基于框架语义和图结构的阅读理解答案抽取方法  

Answer Extraction Method for Reading Comprehension Based on Frame Semantics and GraphStructure

作　　者：杨陟卓[1] 许玲玲 张虎[1] 李茹[1,2] YANG Zhizhuo;XU Lingling;Zhang Hu;LI Ru(School of Computer and Information Technology,Shanxi University,Taiyuan 030006,China;Key Laboratory of Computational Intelligence and Chinese Information Processing of Ministry of Education,Shanxi University,Taiyuan 030006,China)

机构地区：[1]山西大学计算机与信息技术学院,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,太原030006

出　　处：《计算机科学》2023年第8期170-176,共7页Computer Science

基　　金：国家自然科学基金(61936012,62176145);山西省基础研究计划项目面上基金项目(20210302123469)。

摘　　要：机器阅读理解是自然语言处理领域最具挑战性的任务之一。随着深度学习技术的不断发展以及大规模MRC数据集的发布,机器阅读理解模型的性能不断刷新记录。但是以往的模型在逻辑推理、深层语义理解等方面仍存在不足。为解决上述问题,提出了一种基于框架语义和图结构的阅读理解答案抽取方法。该方法首先利用汉语框架网匹配与问句语义相关的候选句;其次提取问题和候选句中的实体,以实体在句子中的依存句法和语义关系构建实体关系图;最后将实体关系图引入图注意网络进行逻辑推理,实现阅读理解答案抽取。在DuReader-robust数据集上的实验结果表明,所提方法取得了比基线模型更好的效果。Machine reading comprehension is one of the most challenging tasks in the field of natural language processing.With the continuous development of deep learning technology and the release of large-scale MRC datasets,the performance of MRC models keep breaking records.However,the previous models still have shortcomings in logical reasoning and deep semantic understanding.In order to solve the above problems,this paper proposes a reading comprehension answer extraction method based on frame semantics and graph structure.This method first uses Chinese FrameNet to match candidate sentences related to question semantics.Secondly,the entities in the questions and candidate sentences are extracted,and the entity relationship graph is constructed based on the dependent syntax and semantic relationships of entities in the sentences.Finally,the entity relationship graph is introduced into the graph attention network for logical reasoning,so as to realize the extraction of reading comprehension answers.Experiment results on Dureader-robust dataset show that the proposed method achieves better results than the baseline model.

关 键 词：机器阅读理解 CFN 实体关系图 图注意网络 句法关系 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]