一种无指导的隐式篇章关系推理方法研究

该文提出一种基于信息检索的无指导方法,用于推理隐式篇章片段之间的语义连接关系,如因果关系、转折关系等。该文基于Google搜索引擎,抽取在句子结构以及语义层面上均与原隐式片段相似的显式片段,通过分析和识别相关显式关系来间接推理隐式关系。主要包括以下三个模块 构建高质量查询关键词并抽取候选显式关系;结合三种隐式关系推理模型(相似度、置信度、关联度),综合考察查询关键词以及候选关系的质量;基于排序学习的方法,统计高质量候选关系中的类别分布以实现最终隐式关系的推理。该文采用Penn Discourse TreeBank 2.0篇章语料库,最终方法精确率达到54.3%,与有指导的方法相比,提高了约14.3%。

An Unsupervised Approach to Inferring Implicit Discourse Relation

In this paper, we propose an unsupervised approach to inferring implicit discourse relation (i.e. relation such as contingency or comparison that is not marked with a connective) based on information retrieval. With Google search engine, we extract candidate explicit relations which are similar to implicit relation on syntactic and semantic levels. These explicit relations which have achieved high accuracy are used to infer implicit relation. The proposed approach contains three modulesfirstly, we construct high-quality queries and extract candidate explicit relations; then three inference models (Similarity, Confidence, Relevance) are presented to evaluate the quality of queries and candidate relations; and finally, base on learning to rank candidate relations, we acquire the statistics of discourse senses distribution to realize the prediction of implicit discourse relation. Experimental results on the PDTB 2.0 show the accuracy of 54.3%, which is a significant improvement of 14.3% over the supervised system.
Key wordsimplicit discourse relation; unsupervised; information retrieval; PDTB 2.0