Effective deep learning approaches for summarization of legal texts

Anand, D. K.; Wagh, Rupali

doi:10.1016/j.jksuci.2019.11.015

Cited by 53 publications

(27 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The results of AutoJudge were better than the base model in terms of consistency and reliability. The problem of unavailability of labeled data for the prediction task is tackled by assigning classes/scores to sentences in the training set, based on their match with reference summary produced by humans using LSTM by Anand et al [4].…”

Section: A Empirical Literature On Legal Judgment Prediction Methodsmentioning

confidence: 99%

“…Some of the LJP frameworks predict final judgment as a binary [2] and multilabel text classification [3] for cases in English of European Court Human Rights and Chinese Judgment Online dataset. One of the most important challenges in LJP is unlabelled data and that was tackled using the Long Short Term Memory framework [4] for Indian Supreme Court judgments with headnotes. At the initial stages, Machine Learning methods such as optimized Lasso Regression [5] [6] for Chinese cases and then deep learning models [7] [8] for automated judgment predictions were used.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Meta Analysis of Attention Models on Legal Judgment Prediction System

Sukanya¹,

J.Priyadarshini²

2021

IJACSA

View full text Add to dashboard Cite

Intelligence in legal research is transforming the legal area in manifold ways. Pendency of court cases is a long-lasting problem in the judiciary due to various reasons such as lack of judges, lack of technology in legal services and the legal loopholes. The judicial system has to be more competent and more reliable in providing justice on time. One of the major causes of pending cases is the lack of legal intelligence to assist the litigants. The study in this paper reviews the challenges faced by judgment prediction system due to lengthy case facts using deep learning model. The Legal Judgment prediction system can help lawyers, judges and civilians to predict the win or loss rate, punishment term and applicable law articles for new cases. Besides, the paper reviews current encoding and decoding architecture with attention mechanism of transformer model that can be used for Legal Judgment Prediction system. Natural Language Processing using deep learning is an exploring field and there is a need for research to evaluate the current state of the art at the intersection of good text processing and feature representation with a deep learning model. This paper aims to develop a systematic review of existing methods used in the legal judgment prediction system and about the Hierarchical Attention Neural network model in detail. This can also be used in other applications such as legal document classification, sentimental analysis, news classification, text translation, medical reports and so on.

show abstract

Section: A Empirical Literature On Legal Judgment Prediction Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

A Meta Analysis of Attention Models on Legal Judgment Prediction System

Sukanya¹,

J.Priyadarshini²

2021

IJACSA

View full text Add to dashboard Cite

show abstract

“…Recently, researchers have explored deep learning methods on the task of legal text summarization and have achieved great performance. Anand et al [38] proposed a model that utilizes CNN and RNN for the Indian legal judgment document summarization task. Huang et al [39] presented a sequence-to-sequence model for the summarization of legal public opinion news by incorporating topic information.…”

Section: Text Summarizationmentioning

confidence: 99%

Automatic Generation of the Draft Procuratorial Suggestions Based on an Extractive Summarization Method: BERTSLCA

Sun

Yang

Wang

et al. 2021

Mathematical Problems in Engineering

View full text Add to dashboard Cite

The automatic generation of the draft procuratorial suggestions is to extract the description of illegal facts, administrative omission, description of laws and regulations, and other information from the case documents. Previously, the existing deep learning methods mainly focus on context-free word embeddings when addressing legal domain-speciﬁc extractive summarization tasks, which cannot get a better semantic understanding of the text and in turn leads to an adverse summarization performance. To this end, we propose a novel deep contextualized embeddings-based method BERTSLCA to conduct the extractive summarization task. The model is mainly based on the variant of BERT called BERTSUM. Firstly, the input document is fed into BERTSUM to get sentence-level embeddings. Then, we design an extracting architecture to catch the long dependency between sentences utilizing the Bi-Long Short-Term Memory (Bi-LSTM) unit, and at the end of the architecture, three cascaded convolution kernels with different sizes are designed to extract the relationships between adjacent sentences. Last, we introduce an attention mechanism to strengthen the ability to distinguish the importance of different sentences. To the best of our knowledge, this is the first work to use the pretrained language model for extractive summarization tasks in the field of Chinese judicial litigation. Experimental results on public interest litigation data and CAIL 2020 dataset all demonstrate that the proposed method achieves competitive performance.

show abstract

“…Regarding the number of input documents to be summarized, the summary can be a single-document summarization (SDS), which produces the summary from a single document, or a multi-document summarization (MDS),which extracts the summary from a set of documents [5]. The determination of significant sentences from a single summary is a lot simpler, assuming that the order of the selected sentences maintains the order as in the original document, the summary still have a coherent document.…”

Section: Introductionmentioning

confidence: 99%

Multilingual Text Summarization using Deep Learning

AlTimimi¹,

Al-Rubbiay²

2021

IJERAT

View full text Add to dashboard Cite

Along with the extreme expansion of big data and the vast development of the internet, making documentation of the huge internet information is the first interest for people. These online textual data led to information overload and redundancy. Multi-document summarization is one of the solutions to such an issue, used to extract the main ideas of the documents and put them into a short summary. Summarizing documents should not affect the major concepts and the meaning of the original text. This paper proposes a new method for multi-document summarization. The basic idea of the proposed method relied on six different features to be extracted of each sentence in the studied collection, these features must be language. A set of the feature vectors is introduced to Convolutional Neural Networks (CNNs) for classification as either summary or non-summary sentences. A graph of summary sentences was generated and assigned scores by the TextRank algorithm. The implemented system was evaluated on both English and Arabic versions of the dataset of the TAC-2011 MultiLing Pilot by using ROUGE metrics. The proposed method achieved an average F-measure 0.46079, 0.20664 using ROUGE-1 and ROUGE-2 respectively, for English documents, and achieved an average F-measure 0.45624, 0.30725 for Arabic documents.

show abstract

Effective deep learning approaches for summarization of legal texts

Cited by 53 publications

References 6 publications

A Meta Analysis of Attention Models on Legal Judgment Prediction System

A Meta Analysis of Attention Models on Legal Judgment Prediction System

Automatic Generation of the Draft Procuratorial Suggestions Based on an Extractive Summarization Method: BERTSLCA

Multilingual Text Summarization using Deep Learning

Contact Info

Product

Resources

About