Matches in SemOpenAlex for { <https://semopenalex.org/work/W3160851104> ?p ?o ?g. }
Showing items 1 to 89 of
89
with 100 items per page.
- W3160851104 abstract "Existing language models usually require large amount of labeled data and are severely challenged by domain shift. In this work we propose a novel model for cross-domain sentiment classification - CLIM - Contrastive Learning with mutual Information Maximization, to explore the potential of contrastive learning for learning domain-invariant and task-discriminative features. To the best of our knowledge, CLIM is the first to investigate contrastive learning for cross-domain sentiment classification. Due to the scarcity of labels on the target domain, we introduce mutual information maximization (MIM) to explore the features that best support the final prediction. Furthermore, MIM is able to maintain a relatively balanced distribution of the model’s prediction, and enlarge the margin between classes on the target, which increases the model robustness and enables the same classifier to be optimal across domains. Consequently, we achieve new state-of-the-art results on the Amazon-review dataset as well as the Airlines dataset, demonstrating the efficacy of our methods." @default.
- W3160851104 created "2021-05-24" @default.
- W3160851104 creator A5013030532 @default.
- W3160851104 creator A5047285420 @default.
- W3160851104 creator A5049051527 @default.
- W3160851104 creator A5070459818 @default.
- W3160851104 creator A5076768386 @default.
- W3160851104 date "2021-06-06" @default.
- W3160851104 modified "2023-10-16" @default.
- W3160851104 title "Cross-Domain Sentiment Classification with Contrastive Learning and Mutual Information Maximization" @default.
- W3160851104 cites W2158108973 @default.
- W3160851104 cites W2507341862 @default.
- W3160851104 cites W2567698949 @default.
- W3160851104 cites W2789132801 @default.
- W3160851104 cites W2790763247 @default.
- W3160851104 cites W2803777992 @default.
- W3160851104 cites W2889774592 @default.
- W3160851104 cites W2963261224 @default.
- W3160851104 cites W2998705539 @default.
- W3160851104 cites W3035431747 @default.
- W3160851104 cites W3094277917 @default.
- W3160851104 doi "https://doi.org/10.1109/icassp39728.2021.9414930" @default.
- W3160851104 hasPublicationYear "2021" @default.
- W3160851104 type Work @default.
- W3160851104 sameAs 3160851104 @default.
- W3160851104 citedByCount "14" @default.
- W3160851104 countsByYear W31608511042020 @default.
- W3160851104 countsByYear W31608511042021 @default.
- W3160851104 countsByYear W31608511042022 @default.
- W3160851104 countsByYear W31608511042023 @default.
- W3160851104 crossrefType "proceedings-article" @default.
- W3160851104 hasAuthorship W3160851104A5013030532 @default.
- W3160851104 hasAuthorship W3160851104A5047285420 @default.
- W3160851104 hasAuthorship W3160851104A5049051527 @default.
- W3160851104 hasAuthorship W3160851104A5070459818 @default.
- W3160851104 hasAuthorship W3160851104A5076768386 @default.
- W3160851104 hasBestOaLocation W31608511042 @default.
- W3160851104 hasConcept C104317684 @default.
- W3160851104 hasConcept C119857082 @default.
- W3160851104 hasConcept C126255220 @default.
- W3160851104 hasConcept C152139883 @default.
- W3160851104 hasConcept C153180895 @default.
- W3160851104 hasConcept C154945302 @default.
- W3160851104 hasConcept C185592680 @default.
- W3160851104 hasConcept C204321447 @default.
- W3160851104 hasConcept C2776330181 @default.
- W3160851104 hasConcept C33923547 @default.
- W3160851104 hasConcept C41008148 @default.
- W3160851104 hasConcept C55493867 @default.
- W3160851104 hasConcept C63479239 @default.
- W3160851104 hasConcept C66402592 @default.
- W3160851104 hasConcept C774472 @default.
- W3160851104 hasConcept C95623464 @default.
- W3160851104 hasConcept C97931131 @default.
- W3160851104 hasConceptScore W3160851104C104317684 @default.
- W3160851104 hasConceptScore W3160851104C119857082 @default.
- W3160851104 hasConceptScore W3160851104C126255220 @default.
- W3160851104 hasConceptScore W3160851104C152139883 @default.
- W3160851104 hasConceptScore W3160851104C153180895 @default.
- W3160851104 hasConceptScore W3160851104C154945302 @default.
- W3160851104 hasConceptScore W3160851104C185592680 @default.
- W3160851104 hasConceptScore W3160851104C204321447 @default.
- W3160851104 hasConceptScore W3160851104C2776330181 @default.
- W3160851104 hasConceptScore W3160851104C33923547 @default.
- W3160851104 hasConceptScore W3160851104C41008148 @default.
- W3160851104 hasConceptScore W3160851104C55493867 @default.
- W3160851104 hasConceptScore W3160851104C63479239 @default.
- W3160851104 hasConceptScore W3160851104C66402592 @default.
- W3160851104 hasConceptScore W3160851104C774472 @default.
- W3160851104 hasConceptScore W3160851104C95623464 @default.
- W3160851104 hasConceptScore W3160851104C97931131 @default.
- W3160851104 hasLocation W31608511041 @default.
- W3160851104 hasLocation W31608511042 @default.
- W3160851104 hasOpenAccess W3160851104 @default.
- W3160851104 hasPrimaryLocation W31608511041 @default.
- W3160851104 hasRelatedWork W1972656095 @default.
- W3160851104 hasRelatedWork W2024160000 @default.
- W3160851104 hasRelatedWork W2061273563 @default.
- W3160851104 hasRelatedWork W2285052147 @default.
- W3160851104 hasRelatedWork W2729514902 @default.
- W3160851104 hasRelatedWork W2743258233 @default.
- W3160851104 hasRelatedWork W2773500201 @default.
- W3160851104 hasRelatedWork W2970216048 @default.
- W3160851104 hasRelatedWork W2998168123 @default.
- W3160851104 hasRelatedWork W4287995534 @default.
- W3160851104 isParatext "false" @default.
- W3160851104 isRetracted "false" @default.
- W3160851104 magId "3160851104" @default.
- W3160851104 workType "article" @default.