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.
作者
王晓晖
李茹
王智强
柴清华
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)
出处
《中文信息学报》
CSCD
北大核心
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)。