Re34:读论文 Organizing Portuguese Legal Documents through Topic Discovery

简介: 本文是2022年SIGIR会议SIRIP(工业)track的paper,关注对法律文书的整理工作(整理、组织、摘要、发现隐主题),以巴西最高法院Jusbrasil的葡萄牙语数据集为例,进行主题建模,直接用术语表而非文档。本文主要探索各种主题建模方法在葡萄牙语数据集上的效果(我咋感觉这个工作量不高呢,是我的错觉吗还是事实如此,SIGIR不是顶会吗,就这?)。

1. 主题建模方法

CombinedTM(CTM)

Top2Vec

BERTopic


2. 数据集和指标

数据集是2K+无标签文档,和425条有标签文档。

这里面介绍了一堆硬指标软指标什么的,感觉还挺复杂的,以后做相关领域了再慢慢看。


3. 实验结果

image.png


相关文章
|
算法 计算机视觉 知识图谱
ACL2022:A Simple yet Effective Relation Information Guided Approach for Few-Shot Relation Extraction
少样本关系提取旨在通过在每个关系中使用几个标记的例子进行训练来预测句子中一对实体的关系。最近的一些工作引入了关系信息
135 0
《Autoencoder-based Semi-Supervised Curriculum Learning For Out-of-domain Speaker Verification》电子版地址
Autoencoder-based Semi-Supervised Curriculum Learning For Out-of-domain Speaker Verification
81 0
《Autoencoder-based Semi-Supervised Curriculum Learning For Out-of-domain Speaker   Verification》电子版地址
|
机器学习/深度学习 自然语言处理 异构计算
Re20:读论文 What About the Precedent: An Information-Theoretic Analysis of Common Law
Re20:读论文 What About the Precedent: An Information-Theoretic Analysis of Common Law
Re20:读论文 What About the Precedent: An Information-Theoretic Analysis of Common Law
|
机器学习/深度学习
Re16:读论文 ILDC for CJPE: Indian Legal Documents Corpus for Court Judgment Prediction and Explanation
Re16:读论文 ILDC for CJPE: Indian Legal Documents Corpus for Court Judgment Prediction and Explanation
Re16:读论文 ILDC for CJPE: Indian Legal Documents Corpus for Court Judgment Prediction and Explanation
|
机器学习/深度学习 计算机视觉
Re14:读论文 ILLSI Interpretable Low-Resource Legal Decision Making
Re14:读论文 ILLSI Interpretable Low-Resource Legal Decision Making
Re14:读论文 ILLSI Interpretable Low-Resource Legal Decision Making
|
自然语言处理
Re24:读论文 IOT-Match Explainable Legal Case Matching via Inverse Optimal Transport-based Rationale Ext
Re24:读论文 IOT-Match Explainable Legal Case Matching via Inverse Optimal Transport-based Rationale Ext
Re24:读论文 IOT-Match Explainable Legal Case Matching via Inverse Optimal Transport-based Rationale Ext
|
机器学习/深度学习 自然语言处理 PyTorch
Re6:读论文 LeSICiN: A Heterogeneous Graph-based Approach for Automatic Legal Statute Identification fro
Re6:读论文 LeSICiN: A Heterogeneous Graph-based Approach for Automatic Legal Statute Identification fro
Re6:读论文 LeSICiN: A Heterogeneous Graph-based Approach for Automatic Legal Statute Identification fro
Re8:读论文 Hier-SPCNet: A Legal Statute Hierarchy-based Heterogeneous Network for Computing Legal Case
Re8:读论文 Hier-SPCNet: A Legal Statute Hierarchy-based Heterogeneous Network for Computing Legal Case
Re8:读论文 Hier-SPCNet: A Legal Statute Hierarchy-based Heterogeneous Network for Computing Legal Case
|
机器学习/深度学习 算法 数据挖掘
Re18:读论文 GCI Everything Has a Cause: Leveraging Causal Inference in Legal Text Analysis
Re18:读论文 GCI Everything Has a Cause: Leveraging Causal Inference in Legal Text Analysis
Re18:读论文 GCI Everything Has a Cause: Leveraging Causal Inference in Legal Text Analysis
|
搜索推荐 PyTorch 算法框架/工具
Re30:读论文 LegalGNN: Legal Information Enhanced Graph Neural Network for Recommendation
Re30:读论文 LegalGNN: Legal Information Enhanced Graph Neural Network for Recommendation
Re30:读论文 LegalGNN: Legal Information Enhanced Graph Neural Network for Recommendation