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

In this paper, we present our approaches for the case law retrieval and thelegal case entailment task in the Competition on Legal InformationExtraction/Entailment (COLIEE) 2021. As first stage retrieval methods combinedwith neural re-ranking methods using contextualized language models like BERTachieved great performance improvements for information retrieval in the weband news domain, we evaluate these methods for the legal domain. A distinctcharacteristic of legal case retrieval is that the query case and casedescription in the corpus tend to be long documents and therefore exceed theinput length of BERT. We address this challenge by combining lexical and denseretrieval methods on the paragraph-level of the cases for the first stageretrieval. Here we demonstrate that the retrieval on the paragraph-leveloutperforms the retrieval on the document-level. Furthermore the experimentssuggest that dense retrieval methods outperform lexical retrieval. Forre-ranking we address the problem of long documents by summarizing the casesand fine-tuning a BERT-based re-ranker with the summaries. Overall, our bestresults were obtained with a combination of BM25 and dense passage retrievalusing domain-specific embeddings.

DoSSIER@COLIEE 2021: Leveraging dense retrieval and summarization-based re-ranking for case law retrieval