Matches in SemOpenAlex for { <https://semopenalex.org/work/W4366991608> ?p ?o ?g. }
- W4366991608 endingPage "2032" @default.
- W4366991608 startingPage "2032" @default.
- W4366991608 abstract "Legal Judgment Prediction aims to automatically predict judgment outcomes based on descriptions of legal cases and established law articles, and has received increasing attention. In the preliminary work, several problems still have not been adequately solved. One is how to utilize limited but valuable label information. Existing methods mostly ignore the gap between the description of established articles and cases, but directly integrate them. Second, most studies ignore the mutual constraint among the subtasks, such as logically or semantically, each charge is only related to some specific articles. To address these issues, we first construct a crime similarity graph and then perform a distillation operation to collect discriminate keywords for each charge. Furthermore, we fuse these discriminative keywords instead of established article descriptions into case embedding with a cross-attention mechanism to obtain deep semantic representations of cases incorporating label information. Finally, under a constraint among subtasks, we optimize the one-hot representation of ground-truth labels to guarantee consistent results across the subtasks based on the label-enhancement algorithm. To verify the effectiveness and robustness of our framework, we conduct extensive experiments on two public datasets. The experimental results show that the proposed method outperforms the state-of-art models by 3.89%/7.92% and 1.23%/2.50% in the average MF1-score of the subtasks on CAIL-Small/Big, respectively." @default.
- W4366991608 created "2023-04-27" @default.
- W4366991608 creator A5001169680 @default.
- W4366991608 creator A5016386045 @default.
- W4366991608 creator A5038050410 @default.
- W4366991608 creator A5046345742 @default.
- W4366991608 creator A5091337485 @default.
- W4366991608 date "2023-04-25" @default.
- W4366991608 modified "2023-09-26" @default.
- W4366991608 title "An Approach Based on Cross-Attention Mechanism and Label-Enhancement Algorithm for Legal Judgment Prediction" @default.
- W4366991608 cites W1596717185 @default.
- W4366991608 cites W1979482500 @default.
- W4366991608 cites W2144211451 @default.
- W4366991608 cites W2330485005 @default.
- W4366991608 cites W2470673105 @default.
- W4366991608 cites W2798580467 @default.
- W4366991608 cites W2890026792 @default.
- W4366991608 cites W2973226110 @default.
- W4366991608 cites W2977487347 @default.
- W4366991608 cites W2981059842 @default.
- W4366991608 cites W2983258080 @default.
- W4366991608 cites W2983419145 @default.
- W4366991608 cites W2990113535 @default.
- W4366991608 cites W2997429021 @default.
- W4366991608 cites W3006170025 @default.
- W4366991608 cites W3034892514 @default.
- W4366991608 cites W3035310383 @default.
- W4366991608 cites W3035347809 @default.
- W4366991608 cites W3101273072 @default.
- W4366991608 cites W3103181983 @default.
- W4366991608 cites W3104871628 @default.
- W4366991608 cites W3106109117 @default.
- W4366991608 cites W3111099392 @default.
- W4366991608 cites W3156638011 @default.
- W4366991608 cites W3156831596 @default.
- W4366991608 cites W3172365208 @default.
- W4366991608 cites W3173549151 @default.
- W4366991608 cites W3176964086 @default.
- W4366991608 cites W3210120707 @default.
- W4366991608 cites W4207022113 @default.
- W4366991608 cites W4232533539 @default.
- W4366991608 cites W4292596001 @default.
- W4366991608 doi "https://doi.org/10.3390/math11092032" @default.
- W4366991608 hasPublicationYear "2023" @default.
- W4366991608 type Work @default.
- W4366991608 citedByCount "0" @default.
- W4366991608 crossrefType "journal-article" @default.
- W4366991608 hasAuthorship W4366991608A5001169680 @default.
- W4366991608 hasAuthorship W4366991608A5016386045 @default.
- W4366991608 hasAuthorship W4366991608A5038050410 @default.
- W4366991608 hasAuthorship W4366991608A5046345742 @default.
- W4366991608 hasAuthorship W4366991608A5091337485 @default.
- W4366991608 hasBestOaLocation W43669916081 @default.
- W4366991608 hasConcept C103278499 @default.
- W4366991608 hasConcept C104317684 @default.
- W4366991608 hasConcept C115961682 @default.
- W4366991608 hasConcept C119857082 @default.
- W4366991608 hasConcept C132525143 @default.
- W4366991608 hasConcept C154945302 @default.
- W4366991608 hasConcept C17744445 @default.
- W4366991608 hasConcept C185592680 @default.
- W4366991608 hasConcept C199539241 @default.
- W4366991608 hasConcept C2524010 @default.
- W4366991608 hasConcept C2776036281 @default.
- W4366991608 hasConcept C2776359362 @default.
- W4366991608 hasConcept C33923547 @default.
- W4366991608 hasConcept C41008148 @default.
- W4366991608 hasConcept C55493867 @default.
- W4366991608 hasConcept C63479239 @default.
- W4366991608 hasConcept C80444323 @default.
- W4366991608 hasConcept C94625758 @default.
- W4366991608 hasConcept C97931131 @default.
- W4366991608 hasConceptScore W4366991608C103278499 @default.
- W4366991608 hasConceptScore W4366991608C104317684 @default.
- W4366991608 hasConceptScore W4366991608C115961682 @default.
- W4366991608 hasConceptScore W4366991608C119857082 @default.
- W4366991608 hasConceptScore W4366991608C132525143 @default.
- W4366991608 hasConceptScore W4366991608C154945302 @default.
- W4366991608 hasConceptScore W4366991608C17744445 @default.
- W4366991608 hasConceptScore W4366991608C185592680 @default.
- W4366991608 hasConceptScore W4366991608C199539241 @default.
- W4366991608 hasConceptScore W4366991608C2524010 @default.
- W4366991608 hasConceptScore W4366991608C2776036281 @default.
- W4366991608 hasConceptScore W4366991608C2776359362 @default.
- W4366991608 hasConceptScore W4366991608C33923547 @default.
- W4366991608 hasConceptScore W4366991608C41008148 @default.
- W4366991608 hasConceptScore W4366991608C55493867 @default.
- W4366991608 hasConceptScore W4366991608C63479239 @default.
- W4366991608 hasConceptScore W4366991608C80444323 @default.
- W4366991608 hasConceptScore W4366991608C94625758 @default.
- W4366991608 hasConceptScore W4366991608C97931131 @default.
- W4366991608 hasFunder F4320321001 @default.
- W4366991608 hasIssue "9" @default.
- W4366991608 hasLocation W43669916081 @default.
- W4366991608 hasLocation W43669916082 @default.
- W4366991608 hasOpenAccess W4366991608 @default.
- W4366991608 hasPrimaryLocation W43669916081 @default.
- W4366991608 hasRelatedWork W2026121273 @default.