Matches in SemOpenAlex for { <https://semopenalex.org/work/W3212152676> ?p ?o ?g. }
- W3212152676 abstract "This paper studies continual learning (CL) of a sequence of aspect sentiment classification (ASC) tasks in a particular CL setting called domain incremental learning (DIL). Each task is from a different domain or product. The DIL setting is particularly suited to ASC because in testing the system needs not know the task/domain to which the test data belongs. To our knowledge, this setting has not been studied before for ASC. This paper proposes a novel model called CLASSIC. The key novelty is a contrastive continual learning method that enables both knowledge transfer across tasks and knowledge distillation from old tasks to the new task, which eliminates the need for task ids in testing. Experimental results show the high effectiveness of CLASSIC." @default.
- W3212152676 created "2021-11-22" @default.
- W3212152676 creator A5013224749 @default.
- W3212152676 creator A5013308036 @default.
- W3212152676 creator A5014528965 @default.
- W3212152676 creator A5044702929 @default.
- W3212152676 date "2021-01-01" @default.
- W3212152676 modified "2023-10-14" @default.
- W3212152676 title "CLASSIC: Continual and Contrastive Learning of Aspect Sentiment Classification Tasks" @default.
- W3212152676 cites W1519626139 @default.
- W3212152676 cites W1682403713 @default.
- W3212152676 cites W1832693441 @default.
- W3212152676 cites W1964613733 @default.
- W3212152676 cites W2106035193 @default.
- W3212152676 cites W2108646579 @default.
- W3212152676 cites W2120501001 @default.
- W3212152676 cites W2160660844 @default.
- W3212152676 cites W2234079371 @default.
- W3212152676 cites W2565989828 @default.
- W3212152676 cites W2765895026 @default.
- W3212152676 cites W2767245334 @default.
- W3212152676 cites W2785567898 @default.
- W3212152676 cites W2788388592 @default.
- W3212152676 cites W2842511635 @default.
- W3212152676 cites W2902625698 @default.
- W3212152676 cites W2911437461 @default.
- W3212152676 cites W2925618549 @default.
- W3212152676 cites W2939137134 @default.
- W3212152676 cites W2940792992 @default.
- W3212152676 cites W2949819354 @default.
- W3212152676 cites W2950893734 @default.
- W3212152676 cites W2954278700 @default.
- W3212152676 cites W2962724315 @default.
- W3212152676 cites W2962808042 @default.
- W3212152676 cites W2963168371 @default.
- W3212152676 cites W2963209029 @default.
- W3212152676 cites W2963341956 @default.
- W3212152676 cites W2963403868 @default.
- W3212152676 cites W2963559848 @default.
- W3212152676 cites W2963572510 @default.
- W3212152676 cites W2963667932 @default.
- W3212152676 cites W2963813679 @default.
- W3212152676 cites W2963936679 @default.
- W3212152676 cites W2964189064 @default.
- W3212152676 cites W2964303773 @default.
- W3212152676 cites W2965043358 @default.
- W3212152676 cites W2967821093 @default.
- W3212152676 cites W2970748152 @default.
- W3212152676 cites W2974317861 @default.
- W3212152676 cites W2991149828 @default.
- W3212152676 cites W2995607862 @default.
- W3212152676 cites W2996144997 @default.
- W3212152676 cites W3002800333 @default.
- W3212152676 cites W3017160304 @default.
- W3212152676 cites W3034867292 @default.
- W3212152676 cites W3034978746 @default.
- W3212152676 cites W3035524453 @default.
- W3212152676 cites W3100345210 @default.
- W3212152676 cites W3102836509 @default.
- W3212152676 cites W3103368673 @default.
- W3212152676 cites W3103855389 @default.
- W3212152676 cites W3106428938 @default.
- W3212152676 cites W3130420381 @default.
- W3212152676 cites W3172053684 @default.
- W3212152676 doi "https://doi.org/10.18653/v1/2021.emnlp-main.550" @default.
- W3212152676 hasPublicationYear "2021" @default.
- W3212152676 type Work @default.
- W3212152676 sameAs 3212152676 @default.
- W3212152676 citedByCount "10" @default.
- W3212152676 countsByYear W32121526762022 @default.
- W3212152676 countsByYear W32121526762023 @default.
- W3212152676 crossrefType "proceedings-article" @default.
- W3212152676 hasAuthorship W3212152676A5013224749 @default.
- W3212152676 hasAuthorship W3212152676A5013308036 @default.
- W3212152676 hasAuthorship W3212152676A5014528965 @default.
- W3212152676 hasAuthorship W3212152676A5044702929 @default.
- W3212152676 hasBestOaLocation W32121526761 @default.
- W3212152676 hasConcept C119857082 @default.
- W3212152676 hasConcept C127413603 @default.
- W3212152676 hasConcept C134306372 @default.
- W3212152676 hasConcept C138885662 @default.
- W3212152676 hasConcept C150899416 @default.
- W3212152676 hasConcept C151730666 @default.
- W3212152676 hasConcept C154945302 @default.
- W3212152676 hasConcept C201995342 @default.
- W3212152676 hasConcept C204321447 @default.
- W3212152676 hasConcept C207685749 @default.
- W3212152676 hasConcept C2524010 @default.
- W3212152676 hasConcept C26517878 @default.
- W3212152676 hasConcept C27206212 @default.
- W3212152676 hasConcept C2777267654 @default.
- W3212152676 hasConcept C2778738651 @default.
- W3212152676 hasConcept C2780451532 @default.
- W3212152676 hasConcept C28006648 @default.
- W3212152676 hasConcept C33923547 @default.
- W3212152676 hasConcept C36503486 @default.
- W3212152676 hasConcept C38652104 @default.
- W3212152676 hasConcept C41008148 @default.
- W3212152676 hasConcept C86803240 @default.
- W3212152676 hasConcept C90673727 @default.