FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4225783786> ?p ?o ?g. }

• W4225783786 endingPage "1990" @default.
• W4225783786 startingPage "1979" @default.
• W4225783786 abstract "Cross-domain sentiment analysis aims to adapt sentiment classification models trained on one or more source domains to the target domain, which can effectively alleviate the problem of insufficient labelled data in specific domains. Unlike most previous methods of adjusting models based on observed data, we propose a novel counterfactual representation augmentation (CRA) method, which aims to improve target-domain generalization by constructing new counterfactual representations for training. Specifically, we train a domain discriminator to learn the domain discrepancy between the source and target domains on unlabeled data, and use a gradient editing method to directly construct counterfactual representations, which reduces the inductive bias of the source domain and augments the training data. Moreover, we further leverage an ensemble-based training method to indirectly encourage the target-domain classifier to rely more on robust features for prediction. Extensive experiments on a widely-used cross-domain sentiment classification benchmark dataset show that our method consistently surpasses different baseline methods on different tasks, demonstrating the strong ability to improve domain generalization. We also find that our model can effectively adjust the decision boundary to make the classifier more robust and generalized, through extensive qualitative and quantitative analysis." @default.
• W4225783786 created "2022-05-05" @default.
• W4225783786 creator A5026906414 @default.
• W4225783786 creator A5057185236 @default.
• W4225783786 date "2023-07-01" @default.
• W4225783786 modified "2023-10-10" @default.
• W4225783786 title "Counterfactual Representation Augmentation for Cross-Domain Sentiment Analysis" @default.
• W4225783786 cites W1977088242 @default.
• W4225783786 cites W1978108654 @default.
• W4225783786 cites W2055103902 @default.
• W4225783786 cites W2068599126 @default.
• W4225783786 cites W2095579012 @default.
• W4225783786 cites W2116064496 @default.
• W4225783786 cites W2124536510 @default.
• W4225783786 cites W2143117649 @default.
• W4225783786 cites W2143891888 @default.
• W4225783786 cites W2153353890 @default.
• W4225783786 cites W2167216307 @default.
• W4225783786 cites W2248676660 @default.
• W4225783786 cites W2333097151 @default.
• W4225783786 cites W2471364849 @default.
• W4225783786 cites W2560730294 @default.
• W4225783786 cites W2561230197 @default.
• W4225783786 cites W2573291455 @default.
• W4225783786 cites W2605323333 @default.
• W4225783786 cites W2612769033 @default.
• W4225783786 cites W2741989495 @default.
• W4225783786 cites W2767280341 @default.
• W4225783786 cites W2789132801 @default.
• W4225783786 cites W2798717312 @default.
• W4225783786 cites W2798820405 @default.
• W4225783786 cites W2798984401 @default.
• W4225783786 cites W2803777992 @default.
• W4225783786 cites W2889774592 @default.
• W4225783786 cites W2890896513 @default.
• W4225783786 cites W2918288435 @default.
• W4225783786 cites W2919115771 @default.
• W4225783786 cites W2945801692 @default.
• W4225783786 cites W2950705418 @default.
• W4225783786 cites W2950940239 @default.
• W4225783786 cites W2951286828 @default.
• W4225783786 cites W2952984539 @default.
• W4225783786 cites W2962727366 @default.
• W4225783786 cites W2962739339 @default.
• W4225783786 cites W2962833164 @default.
• W4225783786 cites W2962869292 @default.
• W4225783786 cites W2963518342 @default.
• W4225783786 cites W2963891433 @default.
• W4225783786 cites W2963969878 @default.
• W4225783786 cites W2964044490 @default.
• W4225783786 cites W2964236337 @default.
• W4225783786 cites W2970019270 @default.
• W4225783786 cites W2970379526 @default.
• W4225783786 cites W2984256198 @default.
• W4225783786 cites W3005283300 @default.
• W4225783786 cites W3025630664 @default.
• W4225783786 cites W3035431747 @default.
• W4225783786 cites W3106544837 @default.
• W4225783786 cites W3152368098 @default.
• W4225783786 cites W3160851104 @default.
• W4225783786 cites W3176001432 @default.
• W4225783786 cites W3176197839 @default.
• W4225783786 cites W3199724653 @default.
• W4225783786 cites W3208191520 @default.
• W4225783786 cites W3211867455 @default.
• W4225783786 cites W4239510810 @default.
• W4225783786 cites W4240795372 @default.
• W4225783786 cites W91453536 @default.
• W4225783786 doi "https://doi.org/10.1109/taffc.2022.3158843" @default.
• W4225783786 hasPublicationYear "2023" @default.
• W4225783786 type Work @default.
• W4225783786 citedByCount "0" @default.
• W4225783786 crossrefType "journal-article" @default.
• W4225783786 hasAuthorship W4225783786A5026906414 @default.
• W4225783786 hasAuthorship W4225783786A5057185236 @default.
• W4225783786 hasConcept C108650721 @default.
• W4225783786 hasConcept C111472728 @default.
• W4225783786 hasConcept C119857082 @default.
• W4225783786 hasConcept C13280743 @default.
• W4225783786 hasConcept C134306372 @default.
• W4225783786 hasConcept C138885662 @default.
• W4225783786 hasConcept C153083717 @default.
• W4225783786 hasConcept C153180895 @default.
• W4225783786 hasConcept C154945302 @default.
• W4225783786 hasConcept C177148314 @default.
• W4225783786 hasConcept C17744445 @default.
• W4225783786 hasConcept C185798385 @default.
• W4225783786 hasConcept C199539241 @default.
• W4225783786 hasConcept C205649164 @default.
• W4225783786 hasConcept C2776359362 @default.
• W4225783786 hasConcept C2779803651 @default.
• W4225783786 hasConcept C33923547 @default.
• W4225783786 hasConcept C36503486 @default.
• W4225783786 hasConcept C41008148 @default.
• W4225783786 hasConcept C66402592 @default.
• W4225783786 hasConcept C76155785 @default.
• W4225783786 hasConcept C94625758 @default.
• W4225783786 hasConcept C94915269 @default.

• next