Matches in SemOpenAlex for { <https://semopenalex.org/work/W4376988897> ?p ?o ?g. }
Showing items 1 to 77 of
77
with 100 items per page.
- W4376988897 abstract "Few-shot text classification has recently been promoted by the meta-learning paradigm which aims to identify target classes with knowledge transferred from source classes with sets of small tasks named episodes. Despite their success, existing works building their meta-learner based on Prototypical Networks are unsatisfactory in learning discriminative text representations between similar classes, which may lead to contradictions during label prediction. In addition, the tasklevel and instance-level overfitting problems in few-shot text classification caused by a few training examples are not sufficiently tackled. In this work, we propose a contrastive learning framework named ContrastNet to tackle both discriminative representation and overfitting problems in few-shot text classification. ContrastNet learns to pull closer text representations belonging to the same class and push away text representations belonging to different classes, while simultaneously introducing unsupervised contrastive regularization at both task-level and instance-level to prevent overfitting. Experiments on 8 few-shot text classification datasets show that ContrastNet outperforms the current state-of-the-art models." @default.
- W4376988897 created "2023-05-18" @default.
- W4376988897 creator A5004793184 @default.
- W4376988897 creator A5006061735 @default.
- W4376988897 creator A5019482811 @default.
- W4376988897 creator A5027015677 @default.
- W4376988897 date "2023-05-16" @default.
- W4376988897 modified "2023-09-26" @default.
- W4376988897 title "ContrastNet: A Contrastive Learning Framework for Few-Shot Text Classification" @default.
- W4376988897 doi "https://doi.org/10.48550/arxiv.2305.09269" @default.
- W4376988897 hasPublicationYear "2023" @default.
- W4376988897 type Work @default.
- W4376988897 citedByCount "0" @default.
- W4376988897 crossrefType "posted-content" @default.
- W4376988897 hasAuthorship W4376988897A5004793184 @default.
- W4376988897 hasAuthorship W4376988897A5006061735 @default.
- W4376988897 hasAuthorship W4376988897A5019482811 @default.
- W4376988897 hasAuthorship W4376988897A5027015677 @default.
- W4376988897 hasBestOaLocation W43769888971 @default.
- W4376988897 hasConcept C119857082 @default.
- W4376988897 hasConcept C153180895 @default.
- W4376988897 hasConcept C154945302 @default.
- W4376988897 hasConcept C162324750 @default.
- W4376988897 hasConcept C17744445 @default.
- W4376988897 hasConcept C178790620 @default.
- W4376988897 hasConcept C185592680 @default.
- W4376988897 hasConcept C187736073 @default.
- W4376988897 hasConcept C199539241 @default.
- W4376988897 hasConcept C204321447 @default.
- W4376988897 hasConcept C22019652 @default.
- W4376988897 hasConcept C2776135515 @default.
- W4376988897 hasConcept C2776359362 @default.
- W4376988897 hasConcept C2777212361 @default.
- W4376988897 hasConcept C2778344882 @default.
- W4376988897 hasConcept C2780451532 @default.
- W4376988897 hasConcept C41008148 @default.
- W4376988897 hasConcept C50644808 @default.
- W4376988897 hasConcept C59404180 @default.
- W4376988897 hasConcept C94625758 @default.
- W4376988897 hasConcept C97931131 @default.
- W4376988897 hasConceptScore W4376988897C119857082 @default.
- W4376988897 hasConceptScore W4376988897C153180895 @default.
- W4376988897 hasConceptScore W4376988897C154945302 @default.
- W4376988897 hasConceptScore W4376988897C162324750 @default.
- W4376988897 hasConceptScore W4376988897C17744445 @default.
- W4376988897 hasConceptScore W4376988897C178790620 @default.
- W4376988897 hasConceptScore W4376988897C185592680 @default.
- W4376988897 hasConceptScore W4376988897C187736073 @default.
- W4376988897 hasConceptScore W4376988897C199539241 @default.
- W4376988897 hasConceptScore W4376988897C204321447 @default.
- W4376988897 hasConceptScore W4376988897C22019652 @default.
- W4376988897 hasConceptScore W4376988897C2776135515 @default.
- W4376988897 hasConceptScore W4376988897C2776359362 @default.
- W4376988897 hasConceptScore W4376988897C2777212361 @default.
- W4376988897 hasConceptScore W4376988897C2778344882 @default.
- W4376988897 hasConceptScore W4376988897C2780451532 @default.
- W4376988897 hasConceptScore W4376988897C41008148 @default.
- W4376988897 hasConceptScore W4376988897C50644808 @default.
- W4376988897 hasConceptScore W4376988897C59404180 @default.
- W4376988897 hasConceptScore W4376988897C94625758 @default.
- W4376988897 hasConceptScore W4376988897C97931131 @default.
- W4376988897 hasLocation W43769888971 @default.
- W4376988897 hasOpenAccess W4376988897 @default.
- W4376988897 hasPrimaryLocation W43769888971 @default.
- W4376988897 hasRelatedWork W130490334 @default.
- W4376988897 hasRelatedWork W1914651075 @default.
- W4376988897 hasRelatedWork W2765564618 @default.
- W4376988897 hasRelatedWork W2905846897 @default.
- W4376988897 hasRelatedWork W2944843851 @default.
- W4376988897 hasRelatedWork W2998168123 @default.
- W4376988897 hasRelatedWork W3044795413 @default.
- W4376988897 hasRelatedWork W3135618744 @default.
- W4376988897 hasRelatedWork W3189898312 @default.
- W4376988897 hasRelatedWork W4287995534 @default.
- W4376988897 isParatext "false" @default.
- W4376988897 isRetracted "false" @default.
- W4376988897 workType "article" @default.