Matches in SemOpenAlex for { <https://semopenalex.org/work/W2809503077> ?p ?o ?g. }
Showing items 1 to 91 of
91
with 100 items per page.
- W2809503077 endingPage "680" @default.
- W2809503077 startingPage "668" @default.
- W2809503077 abstract "Document-level sentiment classification is an important NLP task. The state of the art shows that attention mechanism is particularly effective on document-level sentiment classification. Despite the success of previous attention mechanism, it neglects the correlations among inputs (e.g., words in a sentence), which can be useful for improving the classification result. In this paper, we propose a novel Adaptive Attention Network (AAN) to explicitly model the correlations among inputs. Our AAN has a two-layer attention hierarchy. It first learns an attention score for each input. Given each input’s embedding and attention score, it then computes a weighted sum over all the words’ embeddings. This weighted sum is seen as a “context” embedding, aggregating all the inputs. Finally, to model the correlations among inputs, it computes another attention score for each input, based on the input embedding and the context embedding. These new attention scores are our final output of AAN. In document-level sentiment classification, we apply AAN to model words in a sentence and sentences in a review. We evaluate AAN on three public data sets, and show that it outperforms state-of-the-art baselines." @default.
- W2809503077 created "2018-06-29" @default.
- W2809503077 creator A5017811036 @default.
- W2809503077 creator A5026924268 @default.
- W2809503077 creator A5055007102 @default.
- W2809503077 creator A5065995973 @default.
- W2809503077 date "2018-01-01" @default.
- W2809503077 modified "2023-09-24" @default.
- W2809503077 title "Adaptive Attention Network for Review Sentiment Classification" @default.
- W2809503077 cites W1964613733 @default.
- W2809503077 cites W2120615054 @default.
- W2809503077 cites W2142972908 @default.
- W2809503077 cites W2156413587 @default.
- W2809503077 cites W2166706824 @default.
- W2809503077 cites W2250879510 @default.
- W2809503077 cites W2250966211 @default.
- W2809503077 cites W2251292973 @default.
- W2809503077 cites W2265846598 @default.
- W2809503077 cites W2470673105 @default.
- W2809503077 cites W2563010554 @default.
- W2809503077 cites W2744080778 @default.
- W2809503077 cites W2963168371 @default.
- W2809503077 cites W2963355447 @default.
- W2809503077 doi "https://doi.org/10.1007/978-3-319-93034-3_53" @default.
- W2809503077 hasPublicationYear "2018" @default.
- W2809503077 type Work @default.
- W2809503077 sameAs 2809503077 @default.
- W2809503077 citedByCount "1" @default.
- W2809503077 countsByYear W28095030772020 @default.
- W2809503077 crossrefType "book-chapter" @default.
- W2809503077 hasAuthorship W2809503077A5017811036 @default.
- W2809503077 hasAuthorship W2809503077A5026924268 @default.
- W2809503077 hasAuthorship W2809503077A5055007102 @default.
- W2809503077 hasAuthorship W2809503077A5065995973 @default.
- W2809503077 hasConcept C119857082 @default.
- W2809503077 hasConcept C151730666 @default.
- W2809503077 hasConcept C154945302 @default.
- W2809503077 hasConcept C162324750 @default.
- W2809503077 hasConcept C178790620 @default.
- W2809503077 hasConcept C185592680 @default.
- W2809503077 hasConcept C187736073 @default.
- W2809503077 hasConcept C204321447 @default.
- W2809503077 hasConcept C2777462759 @default.
- W2809503077 hasConcept C2777530160 @default.
- W2809503077 hasConcept C2779227376 @default.
- W2809503077 hasConcept C2779343474 @default.
- W2809503077 hasConcept C2780451532 @default.
- W2809503077 hasConcept C31170391 @default.
- W2809503077 hasConcept C34447519 @default.
- W2809503077 hasConcept C41008148 @default.
- W2809503077 hasConcept C41608201 @default.
- W2809503077 hasConcept C66402592 @default.
- W2809503077 hasConcept C86803240 @default.
- W2809503077 hasConceptScore W2809503077C119857082 @default.
- W2809503077 hasConceptScore W2809503077C151730666 @default.
- W2809503077 hasConceptScore W2809503077C154945302 @default.
- W2809503077 hasConceptScore W2809503077C162324750 @default.
- W2809503077 hasConceptScore W2809503077C178790620 @default.
- W2809503077 hasConceptScore W2809503077C185592680 @default.
- W2809503077 hasConceptScore W2809503077C187736073 @default.
- W2809503077 hasConceptScore W2809503077C204321447 @default.
- W2809503077 hasConceptScore W2809503077C2777462759 @default.
- W2809503077 hasConceptScore W2809503077C2777530160 @default.
- W2809503077 hasConceptScore W2809503077C2779227376 @default.
- W2809503077 hasConceptScore W2809503077C2779343474 @default.
- W2809503077 hasConceptScore W2809503077C2780451532 @default.
- W2809503077 hasConceptScore W2809503077C31170391 @default.
- W2809503077 hasConceptScore W2809503077C34447519 @default.
- W2809503077 hasConceptScore W2809503077C41008148 @default.
- W2809503077 hasConceptScore W2809503077C41608201 @default.
- W2809503077 hasConceptScore W2809503077C66402592 @default.
- W2809503077 hasConceptScore W2809503077C86803240 @default.
- W2809503077 hasLocation W28095030771 @default.
- W2809503077 hasOpenAccess W2809503077 @default.
- W2809503077 hasPrimaryLocation W28095030771 @default.
- W2809503077 hasRelatedWork W2326619756 @default.
- W2809503077 hasRelatedWork W2894570593 @default.
- W2809503077 hasRelatedWork W2901590103 @default.
- W2809503077 hasRelatedWork W2901922204 @default.
- W2809503077 hasRelatedWork W2944636446 @default.
- W2809503077 hasRelatedWork W3027466640 @default.
- W2809503077 hasRelatedWork W3038748136 @default.
- W2809503077 hasRelatedWork W3105191672 @default.
- W2809503077 hasRelatedWork W3107474891 @default.
- W2809503077 hasRelatedWork W3153487575 @default.
- W2809503077 isParatext "false" @default.
- W2809503077 isRetracted "false" @default.
- W2809503077 magId "2809503077" @default.
- W2809503077 workType "book-chapter" @default.