通过修正的关系知识区分法律判决预测中的混淆情形
Distinguish Confusion in Legal Judgment Prediction via Revised Relation Knowledge
AI总结：
针对法律判决预测中由先验相似及数据不平衡导致的后验相似法条混淆问题，提出融合图蒸馏与动量更新记忆机制的D-LADAN模型，在准确率和鲁棒性上显著优于现有最优方法。
摘要：
法律判决预测（LJP）旨在基于案件事实的文本描述自动预测案件的判决结果。在实践中，法条（或罪名）混淆问题频繁出现，表现为适用相似法条（或罪名）的案件容易被误判。尽管近期一些基于先验知识的研究较好地解决了这一问题，但它们忽略了混淆同样会发生在后验语义相似度高的法条之间——这种混淆由数据不平衡问题导致，而非仅存在于先验高度相似的法条之间，这是本研究的进一步发现。\n本文提出一种名为D-LADAN的端到端模型以解决上述挑战。一方面，D-LADAN基于法条的文本定义构建法条间的图结构，并提出图蒸馏操作（GDO）以区分先验语义相似度高的法条。另一方面，D-LADAN提出一种新颖的动量更新记忆机制，用于动态感知法条（或罪名）之间的后验相似度，还提出加权图蒸馏操作以自适应捕捉差异，修正由数据不平衡问题导致的归纳偏置。我们开展了大量实验，结果表明D-LADAN在准确率和鲁棒性上显著优于现有最优方法。
英文摘要：
Legal Judgment Prediction (LJP) aims to automatically predict a law case's judgment results based on the text description of its facts. In practice, the confusing law articles (or charges) problem frequently occurs, reflecting that the law cases applicable to similar articles (or charges) tend to be misjudged. Although some recent works based on prior knowledge solve this issue well, they ignore that confusion also occurs between law articles with a high posterior semantic similarity due to the data imbalance problem instead of only between the prior highly similar ones, which is this work's further finding. This paper proposes an end-to-end model named \textit{D-LADAN} to solve the above challenges. On the one hand, D-LADAN constructs a graph among law articles based on their text definition and proposes a graph distillation operation (GDO) to distinguish the ones with a high prior semantic similarity. On the other hand, D-LADAN presents a novel momentum-updated memory mechanism to dynamically sense the posterior similarity between law articles (or charges) and a weighted GDO to adaptively capture the distinctions for revising the inductive bias caused by the data imbalance problem. We perform extensive experiments to demonstrate that D-LADAN significantly outperforms state-of-the-art methods in accuracy and robustness.
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。
