Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313303786> ?p ?o ?g. }
Showing items 1 to 77 of
77
with 100 items per page.
- W4313303786 abstract "Legal text retrieval serves as a key component in a wide range of legal text processing tasks such as legal question answering, legal case entailment, and statute law retrieval. The performance of legal text retrieval depends, to a large extent, on the representation of text, both query and legal documents. Based on good representations, a legal text retrieval model can effectively match the query to its relevant documents. Because legal documents often contain long articles and only some parts are relevant to queries, it is quite a challenge for existing models to represent such documents. In this paper, we study the use of attentive neural network-based text representation for statute law document retrieval. We propose a general approach using deep neural networks with attention mechanisms. Based on it, we develop two hierarchical architectures with sparse attention to represent long sentences and articles, and we name them Attentive CNN and Paraformer. The methods are evaluated on datasets of different sizes and characteristics in English, Japanese, and Vietnamese. Experimental results show that: i) Attentive neural methods substantially outperform non-neural methods in terms of retrieval performance across datasets and languages; ii) Pretrained transformer-based models achieve better accuracy on small datasets at the cost of high computational complexity while lighter weight Attentive CNN achieves better accuracy on large datasets; and iii) Our proposed Paraformer outperforms state-of-the-art methods on COLIEE dataset, achieving the highest recall and F2 scores in the top-N retrieval task." @default.
- W4313303786 created "2023-01-06" @default.
- W4313303786 creator A5012147485 @default.
- W4313303786 creator A5016730960 @default.
- W4313303786 creator A5018668377 @default.
- W4313303786 creator A5045723152 @default.
- W4313303786 creator A5077641909 @default.
- W4313303786 creator A5090342694 @default.
- W4313303786 date "2022-12-12" @default.
- W4313303786 modified "2023-09-27" @default.
- W4313303786 title "Attentive Deep Neural Networks for Legal Document Retrieval" @default.
- W4313303786 doi "https://doi.org/10.48550/arxiv.2212.13899" @default.
- W4313303786 hasPublicationYear "2022" @default.
- W4313303786 type Work @default.
- W4313303786 citedByCount "0" @default.
- W4313303786 crossrefType "posted-content" @default.
- W4313303786 hasAuthorship W4313303786A5012147485 @default.
- W4313303786 hasAuthorship W4313303786A5016730960 @default.
- W4313303786 hasAuthorship W4313303786A5018668377 @default.
- W4313303786 hasAuthorship W4313303786A5045723152 @default.
- W4313303786 hasAuthorship W4313303786A5077641909 @default.
- W4313303786 hasAuthorship W4313303786A5090342694 @default.
- W4313303786 hasBestOaLocation W43133037861 @default.
- W4313303786 hasConcept C121332964 @default.
- W4313303786 hasConcept C154945302 @default.
- W4313303786 hasConcept C161156560 @default.
- W4313303786 hasConcept C162324750 @default.
- W4313303786 hasConcept C165801399 @default.
- W4313303786 hasConcept C17744445 @default.
- W4313303786 hasConcept C187736073 @default.
- W4313303786 hasConcept C199539241 @default.
- W4313303786 hasConcept C204321447 @default.
- W4313303786 hasConcept C23123220 @default.
- W4313303786 hasConcept C2776359362 @default.
- W4313303786 hasConcept C2780451532 @default.
- W4313303786 hasConcept C41008148 @default.
- W4313303786 hasConcept C44291984 @default.
- W4313303786 hasConcept C50644808 @default.
- W4313303786 hasConcept C62520636 @default.
- W4313303786 hasConcept C66322947 @default.
- W4313303786 hasConcept C81669768 @default.
- W4313303786 hasConcept C94625758 @default.
- W4313303786 hasConceptScore W4313303786C121332964 @default.
- W4313303786 hasConceptScore W4313303786C154945302 @default.
- W4313303786 hasConceptScore W4313303786C161156560 @default.
- W4313303786 hasConceptScore W4313303786C162324750 @default.
- W4313303786 hasConceptScore W4313303786C165801399 @default.
- W4313303786 hasConceptScore W4313303786C17744445 @default.
- W4313303786 hasConceptScore W4313303786C187736073 @default.
- W4313303786 hasConceptScore W4313303786C199539241 @default.
- W4313303786 hasConceptScore W4313303786C204321447 @default.
- W4313303786 hasConceptScore W4313303786C23123220 @default.
- W4313303786 hasConceptScore W4313303786C2776359362 @default.
- W4313303786 hasConceptScore W4313303786C2780451532 @default.
- W4313303786 hasConceptScore W4313303786C41008148 @default.
- W4313303786 hasConceptScore W4313303786C44291984 @default.
- W4313303786 hasConceptScore W4313303786C50644808 @default.
- W4313303786 hasConceptScore W4313303786C62520636 @default.
- W4313303786 hasConceptScore W4313303786C66322947 @default.
- W4313303786 hasConceptScore W4313303786C81669768 @default.
- W4313303786 hasConceptScore W4313303786C94625758 @default.
- W4313303786 hasLocation W43133037861 @default.
- W4313303786 hasOpenAccess W4313303786 @default.
- W4313303786 hasPrimaryLocation W43133037861 @default.
- W4313303786 hasRelatedWork W128416478 @default.
- W4313303786 hasRelatedWork W1487889746 @default.
- W4313303786 hasRelatedWork W1527340856 @default.
- W4313303786 hasRelatedWork W155133298 @default.
- W4313303786 hasRelatedWork W1602736231 @default.
- W4313303786 hasRelatedWork W1830854354 @default.
- W4313303786 hasRelatedWork W2151407063 @default.
- W4313303786 hasRelatedWork W2429147410 @default.
- W4313303786 hasRelatedWork W3077892130 @default.
- W4313303786 hasRelatedWork W83344948 @default.
- W4313303786 isParatext "false" @default.
- W4313303786 isRetracted "false" @default.
- W4313303786 workType "article" @default.