arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2408.09717cs.CL
收藏

SEMDR:一种用于法律判决预测且具备法律线索追踪能力的语义感知双编码器模型

SEMDR: A Semantic-Aware Dual Encoder Model for Legal Judgment Prediction with Legal Clue Tracing

College of Science, Northeastern University(东北大学理学院);School of Computer Science and Engineering, Southern University of Science and Technology(南方科技大学计算机科学与工程学院);Department of Computer Science, University of Reading(雷丁大学计算机科学系)

Pengjie Liu, Wang Zhang, Yulong Ding, Xuefeng Zhang, Shuang-Hua Yang

AI总结:

针对法律判决预测中易混淆案件难区分的问题,提出带三层法律线索追踪机制的语义感知双编码器模型SEMDR,在CAIL2018数据集达SOTA,少样本场景表现优异,可提升预测准确性并降低模型不确定性。

摘要:

法律判决预测(LJP)旨在根据犯罪事实描述形成法律判决。然而,研究人员难以对易混淆的刑事案件(如抢劫罪和盗窃罪)进行分类,这要求LJP模型能够区分相似罪名之间的细微差别。现有方法通常设计手工特征来提取必要的语义法律线索,以做出更准确的法律判决预测。本文提出了一种语义感知双编码器模型(SEMDR),该模型设计了一种新颖的法律线索追踪机制,用于在犯罪事实和法律条文之间进行细粒度语义推理。我们的法律线索追踪机制由三个推理层级构建:1)词汇追踪(Lexicon-Tracing),旨在从犯罪描述中提取犯罪事实;2)句子表示学习,通过对比训练语言模型以更好地表示易混淆的犯罪事实;3)多事实推理,构建理由图以在事实节点之间传播语义线索,从而捕捉犯罪事实之间的细微差异。我们的法律线索追踪机制帮助SEMDR在CAIL2018数据集上达到了当前最优水平(state-of-the-art),并在少样本场景中展现出先进性。实验表明,SEMDR具有强大的能力,能够为犯罪事实学习更具一致性和区分度的表示,这有助于对易混淆的刑事案件做出更准确的预测,并降低模型做出判决时的不确定性。所有代码将通过GitHub发布。

英文摘要:

Legal Judgment Prediction (LJP) aims to form legal judgments based on the criminal fact description. However, researchers struggle to classify confusing criminal cases, such as robbery and theft, which requires LJP models to distinguish the nuances between similar crimes. Existing methods usually design handcrafted features to pick up necessary semantic legal clues to make more accurate legal judgment predictions. In this paper, we propose a Semantic-Aware Dual Encoder Model (SEMDR), which designs a novel legal clue tracing mechanism to conduct fine-grained semantic reasoning between criminal facts and instruments. Our legal clue tracing mechanism is built from three reasoning levels: 1) Lexicon-Tracing, which aims to extract criminal facts from criminal descriptions; 2) Sentence Representation Learning, which contrastively trains language models to better represent confusing criminal facts; 3) Multi-Fact Reasoning, which builds a reasons graph to propagate semantic clues among fact nodes to capture the subtle difference among criminal facts. Our legal clue tracing mechanism helps SEMDR achieve state-of-the-art on the CAIL2018 dataset and shows its advance in few-shot scenarios. Our experiments show that SEMDR has a strong ability to learn more uniform and distinguished representations for criminal facts, which helps to make more accurate predictions on confusing criminal cases and reduces the model uncertainty during making judgments. All codes will be released via GitHub.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑