Matches in SemOpenAlex for { <https://semopenalex.org/work/W2801454967> ?p ?o ?g. }
Showing items 1 to 89 of
89
with 100 items per page.
- W2801454967 abstract "The goal of sentiment-to-sentiment translation is to change the underlying sentiment of a sentence while keeping its content. The main challenge is the lack of parallel data. To solve this problem, we propose a cycled reinforcement learning method that enables training on unpaired data by collaboration between a neutralization module and an emotionalization module. We evaluate our approach on two review datasets, Yelp and Amazon. Experimental results show that our approach significantly outperforms the state-of-the-art systems. Especially, the proposed method substantially improves the content preservation performance. The BLEU score is improved from 1.64 to 22.46 and from 0.56 to 14.06 on the two datasets, respectively." @default.
- W2801454967 created "2018-05-17" @default.
- W2801454967 creator A5003303201 @default.
- W2801454967 creator A5006497264 @default.
- W2801454967 creator A5025565222 @default.
- W2801454967 creator A5035804461 @default.
- W2801454967 creator A5049239373 @default.
- W2801454967 creator A5056630426 @default.
- W2801454967 creator A5074463113 @default.
- W2801454967 date "2018-05-14" @default.
- W2801454967 modified "2023-10-17" @default.
- W2801454967 title "Unpaired Sentiment-to-Sentiment Translation: A Cycled Reinforcement Learning Approach" @default.
- W2801454967 cites W1423339008 @default.
- W2801454967 cites W2130942839 @default.
- W2801454967 cites W2146502635 @default.
- W2801454967 cites W2331128040 @default.
- W2801454967 cites W2475287302 @default.
- W2801454967 cites W2605287558 @default.
- W2801454967 cites W2611605760 @default.
- W2801454967 cites W2740167620 @default.
- W2801454967 cites W2787534827 @default.
- W2801454967 cites W2916132663 @default.
- W2801454967 cites W2950359962 @default.
- W2801454967 cites W2952008036 @default.
- W2801454967 doi "https://doi.org/10.48550/arxiv.1805.05181" @default.
- W2801454967 hasPublicationYear "2018" @default.
- W2801454967 type Work @default.
- W2801454967 sameAs 2801454967 @default.
- W2801454967 citedByCount "40" @default.
- W2801454967 countsByYear W28014549672018 @default.
- W2801454967 countsByYear W28014549672019 @default.
- W2801454967 countsByYear W28014549672020 @default.
- W2801454967 countsByYear W28014549672021 @default.
- W2801454967 crossrefType "posted-content" @default.
- W2801454967 hasAuthorship W2801454967A5003303201 @default.
- W2801454967 hasAuthorship W2801454967A5006497264 @default.
- W2801454967 hasAuthorship W2801454967A5025565222 @default.
- W2801454967 hasAuthorship W2801454967A5035804461 @default.
- W2801454967 hasAuthorship W2801454967A5049239373 @default.
- W2801454967 hasAuthorship W2801454967A5056630426 @default.
- W2801454967 hasAuthorship W2801454967A5074463113 @default.
- W2801454967 hasBestOaLocation W28014549671 @default.
- W2801454967 hasConcept C104317684 @default.
- W2801454967 hasConcept C105580179 @default.
- W2801454967 hasConcept C11413529 @default.
- W2801454967 hasConcept C119857082 @default.
- W2801454967 hasConcept C149364088 @default.
- W2801454967 hasConcept C154945302 @default.
- W2801454967 hasConcept C185592680 @default.
- W2801454967 hasConcept C203005215 @default.
- W2801454967 hasConcept C204321447 @default.
- W2801454967 hasConcept C2777530160 @default.
- W2801454967 hasConcept C41008148 @default.
- W2801454967 hasConcept C48103436 @default.
- W2801454967 hasConcept C55493867 @default.
- W2801454967 hasConcept C66402592 @default.
- W2801454967 hasConcept C97541855 @default.
- W2801454967 hasConceptScore W2801454967C104317684 @default.
- W2801454967 hasConceptScore W2801454967C105580179 @default.
- W2801454967 hasConceptScore W2801454967C11413529 @default.
- W2801454967 hasConceptScore W2801454967C119857082 @default.
- W2801454967 hasConceptScore W2801454967C149364088 @default.
- W2801454967 hasConceptScore W2801454967C154945302 @default.
- W2801454967 hasConceptScore W2801454967C185592680 @default.
- W2801454967 hasConceptScore W2801454967C203005215 @default.
- W2801454967 hasConceptScore W2801454967C204321447 @default.
- W2801454967 hasConceptScore W2801454967C2777530160 @default.
- W2801454967 hasConceptScore W2801454967C41008148 @default.
- W2801454967 hasConceptScore W2801454967C48103436 @default.
- W2801454967 hasConceptScore W2801454967C55493867 @default.
- W2801454967 hasConceptScore W2801454967C66402592 @default.
- W2801454967 hasConceptScore W2801454967C97541855 @default.
- W2801454967 hasLocation W28014549671 @default.
- W2801454967 hasOpenAccess W2801454967 @default.
- W2801454967 hasPrimaryLocation W28014549671 @default.
- W2801454967 hasRelatedWork W1544285860 @default.
- W2801454967 hasRelatedWork W1559710535 @default.
- W2801454967 hasRelatedWork W2372156302 @default.
- W2801454967 hasRelatedWork W2377856297 @default.
- W2801454967 hasRelatedWork W2390586742 @default.
- W2801454967 hasRelatedWork W2393433765 @default.
- W2801454967 hasRelatedWork W2964093087 @default.
- W2801454967 hasRelatedWork W2980481399 @default.
- W2801454967 hasRelatedWork W3107474891 @default.
- W2801454967 hasRelatedWork W562810006 @default.
- W2801454967 isParatext "false" @default.
- W2801454967 isRetracted "false" @default.
- W2801454967 magId "2801454967" @default.
- W2801454967 workType "article" @default.