A Recurrent Attention Network for Judgment Prediction

Judgment prediction is a critical technique in legal field. Judges usually scan both of the fact descriptions and articles repeatedly to select valuables information for a correct match (i.e., determine the correct articles for a given fact description). Previous works only analyze semantics to the corresponding articles, while the repeated semantic interactions between fact descriptions and articles are ignored, thus the performance may be limited. In this paper, we propose a novel Recurrent Attention Network (RAN for short) to address this issue. Specifically, RAN utilizes a LSTM to obtain both fact description and article representations, then a recurrent process is designed to model the iterative interactions between fact descriptions and articles to make a correct match. Experimental results on real-world datasets demonstrate that our proposed model achieves significant improvements over the state-of-the-art methods.

[1]  Zhiyuan Liu,et al.  Legal Judgment Prediction via Topological Learning , 2018, EMNLP.

[2]  Fred Kort.  Predicting Supreme Court Decisions Mathematically: A Quantitative Analysis of the “Right to Counsel” Cases , 1957, American Political Science Review.

[3]  Zhi-Hua Zhou,et al.  ML-KNN: A lazy learning approach to multi-label learning , 2007, Pattern Recognit..

[4]  Jürgen Schmidhuber,et al.  Framewise phoneme classification with bidirectional LSTM and other neural network architectures , 2005, Neural Networks.

[5]  Nikolaos Aletras,et al.  Predicting judicial decisions of the European Court of Human Rights: a Natural Language Processing perspective , 2016, PeerJ Comput. Sci..

[6]  Yoshua Bengio,et al.  Neural Machine Translation by Jointly Learning to Align and Translate , 2014, ICLR.

[7]  Quoc V. Le,et al.  Addressing the Rare Word Problem in Neural Machine Translation , 2014, ACL.

[8]  Jason Weston,et al.  Joint Learning of Words and Meaning Representations for Open-Text Semantic Parsing , 2012, AISTATS.

[9]  Zhi-Hua Zhou,et al.  Multilabel Neural Networks with Applications to Functional Genomics and Text Categorization , 2006, IEEE Transactions on Knowledge and Data Engineering.

[10]  Jason Weston,et al.  A kernel method for multi-labelled classification , 2001, NIPS.

[11]  Mi-Young Kim,et al.  Legal Question Answering Using Ranking SVM and Syntactic/Semantic Similarity , 2014, JSAI-isAI Workshops.

[12]  Alex Graves,et al.  Recurrent Models of Visual Attention , 2014, NIPS.

[13]  Dongyan Zhao,et al.  Learning to Predict Charges for Criminal Cases with Legal Basis , 2017, EMNLP.

[14]  Bowen Zhou,et al.  ABCNN: Attention-Based Convolutional Neural Network for Modeling Sentence Pairs , 2015, TACL.

[15]  Ting Liu,et al.  Attention-over-Attention Neural Networks for Reading Comprehension , 2016, ACL.

[16]  Christopher D. Manning,et al.  Effective Approaches to Attention-based Neural Machine Translation , 2015, EMNLP.

[17]  Bowen Zhou,et al.  A Structured Self-attentive Sentence Embedding , 2017, ICLR.

[18]  Yoon Kim,et al.  Convolutional Neural Networks for Sentence Classification , 2014, EMNLP.

[19]  Josh Blackman,et al.  Predicting the Behavior of the Supreme Court of the United States: A General Approach , 2014, ArXiv.

[20]  R. Keown.  Mathematical Models For Legal Prediction, 2 Computer L.J. 829 (1980) , 1980 .

[21]  Pengfei Wang,et al.  Modeling Dynamic Pairwise Attention for Crime Classification over Legal Articles , 2018, SIGIR.

[22]  Yidong Chen,et al.  Deep Semantic Role Labeling with Self-Attention , 2017, AAAI.

[23]  Zhiyuan Liu,et al.  Few-Shot Charge Prediction with Discriminative Legal Attributes , 2018, COLING.

[24]  Ming-Wei Chang,et al.  BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding , 2019, NAACL.

[25]  Geoff Holmes,et al.  Classifier chains for multi-label classification , 2009, Machine Learning.

[26]  Lukasz Kaiser,et al.  Attention is All you Need , 2017, NIPS.