Matches in SemOpenAlex for { <https://semopenalex.org/work/W4294203886> ?p ?o ?g. }
Showing items 1 to 84 of
84
with 100 items per page.
- W4294203886 endingPage "109825" @default.
- W4294203886 startingPage "109825" @default.
- W4294203886 abstract "Aspect-based sentiment analysis (ABSA) aims at identifying the opinion aspects (aspect extraction) and sentiment polarities toward corresponding aspects (sentiment classification) from a sentence. Recently, some span-based methods, which first extract aspects by detecting aspect boundaries and then predict the span-level sentiments, have achieved promising results. However, the correlations between aspect extraction and sentiment classification have not been explicitly explored. For example, sentimental expressions can be better understood if specific aspects are given. In contrast, aspects can be better detected if we know where the sentimental expressions are located. Therefore, we propose a novel H ierarchical I nteractive N etwork (HIN) to enhance the internal connections between aspect extraction and sentiment classification. To this end, the HIN jointly learns the aspect extractor and sentiment classifier across two layers hierarchically. The former learns some shallow-level interactions via a cross-stitch mechanism, and the latter learns deep-level interactions between two subtasks by using mutual information maximization technology. Extensive experiments on three real-world datasets demonstrate the HIN’s superior performance. • Aspect-Based Sentiment is an emerging area in both research and practice. • We proposed a novel span-based multi-task learning framework to enhance the correlations between two subtasks. • Extensive experimental comparisons against state-of-the-art solutions demonstrate the effectiveness of our proposed method." @default.
- W4294203886 created "2022-09-02" @default.
- W4294203886 creator A5003865319 @default.
- W4294203886 creator A5014957657 @default.
- W4294203886 creator A5017541508 @default.
- W4294203886 creator A5044738979 @default.
- W4294203886 creator A5087300335 @default.
- W4294203886 date "2022-11-01" @default.
- W4294203886 modified "2023-09-27" @default.
- W4294203886 title "Hierarchical Interactive Network for joint aspect extraction and sentiment classification" @default.
- W4294203886 cites W2131774270 @default.
- W4294203886 cites W2250539671 @default.
- W4294203886 cites W2251294039 @default.
- W4294203886 cites W2251648804 @default.
- W4294203886 cites W2252007242 @default.
- W4294203886 cites W2465978385 @default.
- W4294203886 cites W2962741379 @default.
- W4294203886 cites W2963877604 @default.
- W4294203886 cites W2965510113 @default.
- W4294203886 cites W2970003478 @default.
- W4294203886 cites W3035740499 @default.
- W4294203886 cites W3047814463 @default.
- W4294203886 cites W3081285030 @default.
- W4294203886 cites W3101751354 @default.
- W4294203886 cites W3114464259 @default.
- W4294203886 cites W3114613321 @default.
- W4294203886 cites W3114696828 @default.
- W4294203886 cites W3115882185 @default.
- W4294203886 cites W3156892644 @default.
- W4294203886 cites W3167287584 @default.
- W4294203886 cites W3168820831 @default.
- W4294203886 cites W3174716710 @default.
- W4294203886 cites W3176719207 @default.
- W4294203886 cites W3177239031 @default.
- W4294203886 cites W3211920512 @default.
- W4294203886 cites W4290945851 @default.
- W4294203886 doi "https://doi.org/10.1016/j.knosys.2022.109825" @default.
- W4294203886 hasPublicationYear "2022" @default.
- W4294203886 type Work @default.
- W4294203886 citedByCount "1" @default.
- W4294203886 countsByYear W42942038862023 @default.
- W4294203886 crossrefType "journal-article" @default.
- W4294203886 hasAuthorship W4294203886A5003865319 @default.
- W4294203886 hasAuthorship W4294203886A5014957657 @default.
- W4294203886 hasAuthorship W4294203886A5017541508 @default.
- W4294203886 hasAuthorship W4294203886A5044738979 @default.
- W4294203886 hasAuthorship W4294203886A5087300335 @default.
- W4294203886 hasConcept C124101348 @default.
- W4294203886 hasConcept C127413603 @default.
- W4294203886 hasConcept C154945302 @default.
- W4294203886 hasConcept C170154142 @default.
- W4294203886 hasConcept C18555067 @default.
- W4294203886 hasConcept C185592680 @default.
- W4294203886 hasConcept C41008148 @default.
- W4294203886 hasConcept C43617362 @default.
- W4294203886 hasConcept C4725764 @default.
- W4294203886 hasConceptScore W4294203886C124101348 @default.
- W4294203886 hasConceptScore W4294203886C127413603 @default.
- W4294203886 hasConceptScore W4294203886C154945302 @default.
- W4294203886 hasConceptScore W4294203886C170154142 @default.
- W4294203886 hasConceptScore W4294203886C18555067 @default.
- W4294203886 hasConceptScore W4294203886C185592680 @default.
- W4294203886 hasConceptScore W4294203886C41008148 @default.
- W4294203886 hasConceptScore W4294203886C43617362 @default.
- W4294203886 hasConceptScore W4294203886C4725764 @default.
- W4294203886 hasLocation W42942038861 @default.
- W4294203886 hasOpenAccess W4294203886 @default.
- W4294203886 hasPrimaryLocation W42942038861 @default.
- W4294203886 hasRelatedWork W2027246577 @default.
- W4294203886 hasRelatedWork W2030530201 @default.
- W4294203886 hasRelatedWork W2351267244 @default.
- W4294203886 hasRelatedWork W2727645644 @default.
- W4294203886 hasRelatedWork W2790424990 @default.
- W4294203886 hasRelatedWork W3011555937 @default.
- W4294203886 hasRelatedWork W3096054746 @default.
- W4294203886 hasRelatedWork W3107474891 @default.
- W4294203886 hasRelatedWork W3199858452 @default.
- W4294203886 hasRelatedWork W4312221968 @default.
- W4294203886 hasVolume "256" @default.
- W4294203886 isParatext "false" @default.
- W4294203886 isRetracted "false" @default.
- W4294203886 workType "article" @default.