Legal Document Classification: An Application to Law Area Prediction of Petitions to Public Prosecution Service

Noguti, Mariana Y.; Vellasques, Eduardo; Oliveira, Luiz S.

doi:10.1109/ijcnn48605.2020.9207211

Cited by 23 publications

(17 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In this section, we delineate the experiment conducted to compare the performance of KTL-BERT with that of Word2vec+LSTM [16] and Attention-based Bidirectional Gated Recurrent Unit-Convolutional Neural Network (Attention-based BiGRU-CNN) [2], both of which exhibited excellent performance in previous studies.…”

Section: ) Ktl-bert Vs Deep Learning Modelmentioning

confidence: 99%

Domain-Specific Language Model Pre-Training for Korean Tax Law Classification

Piao

Yin

et al. 2022

IEEE Access

View full text Add to dashboard Cite

Owing to their increasing amendments and complexity, most taxpayers do not have the required knowledge of tax laws, which results in issues in everyday life. To use tax counseling services through the internet, a person must first select a category of tax laws corresponding to their tax question. However, a layperson without prior knowledge of tax laws may not know which category to select in the first place. Therefore, a model capable of automatically classifying the categories of tax laws is needed. Recently, a model using BERT has been frequently used for text classification; however, it is generally used in opendomains, and often experiences a degraded performance due to domain-specific technical terms, such as tax laws. Furthermore, a significant amount of time is required to train the model, since BERT is a large-scale model. To address these issues, this study proposes Korean tax law-BERT (KTL-BERT) for the automatic classification of categories of tax questions. For the proposed KTL-BERT, a new pre-trained language model was constructed by performing learning from scratch, to which a static masking method was applied based on DistilRoBERTa. Subsequently, the pre-trained language model was fine-tuned to classify five categories of tax law. A total of 327,735 tax law questions were used to verify the performance of the proposed KTL-BERT. The F1-score of the proposed KTL-BERT was approximately 91.06%, which is higher than that of the benchmark models by approximately 1.07%-15.46%, and the training speed was approximately 0.89%-56.07% higher.INDEX TERMS BERT, domain-specific, Korean tax law, pre-trained language model, text classification.

show abstract

Section: ) Ktl-bert Vs Deep Learning Modelmentioning

confidence: 99%

Domain-Specific Language Model Pre-Training for Korean Tax Law Classification

Piao

Yin

et al. 2022

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Mariana Y. N. et al analyzed the classification of Petitions to Public Prosecution Service in Portuguese [ 19 ]. The aim was to classify 18 areas of law (civil, child and youth, criminal, consumer, etc.).…”

Section: Introductionmentioning

confidence: 99%

Polish Court Ruling Classification Using Deep Neural Networks

Kostrzewa

Nowak

2022

Sensors

View full text Add to dashboard Cite

In this work, the problem of classifying Polish court rulings based on their text is presented. We use natural language processing methods and classifiers based on convolutional and recurrent neural networks. We prepared a dataset of 144,784 authentic, anonymized Polish court rulings. We analyze various general language embedding matrices and multiple neural network architectures with different parameters. Results show that such models can classify documents with very high accuracy (>99%). We also include an analysis of wrongly predicted examples. Performance analysis shows that our method is fast and could be used in practice on typical server hardware with 2 Processors (Central Processing Units, CPUs) or with a CPU and a Graphics processing unit (GPU).

show abstract

“…Legal Artificial Intelligence (LegalAI) (Zhong et al, 2020;Rissland et al, 2003) is a specific subject to apply the artificial intelligence technology into legal tasks including legal judgement prediction (Rosca et al, 2020;Gan et al, 2021), similar case matching (Tran et al, 2019) and law case classification (Noguti et al, 2020;Lin et al, 2012;Li et al, 2019a). In this paper, we focus on law case classification.…”

Section: Introductionmentioning

confidence: 99%

D2GCLF: Document-to-Graph Classifier for Legal Document Classification

Wang¹,

Zhao²,

Amor³

et al. 2022

Findings of the Association for Computational Linguistics: NAACL 2022

View full text Add to dashboard Cite

Legal document classification is an essential task in law intelligence to automate the laborintensive law case filing process. Unlike traditional document classification problems, legal documents should be classified by reasons and facts instead of topics. We propose a Document-to-Graph Classifier (D2GCLF), which extracts facts as relations between key participants in the law case and represents a legal document with four relation graphs. Each graph is responsible for capturing different relations between the litigation participants. We further develop a graph attention network on top of the four relation graphs to classify the legal documents. Experiments on a real-world legal document dataset show that D2GCLF outperforms the state-of-the-art methods in terms of accuracy.

show abstract

Legal Document Classification: An Application to Law Area Prediction of Petitions to Public Prosecution Service

Cited by 23 publications

References 4 publications

Domain-Specific Language Model Pre-Training for Korean Tax Law Classification

Domain-Specific Language Model Pre-Training for Korean Tax Law Classification

Polish Court Ruling Classification Using Deep Neural Networks

D2GCLF: Document-to-Graph Classifier for Legal Document Classification

Contact Info

Product

Resources

About