Improving legal judgment prediction through reinforced criminal element extraction

2022 
Abstract Legal text mining is targeted at automatically analyzing the texts in the legal domain by employing various natural language processing techniques and has attracted enormous attention from the NLP community. As one of the most crucial tasks of legal text mining, Legal Judgment Prediction (LJP) aims to automatically predict judgment results (e.g., applicable law articles, charges, and terms of penalty) according to fact descriptions on law cases and becomes a promising application of artificial intelligence techniques. Unfortunately, ambiguous fact descriptions and law articles often appear due to a great number of shared words and legal concepts. Prior works are proposed to partially address these problems, focusing on introducing additional attributes to distinguish similar fact descriptions, or differentiating confusing law articles by grouping and distilling law articles. However, existing works still face two severe challenges: (1) indistinguishable fact descriptions with different criminals and targets and (2) misleading law articles with highly similar TF–IDF representations, both of which lead to serious misjudgments for the LJP task. In this paper, we present a novel reinforcement learning (RL) based framework, named Criminal Element Extraction Network (CEEN), to handle above challenges simultaneously. In CEEN, we propose four types of discriminative criminal elements, including the criminal, target, intentionality, and criminal behavior. To discriminate ambiguous fact descriptions, an reinforcement learning based extractor is designed to accurately locate elements for different cases. To enhance law article predictions, distinctive element representations are constructed for each type of criminal element. Finally, with the input of element representations, a multi-task predictor is adopted for the judgment predictions. Experimental results on real-world datasets show that extracting criminal elements is highly useful for predicting the judgment results.
    • Correction
    • Source
    • Cite
    • Save
    • Machine Reading By IdeaReader
    44
    References
    1
    Citations
    NaN
    KQI
    []