Matches in SemOpenAlex for { <https://semopenalex.org/work/W4323568909> ?p ?o ?g. }
Showing items 1 to 75 of
75
with 100 items per page.
- W4323568909 abstract "Deep learning techniques have dominated the literature on aspect-based sentiment analysis (ABSA), yielding state-of-the-art results. However, these deep models generally suffer from spurious correlation problems between input features and output labels, which creates significant barriers to robustness and generalization capability. In this paper, we propose a novel Contrastive Variational Information Bottleneck framework (called CVIB) to reduce spurious correlations for ABSA. The proposed CVIB framework is composed of an original network and a self-pruned network, and these two networks are optimized simultaneously via contrastive learning. Concretely, we employ the Variational Information Bottleneck (VIB) principle to learn an informative and compressed network (self-pruned network) from the original network, which discards the superfluous patterns or spurious correlations between input features and prediction labels. Then, self-pruning contrastive learning is devised to pull together semantically similar positive pairs and push away dissimilar pairs, where the representations of the anchor learned by the original and self-pruned networks respectively are regarded as a positive pair while the representations of two different sentences within a mini-batch are treated as a negative pair. To verify the effectiveness of our CVIB method, we conduct extensive experiments on five benchmark ABSA datasets and the experimental results show that our approach achieves better performance than the strong competitors in terms of overall prediction performance, robustness, and generalization." @default.
- W4323568909 created "2023-03-09" @default.
- W4323568909 creator A5008421652 @default.
- W4323568909 creator A5046236233 @default.
- W4323568909 creator A5046405692 @default.
- W4323568909 creator A5052377100 @default.
- W4323568909 date "2023-03-05" @default.
- W4323568909 modified "2023-10-13" @default.
- W4323568909 title "Reducing Spurious Correlations for Aspect-Based Sentiment Analysis with Variational Information Bottleneck and Contrastive Learning" @default.
- W4323568909 doi "https://doi.org/10.48550/arxiv.2303.02846" @default.
- W4323568909 hasPublicationYear "2023" @default.
- W4323568909 type Work @default.
- W4323568909 citedByCount "0" @default.
- W4323568909 crossrefType "posted-content" @default.
- W4323568909 hasAuthorship W4323568909A5008421652 @default.
- W4323568909 hasAuthorship W4323568909A5046236233 @default.
- W4323568909 hasAuthorship W4323568909A5046405692 @default.
- W4323568909 hasAuthorship W4323568909A5052377100 @default.
- W4323568909 hasBestOaLocation W43235689091 @default.
- W4323568909 hasConcept C104317684 @default.
- W4323568909 hasConcept C11413529 @default.
- W4323568909 hasConcept C119857082 @default.
- W4323568909 hasConcept C13280743 @default.
- W4323568909 hasConcept C134306372 @default.
- W4323568909 hasConcept C149635348 @default.
- W4323568909 hasConcept C152139883 @default.
- W4323568909 hasConcept C154945302 @default.
- W4323568909 hasConcept C177148314 @default.
- W4323568909 hasConcept C185592680 @default.
- W4323568909 hasConcept C185798385 @default.
- W4323568909 hasConcept C205649164 @default.
- W4323568909 hasConcept C2780513914 @default.
- W4323568909 hasConcept C33923547 @default.
- W4323568909 hasConcept C41008148 @default.
- W4323568909 hasConcept C55493867 @default.
- W4323568909 hasConcept C60008888 @default.
- W4323568909 hasConcept C63479239 @default.
- W4323568909 hasConcept C66402592 @default.
- W4323568909 hasConcept C97256817 @default.
- W4323568909 hasConceptScore W4323568909C104317684 @default.
- W4323568909 hasConceptScore W4323568909C11413529 @default.
- W4323568909 hasConceptScore W4323568909C119857082 @default.
- W4323568909 hasConceptScore W4323568909C13280743 @default.
- W4323568909 hasConceptScore W4323568909C134306372 @default.
- W4323568909 hasConceptScore W4323568909C149635348 @default.
- W4323568909 hasConceptScore W4323568909C152139883 @default.
- W4323568909 hasConceptScore W4323568909C154945302 @default.
- W4323568909 hasConceptScore W4323568909C177148314 @default.
- W4323568909 hasConceptScore W4323568909C185592680 @default.
- W4323568909 hasConceptScore W4323568909C185798385 @default.
- W4323568909 hasConceptScore W4323568909C205649164 @default.
- W4323568909 hasConceptScore W4323568909C2780513914 @default.
- W4323568909 hasConceptScore W4323568909C33923547 @default.
- W4323568909 hasConceptScore W4323568909C41008148 @default.
- W4323568909 hasConceptScore W4323568909C55493867 @default.
- W4323568909 hasConceptScore W4323568909C60008888 @default.
- W4323568909 hasConceptScore W4323568909C63479239 @default.
- W4323568909 hasConceptScore W4323568909C66402592 @default.
- W4323568909 hasConceptScore W4323568909C97256817 @default.
- W4323568909 hasLocation W43235689091 @default.
- W4323568909 hasOpenAccess W4323568909 @default.
- W4323568909 hasPrimaryLocation W43235689091 @default.
- W4323568909 hasRelatedWork W2096516049 @default.
- W4323568909 hasRelatedWork W2123469175 @default.
- W4323568909 hasRelatedWork W2179794820 @default.
- W4323568909 hasRelatedWork W2355370347 @default.
- W4323568909 hasRelatedWork W3088534631 @default.
- W4323568909 hasRelatedWork W3177538078 @default.
- W4323568909 hasRelatedWork W3179381308 @default.
- W4323568909 hasRelatedWork W4302400283 @default.
- W4323568909 hasRelatedWork W4307473403 @default.
- W4323568909 hasRelatedWork W4312195711 @default.
- W4323568909 isParatext "false" @default.
- W4323568909 isRetracted "false" @default.
- W4323568909 workType "article" @default.