Charge-Based Prison Term Prediction with Deep Gating Network

Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing, pages 6362–6367, Hong Kong, China, November 3–7, 2019. c⃝2019 Association for Computational Linguistics 6362 Charge-Based Prison Term Prediction with Deep Gating Network Huajie Chen1∗ Deng Cai2∗ Wei Dai1 Zehui Dai1 Yadong Ding1 1NLP Group, Gridsum, Beijing, China {chenhuajie,daiwei,daizehui,dingyadong}@gridsum.com 2The Chinese University of Hong Kong thisisjcykcd@gmail.com Abstract Judgment prediction for legal cases has at- tracted much research efforts for its practice use, of which the ultimate goal is prison term prediction. While existing work merely pre- dicts the total prison term, in reality a defen- dant is often charged with multiple crimes. In this paper, we argue that charge-based prison term prediction (CPTP) not only bet- ter fits realistic needs, but also makes the to- tal prison term prediction more accurate and interpretable. We collect the first large-scale structured data for CPTP and evaluate sev- eral competitive baselines. Based on the ob- servation that fine-grained feature selection is the key to achieving good performance, we propose the Deep Gating Network (DGN) for charge-specific feature selection and aggrega- tion. Experiments show that DGN achieves the state-of-the-art performance. 1 Introduction Judgment prediction (Kort, 1957; Ulmer, 1963; Segal, 1984; Liu et al., 2004; Liu and Hsieh, 2006) aims at automatically predicting the judgment re- sult given a textual description of a legal case (An example is given in Figure 1). Recently, there has been a resurgent interest in this task due to the availability of more data and new machine learn- ing techniques (Luo et al., 2017; Zhong et al., 2018b; Hu et al., 2018). Judgment prediction can be decomposed into several sub-tasks: (a) relevant law article extrac- tion (Liu and Hsieh, 2006; Liu and Liao, 2005; Liu et al., 2015), (b) charge prediction (Liu and Hsieh, 2006; Luo et al., 2017; Hu et al., 2018), (c) and prison term prediction (Zhong et al., 2018a). The dependencies among them have also been studied by Zhong et al. (2018b). While effective methods exist for sub-task (a) and (b), (e.g In CAIL2018 ∗Both authors contributed equally. Case description: On July 7, 2017, when the defendant Cui XX was drinking in a bar, he came into conflict with Zhang XX…… After arriving at the police station, he refused to cooperate with the policeman and bited on the arm of the policeman…… Result of judgment: Cui XX was sentenced to 12 months imprisonment for creating disturbances and 12 months imprisonment for obstructing public affairs…… l Charge#1 creating disturbances term 12 months l Charge#2 obstructing public affairs term 12 months Figure 1: An example of judgment prediction. competition (Zhong et al., 2018a), both the charge prediction and the article prediction have attained Fmicro over 95%), the prison term prediction re- mains the performance bottleneck. In this paper, we improve the accuracy of prison term prediction by decomposing it into a set of charge-based prison term predictions (CPTPs). In this way, more subtle and sophisticated interac- tions between …

Content truncated to 500 words