Matches in SemOpenAlex for { <https://semopenalex.org/work/W4286979341> ?p ?o ?g. }
Showing items 1 to 56 of
56
with 100 items per page.
- W4286979341 abstract "Fine-grained classification involves dealing with datasets with larger number of classes with subtle differences between them. Guiding the model to focus on differentiating dimensions between these commonly confusable classes is key to improving performance on fine-grained tasks. In this work, we analyse the contrastive fine-tuning of pre-trained language models on two fine-grained text classification tasks, emotion classification and sentiment analysis. We adaptively embed class relationships into a contrastive objective function to help differently weigh the positives and negatives, and in particular, weighting closely confusable negatives more than less similar negative examples. We find that Label-aware Contrastive Loss outperforms previous contrastive methods, in the presence of larger number and/or more confusable classes, and helps models to produce output distributions that are more differentiated." @default.
- W4286979341 created "2022-07-25" @default.
- W4286979341 creator A5009199818 @default.
- W4286979341 creator A5073103551 @default.
- W4286979341 date "2021-09-12" @default.
- W4286979341 modified "2023-09-25" @default.
- W4286979341 title "Not All Negatives are Equal: Label-Aware Contrastive Loss for Fine-grained Text Classification" @default.
- W4286979341 doi "https://doi.org/10.48550/arxiv.2109.05427" @default.
- W4286979341 hasPublicationYear "2021" @default.
- W4286979341 type Work @default.
- W4286979341 citedByCount "0" @default.
- W4286979341 crossrefType "posted-content" @default.
- W4286979341 hasAuthorship W4286979341A5009199818 @default.
- W4286979341 hasAuthorship W4286979341A5073103551 @default.
- W4286979341 hasBestOaLocation W42869793411 @default.
- W4286979341 hasConcept C120665830 @default.
- W4286979341 hasConcept C121332964 @default.
- W4286979341 hasConcept C126838900 @default.
- W4286979341 hasConcept C153180895 @default.
- W4286979341 hasConcept C154945302 @default.
- W4286979341 hasConcept C183115368 @default.
- W4286979341 hasConcept C192209626 @default.
- W4286979341 hasConcept C204321447 @default.
- W4286979341 hasConcept C2777212361 @default.
- W4286979341 hasConcept C41008148 @default.
- W4286979341 hasConcept C64869954 @default.
- W4286979341 hasConcept C71924100 @default.
- W4286979341 hasConceptScore W4286979341C120665830 @default.
- W4286979341 hasConceptScore W4286979341C121332964 @default.
- W4286979341 hasConceptScore W4286979341C126838900 @default.
- W4286979341 hasConceptScore W4286979341C153180895 @default.
- W4286979341 hasConceptScore W4286979341C154945302 @default.
- W4286979341 hasConceptScore W4286979341C183115368 @default.
- W4286979341 hasConceptScore W4286979341C192209626 @default.
- W4286979341 hasConceptScore W4286979341C204321447 @default.
- W4286979341 hasConceptScore W4286979341C2777212361 @default.
- W4286979341 hasConceptScore W4286979341C41008148 @default.
- W4286979341 hasConceptScore W4286979341C64869954 @default.
- W4286979341 hasConceptScore W4286979341C71924100 @default.
- W4286979341 hasLocation W42869793411 @default.
- W4286979341 hasLocation W42869793412 @default.
- W4286979341 hasOpenAccess W4286979341 @default.
- W4286979341 hasPrimaryLocation W42869793411 @default.
- W4286979341 hasRelatedWork W2033914206 @default.
- W4286979341 hasRelatedWork W2104248463 @default.
- W4286979341 hasRelatedWork W2146076056 @default.
- W4286979341 hasRelatedWork W2163831990 @default.
- W4286979341 hasRelatedWork W2293457016 @default.
- W4286979341 hasRelatedWork W2519422835 @default.
- W4286979341 hasRelatedWork W2789919619 @default.
- W4286979341 hasRelatedWork W3003836766 @default.
- W4286979341 hasRelatedWork W1551406738 @default.
- W4286979341 hasRelatedWork W2610387714 @default.
- W4286979341 isParatext "false" @default.
- W4286979341 isRetracted "false" @default.
- W4286979341 workType "article" @default.