话题性话语标记的自动识别与分类  

Automatic Identification and Classification of Topical Discourse Markers

作　　者：杨进才[1] 余漠洋 胡满 肖明[2] YANG Jincai;YU Moyang;HU Man;XIAO Ming(School of Computer Science,Central China Normal University,Wuhan 430079,China;Research Center for Language and Language Education,Central China Normal University,Wuhan 430079,China)

机构地区：[1]华中师范大学计算机学院,武汉430079 [2]华中师范大学语言与语言教育研究中心,武汉430079

出　　处：《计算机科学》2025年第4期255-261,共7页Computer Science

基　　金：国家社会科学基金(19BYY092);教育部人文社科规划基金(20YJA740047)。

摘　　要：话语标记(Discourse Markers)是一种语言标记,具有组织语篇、引导指意、显示情感的作用,因而受到语言学界的广泛关注。对话语标记及其类别的准确识别,对于篇章理解、说话人意图和情感的把握有重要作用。近十年来,国内外学者对话语标记的功能、特征、来源和系统分类展开研究并取得了丰富的成果。然而,因话语标记形式多变、来源多样、特征抽象、变体繁多,机器自动识别的难度较大。对此,以话题性话语标记为研究对象,提出一种融合外部语言学特征的NFLAT指针网络模型,实现对语篇中话语标记的自动识别和分类。经实验检验,训练后模型对话题性话语标记的识别及分类精确率(P值)达94.55%。Discourse markers,a kind of linguistic markers at the pragmatic level which have functions of organizing discourse,guiding signifier,and expressing emotions,have attracted extensive attention in linguistics.The accurate identification of discourse markers and categories plays an important role in the comprehension of text and the grasp of the speaker’s intention and emotion.In the past decade,scholars at home and abroad have conducted research on function,characteristics,sources and systematic classification of discourse markers and achieved rich results.However,due to the changeable forms,diverse sources,abstract features,and variants,it is difficult for machines to automatically identify discourse markers.In this paper,an NFLAT pointer network model integrating external linguistic features is proposed,which takes topical discourse markers as the research object,and realizes the automatic recognition and classification of discourse markers in discourse.Experimental results show that the precision of the trained model for the recognition and classification of topical discourse markers reaches 94.55%.

关 键 词：话语标记 语义增强 特征融合 自动识别与分类 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]