Matches in SemOpenAlex for { <https://semopenalex.org/work/W3138185524> ?p ?o ?g. }
Showing items 1 to 94 of
94
with 100 items per page.
- W3138185524 endingPage "81" @default.
- W3138185524 startingPage "75" @default.
- W3138185524 abstract "This article takes the lead to study aspect-level sentiment modification (ALSM) without parallel data. Given a sentence, the task of ALSM needs to reverse the sentiment with respect to the given aspect while preserving other content. The main challenge is reversing the sentiment of the given aspect without affecting the sentiments of other aspects in the sentences. To handle this problem, we propose a joint aspect-level sentiment modification (called JASM) model. JASM is a multitask system, which jointly trains two coupled modules: aspect-specific sentiment words extraction and aspect-level sentiment transformation. Besides, we propose a novel memory mechanism to learn aspect-aware sentiment representation and a gating mechanism to dynamically select aspect-aware sentiment information or content information for generating the next words. Experiments show that the proposed model substantially outperforms the compared methods in both aspect-level sentiment transformation and content preservation. For applications, we conduct data augmentation for aspect-based sentiment analysis (ABSA) through generating plausible training data with the trained ALSM model. Experiments show that data augmentation with generated data boosts the performance of a broad range of ABSA models." @default.
- W3138185524 created "2021-03-29" @default.
- W3138185524 creator A5015872882 @default.
- W3138185524 creator A5030867642 @default.
- W3138185524 creator A5054067088 @default.
- W3138185524 creator A5066877556 @default.
- W3138185524 date "2021-01-01" @default.
- W3138185524 modified "2023-10-02" @default.
- W3138185524 title "Toward Aspect-Level Sentiment Modification Without Parallel Data" @default.
- W3138185524 cites W2064675550 @default.
- W3138185524 cites W2251648804 @default.
- W3138185524 cites W2427312199 @default.
- W3138185524 cites W2562607067 @default.
- W3138185524 cites W2756816896 @default.
- W3138185524 cites W2786411768 @default.
- W3138185524 cites W2888556895 @default.
- W3138185524 cites W2946015932 @default.
- W3138185524 cites W2962741379 @default.
- W3138185524 cites W2962808042 @default.
- W3138185524 cites W2963168371 @default.
- W3138185524 cites W2963667126 @default.
- W3138185524 cites W2963909901 @default.
- W3138185524 cites W2964164368 @default.
- W3138185524 cites W304145884 @default.
- W3138185524 doi "https://doi.org/10.1109/mis.2021.3052617" @default.
- W3138185524 hasPublicationYear "2021" @default.
- W3138185524 type Work @default.
- W3138185524 sameAs 3138185524 @default.
- W3138185524 citedByCount "8" @default.
- W3138185524 countsByYear W31381855242021 @default.
- W3138185524 countsByYear W31381855242022 @default.
- W3138185524 countsByYear W31381855242023 @default.
- W3138185524 crossrefType "journal-article" @default.
- W3138185524 hasAuthorship W3138185524A5015872882 @default.
- W3138185524 hasAuthorship W3138185524A5030867642 @default.
- W3138185524 hasAuthorship W3138185524A5054067088 @default.
- W3138185524 hasAuthorship W3138185524A5066877556 @default.
- W3138185524 hasConcept C104317684 @default.
- W3138185524 hasConcept C119857082 @default.
- W3138185524 hasConcept C154945302 @default.
- W3138185524 hasConcept C162324750 @default.
- W3138185524 hasConcept C17744445 @default.
- W3138185524 hasConcept C185592680 @default.
- W3138185524 hasConcept C187736073 @default.
- W3138185524 hasConcept C199539241 @default.
- W3138185524 hasConcept C204241405 @default.
- W3138185524 hasConcept C204321447 @default.
- W3138185524 hasConcept C2776359362 @default.
- W3138185524 hasConcept C2777530160 @default.
- W3138185524 hasConcept C2780451532 @default.
- W3138185524 hasConcept C41008148 @default.
- W3138185524 hasConcept C55493867 @default.
- W3138185524 hasConcept C66402592 @default.
- W3138185524 hasConcept C94625758 @default.
- W3138185524 hasConceptScore W3138185524C104317684 @default.
- W3138185524 hasConceptScore W3138185524C119857082 @default.
- W3138185524 hasConceptScore W3138185524C154945302 @default.
- W3138185524 hasConceptScore W3138185524C162324750 @default.
- W3138185524 hasConceptScore W3138185524C17744445 @default.
- W3138185524 hasConceptScore W3138185524C185592680 @default.
- W3138185524 hasConceptScore W3138185524C187736073 @default.
- W3138185524 hasConceptScore W3138185524C199539241 @default.
- W3138185524 hasConceptScore W3138185524C204241405 @default.
- W3138185524 hasConceptScore W3138185524C204321447 @default.
- W3138185524 hasConceptScore W3138185524C2776359362 @default.
- W3138185524 hasConceptScore W3138185524C2777530160 @default.
- W3138185524 hasConceptScore W3138185524C2780451532 @default.
- W3138185524 hasConceptScore W3138185524C41008148 @default.
- W3138185524 hasConceptScore W3138185524C55493867 @default.
- W3138185524 hasConceptScore W3138185524C66402592 @default.
- W3138185524 hasConceptScore W3138185524C94625758 @default.
- W3138185524 hasFunder F4320321001 @default.
- W3138185524 hasFunder F4320336569 @default.
- W3138185524 hasIssue "1" @default.
- W3138185524 hasLocation W31381855241 @default.
- W3138185524 hasOpenAccess W3138185524 @default.
- W3138185524 hasPrimaryLocation W31381855241 @default.
- W3138185524 hasRelatedWork W1835566166 @default.
- W3138185524 hasRelatedWork W1978971213 @default.
- W3138185524 hasRelatedWork W2081647779 @default.
- W3138185524 hasRelatedWork W2251381233 @default.
- W3138185524 hasRelatedWork W2800016038 @default.
- W3138185524 hasRelatedWork W3107474891 @default.
- W3138185524 hasRelatedWork W3152966760 @default.
- W3138185524 hasRelatedWork W3192794374 @default.
- W3138185524 hasRelatedWork W4312537596 @default.
- W3138185524 hasRelatedWork W4362613237 @default.
- W3138185524 hasVolume "36" @default.
- W3138185524 isParatext "false" @default.
- W3138185524 isRetracted "false" @default.
- W3138185524 magId "3138185524" @default.
- W3138185524 workType "article" @default.