Interpretable Charge Predictions for Criminal Cases: Learning to Generate Court Views from Fact Descriptions
arXiv:1802.08504
Abstract
In this paper, we propose to study the problem of COURT VIEW GENeration from the fact description in a criminal case. The task aims to improve the interpretability of charge prediction systems and help automatic legal document generation. We formulate this task as a text-to-text natural language generation (NLG) problem. Sequenceto-sequence model has achieved cutting-edge performances in many NLG tasks. However, due to the non-distinctions of fact descriptions, it is hard for Seq2Seq model to generate charge-discriminative court views. In this work, we explore charge labels to tackle this issue. We propose a label-conditioned Seq2Seq model with attention for this problem, to decode court views conditioned on encoded charge labels. Experimental results show the effectiveness of our method.
arXiv commentTo appear in NAACL 2018, Long paper
Cited by in corpus (4)
- Overview of CAIL2018: Legal Judgment Prediction Competition
- Semi-Supervised Learning for Neural Keyphrase Generation
- GeoSQA: A Benchmark for Scenario-based Question Answering in the Geography Domain at High School Level
- Deep Ranking Based Cost-sensitive Multi-label Learning for Distant Supervision Relation Extraction