中英双语政治论辩挖掘任务数据集建设  

Building Chinese-English Bilingual Dataset for Political Argument Mining Tasks

作　　者：张霄军 周静狮 ZHANG Xiaojun;ZHOU Jingshi(School of Humanities and Social Sciences,Xi an Jiaotong-Liverpool University,Suzhou,Jiangsu 215123,China;Guangdong Provincial Key Laboratory of Novel Security Intelligence Technologies,Shenzhen,Guangdong 518055,China;School of Advanced Technology,Xi’an Jiaotong-Liverpool University,Suzhou,Jiangsu 215123,China)

机构地区：[1]西交利物浦大学人文社科学院,江苏苏州215123 [2]广东省安全智能新技术重点实验室,广东深圳518055 [3]西交利物浦大学智能工程学院,江苏苏州215123

出　　处：《中文信息学报》2023年第10期167-174,共8页Journal of Chinese Information Processing

基　　金：西交利物浦大学科研发展基金(RDF-22-01-053);广东省安全智能新技术重点实验室开放课题基金(2022B1212010005)。

摘　　要：受制于训练语料资源稀缺,中文论辩挖掘在政治领域的研究才刚刚起步。外交辞令、外事问答以及外宣公告都蕴含着丰富而微妙的政治论辩技巧,在外交领域开展政治论辩挖掘研究具有现实意义和应用价值。该文从在建的“多语外交对话语料库”得到启发,选取部分语料进行政治论辩观点标注、论辩关系标注和论辩句情感分析,初步建成了包含200篇外交部例行记者会实录中英文文本、1536个话轮的中英双语政治论辩挖掘任务数据集BiDAM,并以示例的形式展示了该数据集的可用性。It is the scarcity of dataset that obstacles the development of political argument mining research in China.Diplomatic texts,as the typical form of political genre,demonstrate more vivid but logic debating skills and deserve more attention in argument mining tasks.Inspired by a corpus building for multilingual diplomatic dialogue texts,we select 200 transcribed texts for each Chinese and English Press Regular Conferences,which can be split into 1,536 diplomatic Q/A turns.We annotate Claims,Premises and their relations so that a Chinese-English bilingual dataset for political argument miming tasks(BiDAM)is constructed.We also make the sentiment analysis for each extracted argument for the further studies.

关 键 词：政治论辩 多语外交对话语料库 跨语言论辩挖掘 论辩挖掘任务数据集 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]