Conviction in Judicial Cases Based on Template Tensor Decomposition and Bidirectional LSTM

LI Da-peng; CHEN Jian; WANG Chen; WEN Ying-you; ZHAO Da-zhe

doi:10.12263/DZXB.20200098

您当前的位置：

首页 >

文章列表页 >

Conviction in Judicial Cases Based on Template Tensor Decomposition and Bidirectional LSTM

更新时间：2025-12-08

- Conviction in Judicial Cases Based on Template Tensor Decomposition and Bidirectional LSTM
- Acta Electronica Sinica Vol. 49, Issue 4, Pages: 760-767(2021)
- 作者机构：
  
  1. 东北大学计算机科学与工程学院,辽宁,沈阳,110819
  2. 东北大学东软研究院,辽宁,沈阳,110819
  3. 辽宁省工业控制安全技术工程中心,辽宁,沈阳,110819
  4. 东北大学计算机科学与工程学院,辽宁,沈阳,110819
  5. 东北大学东软研究院,辽宁,沈阳,110819
  6. 辽宁省工业控制安全技术工程中心,辽宁,沈阳,110819
- 作者简介：
- 基金信息：
- DOI：10.12263/DZXB.20200098
  CLC： TP183
- Published：2021
- 稿件说明：
移动端阅览
LI Da-peng, CHEN Jian, WANG Chen, et al. Conviction in Judicial Cases Based on Template Tensor Decomposition and Bidirectional LSTM[J]. Acta Electronica Sinica, 2021, 49(4): 760-767.
DOI：

LI Da-peng, CHEN Jian, WANG Chen, et al. Conviction in Judicial Cases Based on Template Tensor Decomposition and Bidirectional LSTM[J]. Acta Electronica Sinica, 2021, 49(4): 760-767. DOI： 10.12263/DZXB.20200098.

摘要

案件罪名认定是司法业务的重要环节，尚缺乏有效的智能辅助工具和手段.针对案件定罪的难点问题，提出一种结合张量分解和双向LSTM （Long Short-Term Memory）神经网络的案件定罪方法.该方法将案件数据表示为张量，并在张量分解过程中引入模板张量.模板张量可以在双向LSTM神经网络分类模型的训练过程不断的被优化，使得分解后的核心张量包含更加有效的张量结构和特征信息，有助于提高后续分类模型的准确性，实现案件罪名的精准认定.实验结果表明：所提出的基于张量分解和双向LSTM的司法案件定罪方法比现有方法具有更好的准确性.

Abstract

Conviction in judicial cases is an important part of judicial business

but there is still a lack of effective intelligent auxiliary tools and methods. Aiming at the difficult problem of conviction in judicial cases

a method combining tensor decomposition and Bi-LSTM neural network is proposed. This method represents the case data as a tensor and introduces a template tensor in the tensor decomposition process. The template tensor can be continuously optimized during the training process of Bi-LSTM neural network classification model

so that the decomposed core tensor contains more effective tensor structure and feature information

which is helpful to improve the accuracy of the subsequent classification model and realize the accurate conviction in judicial cases. The experimental results show that the proposed method for conviction in judicial cases based on tensor decomposition and Bi-LSTM has better accuracy than the existing methods.

关键词

Keywords

references

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

The Semi-Automatic Classification Data Labeling Method Based on Dispute About Weak Label

Tensor Decomposition and K‑means Clustering Based Array Diagnosis for MIMO Radar in Impulsive Noise Environment

Automatic Domain-Specific Term Extraction and Its Application in Text Classification

A Combined-Convolutional Neural Network for Chinese News Text Classification

A Recommendation Model Based on Dynamic Role Identification and Tensor Decomposition

Related Author

LUO Lin

YANG Xian-feng

YANG Wei

LI Zi-qiang

CHEN Jin-li

LONG Wei-jun

WANG YA-peng

LI Jia-qiang

Related Institution

College of Movie and Media, Sichuan Normal University

School of Computer Science and Software Engineering, Southwest Petroleum University

Chengdu R&D Center, Tellhow Software

Nanjing Research Institute of Electronics Technology

Collaborative Innovation Center on Forecast and Evaluation of Meteorological Disasters, Nanjing University of Information Science and Technology

⁰