融合词语语义与标签依赖的隐式篇章关系识别  

Fusing Word Semantics and Label Dependence for Implicit Discourse Relation Recognition

作　　者：吕国英[1] 郭校金 贾荣荣 LYU Guoying;GUO Xiaojin;JIA Rongrong(School of Computer&Information Technology,Shanxi University,Taiyuan 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

出　　处：《软件导刊》2024年第4期1-7,共7页Software Guide

基　　金：国家社会科学基金项目(18BYY009)。

摘　　要：中文隐式篇章关系识别旨在推断出两个论元间的篇章关系类型。然而,现有的方法往往忽略了论元中词语所蕴含的关键信息,并且仅考虑单个层级内的篇章关系类型,忽略了各层级间篇章关系的依赖关联。鉴于此,提出融合词语语义和标签依赖的方法,以序列生成的方式实现篇章关系识别,先根据相似度权重将词向量嵌入到字编码表示中,应用字词对齐注意力机制强调关键字、词信息,再采用标签注意力编码从蕴含词语语义的论元表示和篇章关系表示中获取篇章关系依赖性的上下文表示,以自下而上的方式预测顶层的篇章关系类型。此外,构建面向阅读理解篇章的篇章关系数据集,并在该数据集上展开实验,结果显示隐式篇章关系识别准确率和F1值分别达到74.19%和73.81%,最终验证了该方法的有效性。Chinese implicit discourse relationship recognition aims to infer the type of discourse relationship between two arguements.However,the existing methods often ignore the key information contained in the words in the argument,and only consider the types of discourse relationships within a single level,and ignore the dependent relationship between levels.Therefore,this paper proposes a method that integrates word semantics and label dependence to realize discourse relationship recognition by sequence generation.Firstly,the word vector is embedded in the character encoding representation according to the similarity weight,and the word alignment attention mechanism is applied to emphasize the keywords and word information.Then,label attention coding is used to obtain the contextual representation of discourse relationship dependence from the meta-representation and discourse relationship representation containing word semantics,and predict the top-level discourse relationship type in a bottom-up manner.In addition,this paper constructs a discourse relationship dataset for reading comprehension discourses,and experiments are carried out on this dataset,and the results show that the accuracy rate and F1 value of implicit discourse relationship recognition reach 74.19%and 73.81%,which finally verifies the effectiveness of the proposed method.

关 键 词：隐式篇章关系 词语语义 标签依赖 序列生成 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]