Matches in SemOpenAlex for { <https://semopenalex.org/work/W4387537160> ?p ?o ?g. }
Showing items 1 to 88 of
88
with 100 items per page.
- W4387537160 abstract "Although the existing Multimodal Named Entity Recognition (MNER) methods have achieved promising performance, they suffer from the following drawbacks in social media scenarios. Firstly, most existing methods are based on a strong assumption that the textual content and the associated images are matched, which is not always valid in real scenarios; Secondly, current methods fail to filter out modality-specific random noise, which impedes models from exploiting modality-shared features. In this paper, a novel multi-task multimodal learning architecture is put forward, which aims to improve Multimodal Named Entity Recognition (MNER) performance by cross-modal auxiliary tasks (CMAT). Specifically, we first separate the shared and task-specific features for the main task and auxiliary tasks respectively, which is accomplished by cross-modal gate-control mechanism. Subsequently, without extra pre-processing or annotations, we utilize the cross-modal matching to address the issue of mismatched image-text pairs, and the cross-modal mutual information maximization to optimize the most relevant cross-modal features. Moreover, experimental results on the two widely used datasets confirm the superiority of our proposed approach." @default.
- W4387537160 created "2023-10-12" @default.
- W4387537160 creator A5046184663 @default.
- W4387537160 creator A5049776286 @default.
- W4387537160 creator A5059350974 @default.
- W4387537160 date "2023-10-01" @default.
- W4387537160 modified "2023-10-12" @default.
- W4387537160 title "Assisting Multimodal Named Entity Recognition by cross-modal auxiliary tasks" @default.
- W4387537160 cites W2008830554 @default.
- W4387537160 cites W2045993505 @default.
- W4387537160 cites W2141099517 @default.
- W4387537160 cites W2626680156 @default.
- W4387537160 cites W2788647998 @default.
- W4387537160 cites W2798298921 @default.
- W4387537160 cites W2887734252 @default.
- W4387537160 cites W2913340405 @default.
- W4387537160 cites W2943547402 @default.
- W4387537160 cites W2970231061 @default.
- W4387537160 cites W3132069728 @default.
- W4387537160 cites W3139240072 @default.
- W4387537160 cites W3176858586 @default.
- W4387537160 cites W3182683290 @default.
- W4387537160 cites W3211950664 @default.
- W4387537160 cites W4212998232 @default.
- W4387537160 doi "https://doi.org/10.1016/j.patrec.2023.10.004" @default.
- W4387537160 hasPublicationYear "2023" @default.
- W4387537160 type Work @default.
- W4387537160 citedByCount "0" @default.
- W4387537160 crossrefType "journal-article" @default.
- W4387537160 hasAuthorship W4387537160A5046184663 @default.
- W4387537160 hasAuthorship W4387537160A5049776286 @default.
- W4387537160 hasAuthorship W4387537160A5059350974 @default.
- W4387537160 hasConcept C105795698 @default.
- W4387537160 hasConcept C115961682 @default.
- W4387537160 hasConcept C119857082 @default.
- W4387537160 hasConcept C153180895 @default.
- W4387537160 hasConcept C154945302 @default.
- W4387537160 hasConcept C162324750 @default.
- W4387537160 hasConcept C165064840 @default.
- W4387537160 hasConcept C175444787 @default.
- W4387537160 hasConcept C185592680 @default.
- W4387537160 hasConcept C187736073 @default.
- W4387537160 hasConcept C188027245 @default.
- W4387537160 hasConcept C204321447 @default.
- W4387537160 hasConcept C2776330181 @default.
- W4387537160 hasConcept C2780226545 @default.
- W4387537160 hasConcept C2780451532 @default.
- W4387537160 hasConcept C28490314 @default.
- W4387537160 hasConcept C33923547 @default.
- W4387537160 hasConcept C41008148 @default.
- W4387537160 hasConcept C71139939 @default.
- W4387537160 hasConcept C99498987 @default.
- W4387537160 hasConceptScore W4387537160C105795698 @default.
- W4387537160 hasConceptScore W4387537160C115961682 @default.
- W4387537160 hasConceptScore W4387537160C119857082 @default.
- W4387537160 hasConceptScore W4387537160C153180895 @default.
- W4387537160 hasConceptScore W4387537160C154945302 @default.
- W4387537160 hasConceptScore W4387537160C162324750 @default.
- W4387537160 hasConceptScore W4387537160C165064840 @default.
- W4387537160 hasConceptScore W4387537160C175444787 @default.
- W4387537160 hasConceptScore W4387537160C185592680 @default.
- W4387537160 hasConceptScore W4387537160C187736073 @default.
- W4387537160 hasConceptScore W4387537160C188027245 @default.
- W4387537160 hasConceptScore W4387537160C204321447 @default.
- W4387537160 hasConceptScore W4387537160C2776330181 @default.
- W4387537160 hasConceptScore W4387537160C2780226545 @default.
- W4387537160 hasConceptScore W4387537160C2780451532 @default.
- W4387537160 hasConceptScore W4387537160C28490314 @default.
- W4387537160 hasConceptScore W4387537160C33923547 @default.
- W4387537160 hasConceptScore W4387537160C41008148 @default.
- W4387537160 hasConceptScore W4387537160C71139939 @default.
- W4387537160 hasConceptScore W4387537160C99498987 @default.
- W4387537160 hasLocation W43875371601 @default.
- W4387537160 hasOpenAccess W4387537160 @default.
- W4387537160 hasPrimaryLocation W43875371601 @default.
- W4387537160 hasRelatedWork W2361654993 @default.
- W4387537160 hasRelatedWork W2364381299 @default.
- W4387537160 hasRelatedWork W2374013449 @default.
- W4387537160 hasRelatedWork W2374430585 @default.
- W4387537160 hasRelatedWork W2377397762 @default.
- W4387537160 hasRelatedWork W2385859805 @default.
- W4387537160 hasRelatedWork W2392886218 @default.
- W4387537160 hasRelatedWork W2530972254 @default.
- W4387537160 hasRelatedWork W627697492 @default.
- W4387537160 hasRelatedWork W73545470 @default.
- W4387537160 isParatext "false" @default.
- W4387537160 isRetracted "false" @default.
- W4387537160 workType "article" @default.