Evidence Mining for Interpretable Charge Prediction via Prompt Learning
Evidence Mining for Interpretable Charge Prediction via Prompt Learning
复制标题
DOI：
10.1109/tcss.2022.3178551
复制
发表时间：
2022-06-08
影响因子：
5
通讯作者：
Liu，Jinhang
中科院分区：
文献类型：
--
作者：
Li，Lin;Liu，Dan;Liu，Jinhang
如今，越来越多的研究者致力于将人工智能技术应用于法律的领域，以支持决策。指控预测是法律的判决预测的一个子任务。其目的是分析自然语言文本的事实描述，并预测与案件相对应的指控。目前，大多数研究将指控预测作为一个多类分类任务，由于事实描述与指控标签之间的语义相关性较弱，导致解释效果不理想。为了解决这一问题，提出了一种基于提示学习的生成式证据挖掘方法。具体来说，在训练阶段，我们重新制定的收费标签到提示模板，我们设计，以提高收费标签和事实描述之间的语义相关性。在测试阶段，电荷标签通过基于即时学习的模型生成。同时，我们从Transformer编码器中的多头自注意中计算每个句子的注意分数，并选择注意分数最高的句子作为证据。我们在真实的数据集上的实验结果表明，我们的方法优于传统的基于微调的分类方法。
Nowadays, more and more researchers are committed to applying artificial intelligence technology to the legal field to support decision-making. Charge prediction is a subtask of legal judgment prediction (LJP). Its purpose is to analyze the fact description of natural language text and predict a charge corresponding to a case. At present, most of the research takes charge prediction as a multiclass classification task, which leads to unsatisfactory interpretation due to the weak semantic correlation between the fact descriptions and charge labels. In order to solve this problem, we propose a method of generative evidence mining based on prompt learning. Specifically, in the training phase, we reformulate the charge labels into the prompt template that we design to enhance the semantic correlation between the charge labels and the fact descriptions. In the testing phase, the charge labels are generated via the model based on prompt learning. Meanwhile, we calculate the attention score of each sentence from the multihead self-attention in the transformer encoder and choose the sentence with the highest attention score as the evidence. Our experimental results on a real dataset show that our method is better than the traditional fine-tuning-based classification method.