English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Legal case retrieval is an information retrieval task in the legal domain,which aims to retrieve relevant cases with a given query case. Recent researchof legal case retrieval mainly relies on traditional bag-of-words models andlanguage models. Although these methods have achieved significant improvementin retrieval accuracy, there are still two challenges: (1) Legal structuralinformation neglect. Previous neural legal case retrieval models mostly encodethe unstructured raw text of case into a case representation, which causes thelack of important legal structural information in a case and leads to poor caserepresentation; (2) Lengthy legal text limitation. When using the powerfulBERT-based models, there is a limit of input text lengths, which inevitablyrequires to shorten the input via truncation or division with a loss of legalcontext information. In this paper, a graph neural networks-based legal caseretrieval model, CaseGNN, is developed to tackle these challenges. Toeffectively utilise the legal structural information during encoding, a case isfirstly converted into a Text-Attributed Case Graph (TACG), followed by adesigned Edge Graph Attention Layer and a readout function to obtain the casegraph representation. The CaseGNN model is optimised with a carefully designedcontrastive loss with easy and hard negative sampling. Since the textattributes in the case graph come from individual sentences, the restriction ofusing language models is further avoided without losing the legal context.Extensive experiments have been conducted on two benchmarks from COLIEE 2022and COLIEE 2023, which demonstrate that CaseGNN outperforms otherstate-of-the-art legal case retrieval methods. The code has been released onhttps://github.com/yanran-tang/CaseGNN.

CaseGNN: Graph Neural Networks for Legal Case Retrieval with Text-Attributed Graphs