Recognition Of Applicable Laws Based On Hierarchical Multi-label Classification

During the trial of legal cases,it is an important issue for the judiciary authorities,the lawyers and the litigants to find out the applicable laws of legal cases according to the facts.With the advance of judicial reform which aims to promote judicial open-ness,massive documents of judgment containing the facts and applicable laws of legal cases are made public on the Internet gradually,which makes it possible to recognize the applicable laws of legal cases automatically by data mining.However,it is quite complicated to accomplish the goal due to two reasons.The first reason is that docu-ments of judgement,which are the data to be dealt with,are in text form,while normal classification methods are usually designed for structured data.The second reason is that the articles of law are structured in a hierarchy and multiple articles of law with d-ifferent levels can be applicable to a single legal case,making automatic recognition of applicable laws of legal cases a hierarchical multi-label classification problem.Hence,thorough analysis of the characteristic of the problem is needed so as to find out the so-lutions for practical and effective automatic recognition of the applicable laws of legal cases.In this thesis,a system that can automatically recognize of the applicable laws of legal cases was built by data mining on documents of judgement.The most important contributions of this work are the following:1.Proposed a lazy hierarchical multi-label classification algorithm named Lazy-HMC.As a lazy learning method,Lazy-HMC supports incremental learning and can thus perform very well when the data size is large and is growing larg-er.Lazy-HMC takes the hierarchy of the class labels into consideration during the training phase and extend the class labels of training examples accordingly,which makes the output of the algorithm meets the hierarchical constraint.Dur-ing the test phase,k nearest neighbors in the training set of the given instance are found firstly.The confidence that the instance belongs to each class label can be computed based on the weight of each neighboring example.Eventually,the class labels of the given instance are predicted accordingly.2.Many documents of judgement are collected by web crawling,from which the facts and the applicable laws of legal cases are extracted.Using text mining technology such as vector space model,the facts of legal cases can be converted to structured text feature vectors and the dimension of the feature vector can be reduced by feature selection.Consequently,the structured sample data set con-taining the facts and the applicable laws of legal cases can be constructed.The prediction model of the applicable laws of legal cases was built by performing Lazy-HMC on the constructed structured sample data set.The experiment compared the performance of Lazy-HMC with different value of parameters,and proved that Lazy-HMC is effective in automatic recognition of the applicable laws of legal cases by comparing with two other common hierarchical multi-label classification algorithms.