Abstract
Precedence retrieval is the process of retrieving similar prior case documents for the given current case document in the legal domain. Referencing the prior cases is important to ensure that an identical situation is treated similarly in all the cases. Concise representation of case documents using catch phrases facilitates the practitioners to avoid spending more time on reading the whole documents for finding the prior cases. The existing approaches for precedent retrieval in the legal domain use either statistical or semantic similarity features to find the prior cases. However, the substruction similarity features that consider the context of the statement helps to correctly identify the prior cases. Further, the existing approaches consider the whole document while extracting the similarity features, which is time-consuming. In this paper, we propose to use a combination of statistical, semantic, and substruction similarity features that are extracted from the catch phrases of the legal documents. The catch phrases from legal documents are extracted by utilizing Sequence-to-Sequence deep neural network with stacked encoder-decoder and Long Short Term Memory (LSTM) as the recurrent unit. The substruction similarity features are obtained using a convolutional neural network. The IRLeD@FIRE-2017 dataset is used for evaluating our approach. The experimental results show that considering catch phrases reduces the retrieval time without reducing the retrieval performance. The k-paired t-test also shows that the improvement in performance of the model by using substruction similarity features that are extracted from the catch phrases is statistically significant when compared with other models. The PReLCaP outperforms state-of-the-art approaches with the MAP score of 0.632 on test data.
Similar content being viewed by others
References
Akkalyoncu Yilmaz Z, Wang S, Yang W, Zhang H, Lin J (2019) “Applying BERT to Document Retrieval with Birc”. In: Proceedings of the 2019 conference on empirical methods in natural language processing and the 9th international joint conference on natural language processing (EMNLP-IJCNLP): system demonstrations, association for computational linguistics, Hong Kong, China, pp 19–24., https://doi.org/10.18653/v1/D19-3004
Allard T, Béziaud L, Gambs S (2020) “Online publication of court records: circumventing the privacy-transparency trade-off. eprint2007.01688
Almuslim I, Inkpen D (2020) Document level embeddings for identifying similar legal cases and laws (aila 2020 shared task). Proceedings of FIRE pp 42–48
Aroraa J, Patankara T, Shaha A, Joshia S (2020) Artificial intelligence as legal research assistant. FIRE (Working Notes) pp 60–65
Balaji NNA, Bharathi B, Bhuvana J (2020) Legal information retrieval and rhetorical role labelling for legal judgements. In: FIRE (Working Notes), pp 26–30
Barathi Ganesh H, Reshma U, Anand Kumar M, Soman K (2017) “Distributed representation in information retrieval - Amrita_cen_nlp@irled 2017”. FIRE (CEUR Vol-2036) pp 69–71
Bhattacharya P, Ghosh K, Ghosh S, Pal A, Mehta P, Bhattacharya A, Majumder P (2019) “Overview of the FIRE 2019 AILA track: artificial intelligence for legal assistance”. In: FIRE (CEUR Vol-2517), pp 1–12
Caserta S (2020) Digitalization of the legal field and the future of large law firms. Laws 9(2):14
Devyatkin D, Sofronova A, Yadrintsev V (2020) Revealing implicit relations in Russian legal texts. In: Kuznetsov SO, Panov AI, Yakovlev KS (eds) Artificial intelligence. Springer International Publishing, Cham, pp 228–239
Di Nunzioa GM (2020) A study on lemma vs stem for legal information retrieval using r tidyverse. ims unipd@ aila 2020 task pp 54–59
Eto M (2019) Extended co-citation search: Graph-based document retrieval on a co-citation network containing citation context information. Inf Process Manag 56(6):102046
Fink T, Recski G, Hanbury A (2020) Fire2020 aila track: legal domain search with minimal domain knowledge. In: FIRE (Working Notes), pp 76–81
Gain B, Bandyopadhyay D, De A, Saikh T, Ekbal A (2021) Iitp at aila 2019: System report for artificial intelligence for legal assistance shared task. arXiv preprint arXiv:2105.11347
Gao J, Ning H, Sun H, Liu R, Han Z, Kong L, Qi H (2019) Fire2019@ aila: Legal retrieval based on information retrieval model. In: FIRE (Working Notes), pp 64–69
Hao S, Shi C, Niu Z, Cao L (2018) Concept coupling learning for improving concept lattice-based document retrieval. Eng Appl Artif Intell 69:65–75. https://doi.org/10.1016/j.engappai.2017.12.007
Hofst atter S, Zamani H, Mitra B, Craswell N, Hanbury A (2020) Local self-attention over long text for efficient document retrieval, Association for computing machinery, New York, NY, USA, p 2021-2024. https://doi.org/10.1145/3397271.3401224
Kayalvizhi S, Thenmozhi D (2020) Deep learning approach for extracting catch phrases from legal documents. In: Neural networks for natural language processing, IGI Global, pp 143–158
Kayalvizhi S, Thenmozhi D, Aravindan C (2019) Legal assistance using word embeddings. In: FIRE (Working Notes), pp 36–39
Kayalvizhi S, Thenmozhi D, Aravindan C (2020) Best matching algorithm to identify and rank the relevant statutes. In: Proceedings of FIRE pp 31–34
Kulkarni YH, Patil R, Shridharan S (2017) Detection of catchphrases and precedence in legal documents. In: FIRE (CEUR Vol-2036), pp 86–89
Kuzi S, Zhang M, Li C, Bendersky M, Najork M (2020) Leveraging semantic and lexical matching to improve the recall of document retrieval systems: a hybrid approach
Leburu-Dingalo T, Motlogelwa NP, Thuma E, Modongo M (2020) Ub at fire 2020 precedent and statute retrieval. In: FIRE (Working Notes), pp 12–17
Lefoane M, Koboyatshwene T, Narasimhan L (2018) KNN clustering approach to legal precedence retrieval. In: Twelfth international workshop on juris-informatics (JURISIN 2018)
Li G, Wang Z, Ma Y (2019) Combining domain knowledge extraction with graph long short-term memory for learning classification of Chinese legal documents. IEEE Access 7:139616–139627. https://doi.org/10.1109/ACCESS.2019.2943668
Liu L, Liu L, Han Z (2020) Query revaluation method for legal information retrieval. In: FIRE (Working Notes), pp 18–21
Locke D, Zuccon G (2017) Automatic cited decision retrieval: working notes of Ielab for FIRE legal track precedence retrieval task. FIRE (CEUR Vol-2036) pp 80–81
Ma Y, Zhang P, Ma J (2018) An efficient approach to learning chinese judgment document similarity based on knowledge summarization. eprint1808.01843
Mandal A, Ghosh K, Bhattacharya A, Pal A, Ghosh S (2017) Overview of the FIRE 2017 IRLeD track: information retrieval from legal Documents. In: FIRE (CEUR Vol-2036), pp 63–68
Mandal S, Das SD (2019) Unsupervised identification of relevant cases & statutes using word embeddings. In: FIRE (Working Notes), pp 31–35
Maxwell T, Schafer B (2008) Concept and context in legal information retrieval. 189:63–72. https://doi.org/10.3233/978-1-58603-952-3-63
More R, Patil J, Palaskar A, Pawde A (2019) Removing named entities to find precedent legal cases. In: FIRE (Working Notes), pp 13–18
Padigi SV, Mayank M, Natarajan S (2019) Precedent case retrieval using wordnet and deep recurrent neural networks
Rameshkannan R, Rajalakshmi R (2019) Dlrg@ aila 2019: context-aware legal assistance system. In: Proceedings of FIRE
Renjit S, Idicula SM (2019) Cusat nlp@ aila-fire2019: similarity in legal texts using document level embeddings. In: FIRE (Working Notes), pp 25–30
Sandeep G, Bharadwaj S (2017) An extraction based approach to keyword generation and precedence retrieval: BITS Pilani-Hyderabad. In: FIRE (CEUR Vol-2036), pp 74–77
Sugathadasa K, Ayesha B, de Silva N, Perera AS, Jayawardana V, Lakmal D, Perera M (2018) Legal document retrieval using document vector embeddings and deep learning. In: Science and information conference, Springer, pp 160–175
Thenmozhi D, Kannan K, Aravindan C (2017) A text similarity approach for precedence retrieval from legal documents. In: FIRE (CEUR Vol-2036), pp 90–91
Tian L, Ning H, Kong L, Han Z, Xiao R, Qi H (2017) HLJIT2017@ IRLed-FIRE2017: information retrieval from legal documents. In: FIRE (CEUR Vol-2036), pp 82–85
Van Opijnen M, Santos C (2017) On the concept of relevance in legal information retrieval. Artif Intell Law 25(1):65–87
Wu M, Wu Z, Wang X, Han Z (2020) Retrieval model and classification model for aila2020. In: FIRE (Working Notes), pp 82–86
Xu Y, Li T, Han Z (2020) The language model for legal retrieval and bert-based model for rhetorical role labeling for legal judgments. In: FIRE (Working Notes), pp 71–75
Yang W, Zhang H, Lin J (2019) Simple applications of BERT for Ad Hoc document retrieval. eprint1903.10972
Zhao Z, Ning H, Liu L, Huang C, Kong L, Han Y, Han Z (2019) Fire 2019@ aila: Legal information retrieval using improved bm25. FIRE (Working Notes) 2517:40–45
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Sampath, K., Durairaj, T. PReLCaP : Precedence Retrieval from Legal Documents Using Catch Phrases. Neural Process Lett 54, 3873–3891 (2022). https://doi.org/10.1007/s11063-022-10791-z
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11063-022-10791-z