面向中文法律裁判文书的抽取式摘要算法
作者:
作者单位:

1.中国科学院深圳先进技术研究院;2.中国科学院大学

作者简介:

通讯作者:

基金项目:

法律人工智能联合实验室项目(Y9Z028)

伦理声明:



Extractive Summarization Algorithm for Chinese Legal Judgment Documents
Author:
Ethical statement:

Affiliation:

1.Shenzhen Institute of Advanced Technology,Chinese Academy of Sciences;2.University of Chinese Academy of Sciences

Funding:

This work is supported by SIAT-DELI Artificial Intelligence and Law Lab (Y9Z028)

  • 摘要
  • |
  • 图/表
  • |
  • 访问统计
  • |
  • 参考文献
  • |
  • 相似文献
  • |
  • 引证文献
  • |
  • 资源附件
    摘要:

    裁判文书自动摘要的目的在于让计算机能够自动选择、抽取和压缩法律文本中的重要信息,从而减轻法律从业者的工作量。目前,大多数基于预训练语言模型的摘要算法对于输入文本的长度存在限制,因此无法对长文本进行有效摘要。为此,本文提出了一种新的抽取式摘要算法,该算法利用预训练语言模型生成句子向量,并基于Transformer编码器结构融合句子向量、位置和长度信息,完成句子摘要。实验结果显示,该算法能够有效处理长文本摘要任务。此外,模型在2020年中国法律智能技术评测CAIL摘要数据集上进行了测试,结果表明,相较于基线模型,该模型在ROUGE-1、ROUGE-2和ROUGE-L指标上均有显著提升。

    Abstract:

    The purpose of automatic judgment document summarization is to allow computers to automatically select, extract, and compress important information from legal texts so as to reduce workload of practitioners. Currently, most summarization algorithms based on pre-trained language models have limitations on the length of the input text, so they cannot effectively summarize long texts. In this thesis, we propose a new extractive summarization algorithm, which uses a pre-trained language model to generate sentence vectors. Based on the Transformer encoder structure, the summarization task can be completed by fused information including sentence vectors, position and length of sentences. Experimental results showed that, the algorithm can effectively handle the task of summarizing long texts. In addition, the model was tested on the 2020 CAIL (Challenge of AI in Law) summarization dataset, and results showed that compared to the baseline model, the proposed model showed significant improvement in the ROUGE-1, ROUGE-2, and ROUGE-L metrics.

    参考文献
    相似文献
    引证文献
引用本文

温嘉宝,杨敏.面向中文法律裁判文书的抽取式摘要算法 [J].集成技术,

Citing format
WEN Jiabao, YANG min. Extractive Summarization Algorithm for Chinese Legal Judgment Documents[J]. Journal of Integration Technology.

复制
分享
文章指标
  • 点击次数:
  • 下载次数:
  • HTML阅读次数:
历史
  • 收稿日期:2023-02-09
  • 最后修改日期:2023-02-19
  • 录用日期:
  • 在线发布日期: 2023-05-11
  • 出版日期: