Matches in SemOpenAlex for { <https://semopenalex.org/work/W4384080571> ?p ?o ?g. }
- W4384080571 endingPage "2795" @default.
- W4384080571 startingPage "2787" @default.
- W4384080571 abstract "The fast spread of hate speech on social media impacts the Internet environment and our society by increasing prejudice and hurting people. Detecting hate speech has aroused broad attention in the field of natural language processing. Although hate speech detection has been addressed in recent work, this task still faces two inherent unsolved challenges. The first challenge lies in the complex semantic information conveyed in hate speech, particularly the interference of insulting words in hate speech detection. The second challenge is the imbalanced distribution of hate speech and non-hate speech, which may significantly deteriorate the performance of models. To tackle these challenges, we propose a novel dual contrastive learning (DCL) framework for hate speech detection. Our framework jointly optimizes the self-supervised and the supervised contrastive learning loss for capturing span-level information beyond the token-level emotional semantics used in existing models, particularly detecting speech containing abusive and insulting words. Moreover, we integrate the focal loss into the dual contrastive learning framework to alleviate the problem of data imbalance. We conduct experiments on two publicly available English datasets, and experimental results show that the proposed model outperforms the state-of-the-art models and precisely detects hate speeches." @default.
- W4384080571 created "2023-07-13" @default.
- W4384080571 creator A5001030192 @default.
- W4384080571 creator A5016649343 @default.
- W4384080571 creator A5023931221 @default.
- W4384080571 creator A5030649664 @default.
- W4384080571 creator A5040724695 @default.
- W4384080571 creator A5049585151 @default.
- W4384080571 creator A5062895972 @default.
- W4384080571 creator A5084190619 @default.
- W4384080571 date "2023-01-01" @default.
- W4384080571 modified "2023-10-09" @default.
- W4384080571 title "Hate Speech Detection via Dual Contrastive Learning" @default.
- W4384080571 cites W2160685721 @default.
- W4384080571 cites W2493916176 @default.
- W4384080571 cites W2564933006 @default.
- W4384080571 cites W2595653137 @default.
- W4384080571 cites W2806872289 @default.
- W4384080571 cites W2809034148 @default.
- W4384080571 cites W2953980153 @default.
- W4384080571 cites W2954226438 @default.
- W4384080571 cites W2955042007 @default.
- W4384080571 cites W2963351448 @default.
- W4384080571 cites W3000571327 @default.
- W4384080571 cites W3034403876 @default.
- W4384080571 cites W3087124270 @default.
- W4384080571 cites W3094411615 @default.
- W4384080571 cites W3104674089 @default.
- W4384080571 cites W3110446398 @default.
- W4384080571 cites W3118142489 @default.
- W4384080571 cites W3156636935 @default.
- W4384080571 cites W3173171735 @default.
- W4384080571 cites W3173268697 @default.
- W4384080571 cites W3174490084 @default.
- W4384080571 cites W4220873374 @default.
- W4384080571 cites W4225603069 @default.
- W4384080571 cites W4282937884 @default.
- W4384080571 cites W4284968770 @default.
- W4384080571 cites W4290713716 @default.
- W4384080571 doi "https://doi.org/10.1109/taslp.2023.3294715" @default.
- W4384080571 hasPublicationYear "2023" @default.
- W4384080571 type Work @default.
- W4384080571 citedByCount "1" @default.
- W4384080571 crossrefType "journal-article" @default.
- W4384080571 hasAuthorship W4384080571A5001030192 @default.
- W4384080571 hasAuthorship W4384080571A5016649343 @default.
- W4384080571 hasAuthorship W4384080571A5023931221 @default.
- W4384080571 hasAuthorship W4384080571A5030649664 @default.
- W4384080571 hasAuthorship W4384080571A5040724695 @default.
- W4384080571 hasAuthorship W4384080571A5049585151 @default.
- W4384080571 hasAuthorship W4384080571A5062895972 @default.
- W4384080571 hasAuthorship W4384080571A5084190619 @default.
- W4384080571 hasConcept C138885662 @default.
- W4384080571 hasConcept C154945302 @default.
- W4384080571 hasConcept C184337299 @default.
- W4384080571 hasConcept C199360897 @default.
- W4384080571 hasConcept C202444582 @default.
- W4384080571 hasConcept C204201278 @default.
- W4384080571 hasConcept C204321447 @default.
- W4384080571 hasConcept C2780980858 @default.
- W4384080571 hasConcept C28490314 @default.
- W4384080571 hasConcept C33923547 @default.
- W4384080571 hasConcept C38652104 @default.
- W4384080571 hasConcept C41008148 @default.
- W4384080571 hasConcept C41895202 @default.
- W4384080571 hasConcept C48145219 @default.
- W4384080571 hasConcept C61328038 @default.
- W4384080571 hasConcept C9652623 @default.
- W4384080571 hasConceptScore W4384080571C138885662 @default.
- W4384080571 hasConceptScore W4384080571C154945302 @default.
- W4384080571 hasConceptScore W4384080571C184337299 @default.
- W4384080571 hasConceptScore W4384080571C199360897 @default.
- W4384080571 hasConceptScore W4384080571C202444582 @default.
- W4384080571 hasConceptScore W4384080571C204201278 @default.
- W4384080571 hasConceptScore W4384080571C204321447 @default.
- W4384080571 hasConceptScore W4384080571C2780980858 @default.
- W4384080571 hasConceptScore W4384080571C28490314 @default.
- W4384080571 hasConceptScore W4384080571C33923547 @default.
- W4384080571 hasConceptScore W4384080571C38652104 @default.
- W4384080571 hasConceptScore W4384080571C41008148 @default.
- W4384080571 hasConceptScore W4384080571C41895202 @default.
- W4384080571 hasConceptScore W4384080571C48145219 @default.
- W4384080571 hasConceptScore W4384080571C61328038 @default.
- W4384080571 hasConceptScore W4384080571C9652623 @default.
- W4384080571 hasFunder F4320321001 @default.
- W4384080571 hasFunder F4320323086 @default.
- W4384080571 hasLocation W43840805711 @default.
- W4384080571 hasOpenAccess W4384080571 @default.
- W4384080571 hasPrimaryLocation W43840805711 @default.
- W4384080571 hasRelatedWork W2069501481 @default.
- W4384080571 hasRelatedWork W2099105119 @default.
- W4384080571 hasRelatedWork W2164637175 @default.
- W4384080571 hasRelatedWork W2360836312 @default.
- W4384080571 hasRelatedWork W2603275087 @default.
- W4384080571 hasRelatedWork W3002577753 @default.
- W4384080571 hasRelatedWork W3135230428 @default.
- W4384080571 hasRelatedWork W4309395076 @default.
- W4384080571 hasRelatedWork W642007152 @default.