An Element-aware Multi-representation Model for Law Article Prediction

Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing, pages 6663–6668, November 16–20, 2020. c⃝2020 Association for Computational Linguistics 6663 An Element-aware Multi-representation Model for Law Article Prediction Huilin Zhong1, Junsheng Zhou∗1, Weiguang Qu1, Yunfei Long2, and Yanhui Gu1 1 School of Computer and Electronic Information, Nanjing Normal University, China 2 School of Computer Science and Electronic Engineering, University of Essex, Colchester, UK CO2 8JT {zhoujs, wgqu}@njnu.edu.cn, yanhgu@gmail.com yl20051@essex.ac.uk, elaine1027zhl@hotmail.com Abstract Existing works have proved that using law ar- ticles as external knowledge can improve the performance of the Legal Judgment Predic- tion. However, they do not fully use law arti- cle information and most of the current work is only for single label samples. In this pa- per, we propose a Law Article Element-aware Multi-representation Model (LEMM), which can make full use of law article information and can be used for multi-label samples. The model uses the labeled elements of law articles to extract fact description features from mul- tiple angles. It generates multiple representa- tions of a fact for classification. Every label has a law-aware fact representation to encode more information. To capture the dependen- cies between law articles, the model also in- troduces a self-attention mechanism between multiple representations. Compared with base- line models like TopJudge, this model im- proves the accuracy of 5.84%, the macro F1 of 6.42%, and the micro F1 of 4.28%. 1 Introduction Legal Judgment Prediction(LJP) aims to predict a law case’s judgment results given a fact descrip- tion text. LJP mainly contains three sub-tasks, law article prediction, charge prediction, and terms of penalty prediction. In the civil law system, the cor- rect prediction of law article prediction can help im- prove the accuracy of charge prediction(Luo et al., 2017). The investigation of law article prediction has significant meaning for LJP. The law article prediction aims to predict the case’s relevant law articles given the fact descrip- tion (hereinafter abbreviated fact) of a case. In the law article prediction, law articles play an essen- tial role as external information. Luo et al. (2017) uses some candidate law articles to improve the per- formance of the charge prediction task. However, current researches have two main limitations. One is that certain law articles are considerably similar which makes them difficult to distinguish. Using the representation of overall law articles to extract fact information is not intuitive enough. Another one is that most of the works (Zhong et al., 2018a; Yang et al., 2019; Liu et al., 2019) only predict on single label examples. Meanwhile, in the actual judgment, many cases contain multiple relevant law articles(Zhong et al., 2018b). Human judge process mainly compares the ele- ments of law article with the case description(Hu et al., 2018), such as the subject of crime (person or specific identity), the object of the crime (person or thing), the purpose and motive of the crime, the harmful behavior, the adverse result, and the crime scene (time or place). To make full use of the law article …

Content truncated to 500 words