Matches in SemOpenAlex for { <https://semopenalex.org/work/W4372260428> ?p ?o ?g. }
Showing items 1 to 90 of
90
with 100 items per page.
- W4372260428 abstract "Multi-label text classification, which aims to predict the relevant labels for each given document, is one of the fundamental tasks of natural language processing. Recent studies have utilized Transformer, which embeds texts and class labels into a joint space to capture the label correlation. However, existing methods tend to take up extra input length and ignore the significance of taxonomic hierarchy. For this reason, we introduce a label correlation enhanced decoder (LED) for multi-label text classification. LED predicts the presence or absence of class labels in parallel with label representation and captures label correlation through multi-task learning. In addition, we propose a hierarchy-aware mask to capture the hierarchical dependency between labels. Comprehensive experiments on four benchmark datasets show that LED outperforms the state-of-the-art baselines. Detailed analysis validates the effectiveness of our proposed method." @default.
- W4372260428 created "2023-05-07" @default.
- W4372260428 creator A5003685841 @default.
- W4372260428 creator A5028133931 @default.
- W4372260428 creator A5040023321 @default.
- W4372260428 creator A5059095488 @default.
- W4372260428 creator A5088072972 @default.
- W4372260428 date "2023-06-04" @default.
- W4372260428 modified "2023-09-27" @default.
- W4372260428 title "LED: Label Correlation Enhanced Decoder for Multi-Label Text Classification" @default.
- W4372260428 cites W1999954155 @default.
- W4372260428 cites W2295072214 @default.
- W4372260428 cites W2759474451 @default.
- W4372260428 cites W2949448715 @default.
- W4372260428 cites W2963631426 @default.
- W4372260428 cites W2963912736 @default.
- W4372260428 cites W2971092323 @default.
- W4372260428 cites W2997713239 @default.
- W4372260428 cites W3035690777 @default.
- W4372260428 cites W3109636347 @default.
- W4372260428 cites W3175161202 @default.
- W4372260428 cites W3175301415 @default.
- W4372260428 cites W3176676637 @default.
- W4372260428 cites W3193078993 @default.
- W4372260428 doi "https://doi.org/10.1109/icassp49357.2023.10096210" @default.
- W4372260428 hasPublicationYear "2023" @default.
- W4372260428 type Work @default.
- W4372260428 citedByCount "0" @default.
- W4372260428 crossrefType "proceedings-article" @default.
- W4372260428 hasAuthorship W4372260428A5003685841 @default.
- W4372260428 hasAuthorship W4372260428A5028133931 @default.
- W4372260428 hasAuthorship W4372260428A5040023321 @default.
- W4372260428 hasAuthorship W4372260428A5059095488 @default.
- W4372260428 hasAuthorship W4372260428A5088072972 @default.
- W4372260428 hasBestOaLocation W43722604281 @default.
- W4372260428 hasConcept C117220453 @default.
- W4372260428 hasConcept C119857082 @default.
- W4372260428 hasConcept C13280743 @default.
- W4372260428 hasConcept C153180895 @default.
- W4372260428 hasConcept C154945302 @default.
- W4372260428 hasConcept C162324750 @default.
- W4372260428 hasConcept C185798385 @default.
- W4372260428 hasConcept C187736073 @default.
- W4372260428 hasConcept C19768560 @default.
- W4372260428 hasConcept C204321447 @default.
- W4372260428 hasConcept C205649164 @default.
- W4372260428 hasConcept C2524010 @default.
- W4372260428 hasConcept C2776482837 @default.
- W4372260428 hasConcept C2777212361 @default.
- W4372260428 hasConcept C2780451532 @default.
- W4372260428 hasConcept C31170391 @default.
- W4372260428 hasConcept C33923547 @default.
- W4372260428 hasConcept C34447519 @default.
- W4372260428 hasConcept C41008148 @default.
- W4372260428 hasConceptScore W4372260428C117220453 @default.
- W4372260428 hasConceptScore W4372260428C119857082 @default.
- W4372260428 hasConceptScore W4372260428C13280743 @default.
- W4372260428 hasConceptScore W4372260428C153180895 @default.
- W4372260428 hasConceptScore W4372260428C154945302 @default.
- W4372260428 hasConceptScore W4372260428C162324750 @default.
- W4372260428 hasConceptScore W4372260428C185798385 @default.
- W4372260428 hasConceptScore W4372260428C187736073 @default.
- W4372260428 hasConceptScore W4372260428C19768560 @default.
- W4372260428 hasConceptScore W4372260428C204321447 @default.
- W4372260428 hasConceptScore W4372260428C205649164 @default.
- W4372260428 hasConceptScore W4372260428C2524010 @default.
- W4372260428 hasConceptScore W4372260428C2776482837 @default.
- W4372260428 hasConceptScore W4372260428C2777212361 @default.
- W4372260428 hasConceptScore W4372260428C2780451532 @default.
- W4372260428 hasConceptScore W4372260428C31170391 @default.
- W4372260428 hasConceptScore W4372260428C33923547 @default.
- W4372260428 hasConceptScore W4372260428C34447519 @default.
- W4372260428 hasConceptScore W4372260428C41008148 @default.
- W4372260428 hasFunder F4320321001 @default.
- W4372260428 hasLocation W43722604281 @default.
- W4372260428 hasOpenAccess W4372260428 @default.
- W4372260428 hasPrimaryLocation W43722604281 @default.
- W4372260428 hasRelatedWork W1485630101 @default.
- W4372260428 hasRelatedWork W1545818850 @default.
- W4372260428 hasRelatedWork W2498017833 @default.
- W4372260428 hasRelatedWork W2798703557 @default.
- W4372260428 hasRelatedWork W2912288872 @default.
- W4372260428 hasRelatedWork W2964177319 @default.
- W4372260428 hasRelatedWork W2983785000 @default.
- W4372260428 hasRelatedWork W4297408405 @default.
- W4372260428 hasRelatedWork W63071447 @default.
- W4372260428 hasRelatedWork W85855394 @default.
- W4372260428 isParatext "false" @default.
- W4372260428 isRetracted "false" @default.
- W4372260428 workType "article" @default.