融入法律知识的问句匹配

Incorporating Legal Knowledge into Question Matching

问句匹配是问答系统的重要任务,当前方法通常采用神经网络建模两个句子的语义匹配程度.但是,在法律领域中,问句常存在文本表征稀疏、法律词的专业性较强、句子蕴含法律知识不足等问题.因此,通用领域的深度学习文本匹配模型在法律问句匹配任务上效果并不好.为了让模型更好的理解法律问句的含义、建模法律领域知识,首先构建一个法律领域知识库,在此基础上提出一种融合法律领域知识(如法律词汇和法律法条)的问句匹配模型.具体地,构建了合同纠纷、离婚、交通事故、劳动工伤、债务债权等5种法律纠纷类别下的法律词典,并且收集了相关法律法条,构建法律领域知识库.在问句匹配中,首先查询法律知识库检索问句对所对应的法律词汇和法律法条,进而通过交叉关注模型同时建模问句、法律词汇、法律法条三者之间的关联,最终实现更精准的问句匹配,在多个法律类别下的实验表明提出的方法能有效提升问句匹配性能.

Question matching is an important task of question answering systems.Current methods usually use neural networks to model the semantic matching degree of two sentences.However,in the field of law,questions often have some problems,such as sparse textual representation,professional legal words,and insufficient legal knowledge contained in sentences.Therefore,the general domain deep learning text matching model is not effective in the legal question matching task.In order to make the model better understand the meaning of legal questions and model the knowledge of the legal field,this study firstly constructs a knowledge base of the legal field,and then proposes a question matching model integrating the knowledge of the legal field(such as legal words and statutes).Specifically,a legal dictionary under five categories of legal disputes has been constructed,including contract dispute,divorce,traffic accident,labor injury,debt and creditor’s right,and relevant legal articles have been collected to build a knowledge base in the legal field.In question matching,the legal knowledge base is first searched for the legal words and statutes corresponding to the question pair,and then the relationship among the question,legal words,and statutes is modeled simultaneously through the cross attention model.Finally,to achieve more accurate question matching,experiments under multiple legal categories were carried out,and the results show that the proposed method in this study can effectively improve the performance of question matching.