Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

A sequence labeling model for catchphrase identification from legal case documents

A sequence labeling model for catchphrase identification from legal case documents In a Common Law system, legal practitioners need frequent access to prior case documents that discuss relevant legal issues. Case documents are generally very lengthy, containing complex sentence structures, and reading them fully is a strenuous task even for legal practitioners. Having a concise overview of these documents can relieve legal practitioners from the task of reading the complete case statements. Legal catchphrases are (multi-word) phrases that provide a concise overview of the contents of a case document, and automated generation of catchphrases is a challenging problem in legal analytics. In this paper, we propose a novel supervised neural sequence tagging model for the extraction of catchphrases from legal case documents. Specifically, we show that incorporating document-specific information along with a sequence tagging model can enhance the performance of catchphrase extraction. We perform experiments over a set of Indian Supreme Court case documents, for which the gold-standard catchphrases (annotated by legal practitioners) are obtained from a popular legal information system. The performance of our proposed method is compared with that of several existing supervised and unsupervised methods, and our proposed method is empirically shown to be superior to all baselines. http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png Artificial Intelligence and Law Springer Journals

A sequence labeling model for catchphrase identification from legal case documents

Download PDF
34 pages

Loading next page...
 
/lp/springer-journals/a-sequence-labeling-model-for-catchphrase-identification-from-legal-LLizyiewDK
Publisher
Springer Journals
Copyright
Copyright © The Author(s), under exclusive licence to Springer Nature B.V. 2021
ISSN
0924-8463
eISSN
1572-8382
DOI
10.1007/s10506-021-09296-2
Publisher site
See Article on Publisher Site

Abstract

In a Common Law system, legal practitioners need frequent access to prior case documents that discuss relevant legal issues. Case documents are generally very lengthy, containing complex sentence structures, and reading them fully is a strenuous task even for legal practitioners. Having a concise overview of these documents can relieve legal practitioners from the task of reading the complete case statements. Legal catchphrases are (multi-word) phrases that provide a concise overview of the contents of a case document, and automated generation of catchphrases is a challenging problem in legal analytics. In this paper, we propose a novel supervised neural sequence tagging model for the extraction of catchphrases from legal case documents. Specifically, we show that incorporating document-specific information along with a sequence tagging model can enhance the performance of catchphrase extraction. We perform experiments over a set of Indian Supreme Court case documents, for which the gold-standard catchphrases (annotated by legal practitioners) are obtained from a popular legal information system. The performance of our proposed method is compared with that of several existing supervised and unsupervised methods, and our proposed method is empirically shown to be superior to all baselines.

Journal

Artificial Intelligence and Law – Springer Journals

Published: Sep 1, 2022

Keywords: Legal catchphrases; Catchphrase extraction; Keyphrase extraction; Legal analytics; Sequence tagging; BiGRU; CRF; Doc2Vec

References

  • Wikipedia-based query phrase expansion in patent class search
    Al-Shboul, B; Myaeng, SH
  • Dbpedia-a crystallization point for the web of data
    Bizer, C; Lehmann, J; Kobilarov, G; Auer, S; Becker, C; Cyganiak, R; Hellmann, S
  • Random forests
    Breiman, L
  • Named entity recognition with bidirectional LSTM-CNNs
    Chiu, JP; Nichols, E
  • Dealing with temporal variation in patent categorization
    Dhondt, E; Verberne, S; Oostdijk, N; Beney, J; Koster, C; Boves, L
  • Keyword extraction: issues and methods
    Firoozeh, N; Nazarenko, A; Alizon, F; Daille, B
  • Support vector machines
    Hearst, MA; Dumais, ST; Osuna, E; Platt, J; Scholkopf, B
  • Patent keyword extraction algorithm based on distributed representation for patent classification
    Hu, J; Li, S; Yao, Y; Yu, L; Yang, G; Hu, J
  • Extracting indices from Japanese legal documents
    Le, TTN; Shirai, K; Nguyen, ML; Shimazu, A
  • Biomedical term extraction: overview and a new methodology
    Lossio-Ventura, JA; Jonquet, C; Roche, M; Teisseire, M
  • The effect of citation analysis on query expansion for patent retrieval
    Mahdabi, P; Crestani, F
  • Textual keyword extraction and summarization: state-of-the-art
    Nasar, Z; Jaffry, SW; Malik, MK
  • Keyphrase extraction using knowledge graphs
    Shi, W; Zheng, W; Yu, JX; Cheng, H; Zou, L
  • Using query logs of uspto patent examiners for automatic query expansion in patent searching
    Tannebaum, W; Rauber, A
  • A multi-centrality index for graph-based keyword extraction
    Vega-Oliveros, DA; Gomes, PS; Milios, EE; Berton, L
  • Evaluation and analysis of term scoring methods for term extraction
    Verberne, S; Sappelli, M; Hiemstra, D; Kraaij, W
  • Document keyphrases as subject metadata: Incorporating document key concepts in search results
    Wu, YFB; Li, Q
  • Using multiple query representations in patent prior-art search
    Zhou, D; Truran, M; Liu, J; Zhang, S
  • Connectionist learning procedures.
    Hinton GE
  • Patent keyword extraction algorithm based on distributed representation for patent classification
    J Hu, S Li, Y Yao, L Yu, G Yang, J Hu
  • Conditional random fields: Probabilistic models for segmenting and labeling sequence data.
    Lafferty JD, McCallum A, Pereira FCN
  • Neural architectures for named entity recognition.
    Lample G, Ballesteros M, Subramanian S, Kawakami K, Dyer C
  • Distributed representations of sentences and documents.
    Le Q, Mikolov T
  • Extracting indices from Japanese legal documents
    TTN Le, K Shirai, ML Nguyen, A Shimazu
  • ROUGE: A package for automatic evaluation of summaries.
    Lin CY
  • Clustering to find exemplar terms for keyphrase extraction.
    Liu Z, Li P, Zheng Y, Sun M
  • Automatic keyphrase extraction via topic decomposition.
    Liu Z, Huang W, Zheng Y, Sun M
  • Biomedical term extraction: overview and a new methodology
    JA Lossio-Ventura, C Jonquet, M Roche, M Teisseire
  • The effect of citation analysis on query expansion for patent retrieval
    P Mahdabi, F Crestani
  • Automatic catchphrase identification from legal court case documents.
    Mandal A, Ghosh K, Pal A, Ghosh S
  • Unsupervised approaches for measuring textual similarity between legal court case reports
    Mandal A, Ghosh K, Ghosh S, Mandal S
  • Human-competitive automatic topic indexing
    Medelyan O
  • Textual keyword extraction and summarization: state-of-the-art
    Z Nasar, SW Jaffry, MK Malik
  • Recurrent neural network-based models for recognizing requisite and effectuation parts in legal texts
    Nguyen S, Nguyen LM, Tojo S, Satoh K, Shimazu A
  • Applying information extraction for patent structure analysis.
    Okamoto M, Shan Z, Orihara R
  • Deep contextualized word representations.
    Peters M, Neumann M, Iyyer M, Gardner M, Clark C, Lee K, Zettlemoyer L
  • Citation summarization through keyphrase extraction.
    Qazvinian V, Radev DR, Özgür A
  • Keyphrase extraction using knowledge graphs
    W Shi, W Zheng, JX Yu, H Cheng, L Zou
  • Keyword and keyphrase extraction techniques: a literature review
    Siddiqi S, Sharan A
  • Nonparametric Statistics for the Behavioral Sciences
    Siegel S
  • Extraction of keywords of novelties from patent claims.
    Suzuki S, Takatsuka H
  • Using query logs of uspto patent examiners for automatic query expansion in patent searching
    W Tannebaum, A Rauber
  • A language model approach to keyphrase extraction.
    Tomokiyo T, Hurst M
  • Encoded summarization: summarizing documents into continuous vector space for legal case retrieval
    Tran V, Le Nguyen M, Tojo S, Satoh K
  • Automatic catchphrase extraction from legal case documents via scoring using deep neural networks
    Tran VD, Nguyen ML, Satoh K
  • Single and multiple layer bi-lstmcrf for recognizing requisite and effectuation parts in legal texts.
    Truong S, Le Minh N, Satoh K, Satoshi T, Shimazu A
  • A multi-centrality index for graph-based keyword extraction
    DA Vega-Oliveros, PS Gomes, EE Milios, L Berton
  • Evaluation and analysis of term scoring methods for term extraction
    S Verberne, M Sappelli, D Hiemstra, W Kraaij
  • Kea: Practical automatic keyphrase extraction.
    Witten IH, Paynter GW, Frank E, Gutwin C, Nevill-Manning CG
  • Document keyphrases as subject metadata: Incorporating document key concepts in search results
    YFB Wu, Q Li
  • Automatic extraction of catchphrases from software license agreement
    Zahoor F, Bajwa IS
  • How does NLP benefit legal system: A summary of legal artificial intelligence.
    Zhong H, Xiao C, Tu C, Zhang T, Liu Z, Sun M
  • Using multiple query representations in patent prior-art search
    D Zhou, M Truran, J Liu, S Zhang
  • Deep neural model with self-training for scientific keyphrase extraction
    Zhu X, Lyu C, Ji D, Liao H, Li F