FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313257365> ?p ?o ?g. }

• W4313257365 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.
• W4313257365 created "2023-01-06" @default.
• W4313257365 creator A5012147485 @default.
• W4313257365 creator A5012671676 @default.
• W4313257365 creator A5016730960 @default.
• W4313257365 creator A5045723152 @default.
• W4313257365 creator A5077641909 @default.
• W4313257365 creator A5090342694 @default.
• W4313257365 date "2022-12-27" @default.
• W4313257365 modified "2023-09-27" @default.
• W4313257365 title "Attentive deep neural networks for legal document retrieval" @default.
• W4313257365 cites W1832693441 @default.
• W4313257365 cites W1966443646 @default.
• W4313257365 cites W1978394996 @default.
• W4313257365 cites W1985697096 @default.
• W4313257365 cites W1994559819 @default.
• W4313257365 cites W2131876387 @default.
• W4313257365 cites W2136189984 @default.
• W4313257365 cites W2171928131 @default.
• W4313257365 cites W2250539671 @default.
• W4313257365 cites W2250966211 @default.
• W4313257365 cites W2508865106 @default.
• W4313257365 cites W2562607067 @default.
• W4313257365 cites W2608787653 @default.
• W4313257365 cites W2770344018 @default.
• W4313257365 cites W2789335858 @default.
• W4313257365 cites W2903938540 @default.
• W4313257365 cites W2964259149 @default.
• W4313257365 cites W2969991835 @default.
• W4313257365 cites W2970641574 @default.
• W4313257365 cites W2996274640 @default.
• W4313257365 cites W3001873397 @default.
• W4313257365 cites W3034707327 @default.
• W4313257365 cites W3034999214 @default.
• W4313257365 cites W3035390927 @default.
• W4313257365 cites W3086962592 @default.
• W4313257365 cites W3117737817 @default.
• W4313257365 cites W3122775348 @default.
• W4313257365 cites W31369764 @default.
• W4313257365 cites W3180395890 @default.
• W4313257365 cites W3184496804 @default.
• W4313257365 cites W3186948566 @default.
• W4313257365 cites W3190892098 @default.
• W4313257365 cites W4200106686 @default.
• W4313257365 cites W4210931461 @default.
• W4313257365 doi "https://doi.org/10.1007/s10506-022-09341-8" @default.
• W4313257365 hasPublicationYear "2022" @default.
• W4313257365 type Work @default.
• W4313257365 citedByCount "0" @default.
• W4313257365 crossrefType "journal-article" @default.
• W4313257365 hasAuthorship W4313257365A5012147485 @default.
• W4313257365 hasAuthorship W4313257365A5012671676 @default.
• W4313257365 hasAuthorship W4313257365A5016730960 @default.
• W4313257365 hasAuthorship W4313257365A5045723152 @default.
• W4313257365 hasAuthorship W4313257365A5077641909 @default.
• W4313257365 hasAuthorship W4313257365A5090342694 @default.
• W4313257365 hasBestOaLocation W43132573652 @default.
• W4313257365 hasConcept C121332964 @default.
• W4313257365 hasConcept C154945302 @default.
• W4313257365 hasConcept C161156560 @default.
• W4313257365 hasConcept C162324750 @default.
• W4313257365 hasConcept C165801399 @default.
• W4313257365 hasConcept C17744445 @default.
• W4313257365 hasConcept C187736073 @default.
• W4313257365 hasConcept C199539241 @default.
• W4313257365 hasConcept C204321447 @default.
• W4313257365 hasConcept C23123220 @default.
• W4313257365 hasConcept C2776359362 @default.
• W4313257365 hasConcept C2780451532 @default.
• W4313257365 hasConcept C41008148 @default.
• W4313257365 hasConcept C44291984 @default.
• W4313257365 hasConcept C50644808 @default.
• W4313257365 hasConcept C62520636 @default.
• W4313257365 hasConcept C66322947 @default.
• W4313257365 hasConcept C81669768 @default.
• W4313257365 hasConcept C94625758 @default.
• W4313257365 hasConceptScore W4313257365C121332964 @default.
• W4313257365 hasConceptScore W4313257365C154945302 @default.
• W4313257365 hasConceptScore W4313257365C161156560 @default.
• W4313257365 hasConceptScore W4313257365C162324750 @default.
• W4313257365 hasConceptScore W4313257365C165801399 @default.
• W4313257365 hasConceptScore W4313257365C17744445 @default.
• W4313257365 hasConceptScore W4313257365C187736073 @default.
• W4313257365 hasConceptScore W4313257365C199539241 @default.
• W4313257365 hasConceptScore W4313257365C204321447 @default.
• W4313257365 hasConceptScore W4313257365C23123220 @default.
• W4313257365 hasConceptScore W4313257365C2776359362 @default.
• W4313257365 hasConceptScore W4313257365C2780451532 @default.
• W4313257365 hasConceptScore W4313257365C41008148 @default.
• W4313257365 hasConceptScore W4313257365C44291984 @default.
• W4313257365 hasConceptScore W4313257365C50644808 @default.
• W4313257365 hasConceptScore W4313257365C62520636 @default.
• W4313257365 hasConceptScore W4313257365C66322947 @default.
• W4313257365 hasConceptScore W4313257365C81669768 @default.
• W4313257365 hasConceptScore W4313257365C94625758 @default.
• W4313257365 hasFunder F4320334764 @default.
• W4313257365 hasFunder F4320338279 @default.
• W4313257365 hasLocation W43132573651 @default.
• W4313257365 hasLocation W43132573652 @default.
• W4313257365 hasLocation W43132573653 @default.

• next