价信息的使用能够较大幅度提高动名词性谓词的语义角色标注性能：基于正确句法树和正确谓词识别，动词性谓词的SRL性能F1值达到93.69%；名词性谓词的SRL性能F1值达到79.23% ；均优于目前国内外的同类系统.

Abstract

Semantic roles labeling is a kind of shallow semantic analysis.Existing Chinese semantic analysis methods and semantic roles labeling systems do not effectively characterize Chinese essential features

and it causes the currently larger difference between Chinese SRL systems and English SRL systems.Valence structures can better characterize syntactic structures and semantic constitution relations of Chinese sentences

so we appropriately modified the semantic roles labeling systems and incorporated the valence information of predicates into semantic roles labeling.Experimental results show that proper use of valence information significantly improves the performance of semantic roles labeling system:the verbal SRL approach achieves the performance of 93.69% in F1-measure and the nominal SRL approach achieves the performance of 79.23% in F1-measure on golden parse trees and golden predicates

and all outperform the state-of-the-art SRL systems.

关键词

Keywords

references

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

A Statistical Parsing Model Based on Valence Structure and Semantic Dependency

A Chinese Textual Entailment Recognition Method Incorporating Semantic Role and Self-Attention

Related Author

YUAN Li-chi

ZHANG Zhi-chang

ZENG Yang-yang

PANG Ya-li

Related Institution

Jiangxi Key Laboratory of Data and Knowledge Engineering, Jiangxi University of Finance and Economics

School of Information Technology Jiangxi University of Finance and Economics Nanchang China

Jiangxi Key Laboratory of Data and Knowledge Engineering Jiangxi University of Finance and Economics Nanchang China

College of Computer Science and Engineering, Northwest Normal University

⁰