基于Self-Attention的句法感知汉语框架语义角色标注  

Syntax-Aware Chinese Frame Semantic Role Labeling Based on Self-Attention

作　　者：王晓晖 李茹[1,2] 王智强 柴清华[4] 韩孝奇 WANG Xiaohui;LI Ru;WANG Zhiqiang;CHAI Qinghua;HAN Xiaoqi(School of Computer and Information Technology,Shanxi University,Taiyuan,Shanxi 030006,China;Key Laboratory of Ministry of Education for Computational Intelligenceand Chinese Information Processing,Shanxi University,Taiyuan,Shanxi 030006,China;Institute of Intelligent Information Processing,Shanxi University,Taiyuan,Shanxi 030006,China;School of Foreign Languages,Shanxi University,Taiyuan,Shanxi 030006,China)

机构地区：[1]山西大学计算机与信息技术学院,山西太原030006 [2]山西大学计算智能与中文信息处理教育部重点实验室,山西太原030006 [3]山西大学智能信息处理研究所,山西太原030006 [4]山西大学外国语学院,山西太原030006

出　　处：《中文信息学报》2022年第10期38-44,共7页Journal of Chinese Information Processing

基　　金：国家自然科学基金(61772324,61936012)。

摘　　要：框架语义角色标注(Frame Semantic Role Labeling,FSRL)是基于FrameNet标注体系的语义分析任务。语义角色标注通常对句法有很强的依赖性,目前的语义角色标注模型大多基于双向长短时记忆网络Bi-LSTM,虽然可以获取句子中的长距离依赖信息,但无法很好地获取句子中的句法信息。因此,引入Self-Attention机制来捕获句子中每个词的句法信息。实验结果表明,该模型在CFN(Chinese FrameNet,汉语框架网)数据集上的F_(1)值得到了提升,证明了融入self-attention机制可以改进汉语框架语义角色标注模型的性能。Frame semantic role labeling is a semantic analysis task based on theFrameNet.Semantic role labeling usually has a strong dependence on syntax.Most of the current semantic role labeling models are based on Bi-LSTM,which can obtain the long-distance dependency information in sentences,but cannot obtain the syntactic information in sentences well.In this paper,we iimental results show that the F_(1) of the model on the CFN(Chinese FrameNet)dataset has been improved,which proves that the self-attention mechanism can improve the performance of the Chinese frame semantic role labeling model.

关 键 词：语义角色标注 自注意力机制 双向长短时记忆网络 汉语框架网 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]