Matches in SemOpenAlex for { <https://semopenalex.org/work/W2897826647> ?p ?o ?g. }
Showing items 1 to 81 of
81
with 100 items per page.
- W2897826647 abstract "Text simplification (TS) can be viewed as monolingual translation task, translating between text variations within a single language. Recent neural TS models draw on insights from neural machine translation to learn lexical simplification and content reduction using encoder-decoder model. But different from neural machine translation, we cannot obtain enough ordinary and simplified sentence pairs for TS, which are expensive and time-consuming to build. Target-side simplified sentences plays an important role in boosting fluency for statistical TS, and we investigate the use of simplified sentences to train, with no changes to the network architecture. We propose to pair simple training sentence with a synthetic ordinary sentence via back-translation, and treating this synthetic data as additional training data. We train encoder-decoder model using synthetic sentence pairs and original sentence pairs, which can obtain substantial improvements on the available WikiLarge data and WikiSmall data compared with the state-of-the-art methods." @default.
- W2897826647 created "2018-10-26" @default.
- W2897826647 creator A5062724090 @default.
- W2897826647 date "2018-10-10" @default.
- W2897826647 modified "2023-09-24" @default.
- W2897826647 title "Improving Neural Text Simplification Model with Simplified Corpora" @default.
- W2897826647 cites W1507711477 @default.
- W2897826647 cites W1843891098 @default.
- W2897826647 cites W2123442489 @default.
- W2897826647 cites W2133564696 @default.
- W2897826647 cites W2153982529 @default.
- W2897826647 cites W2284660317 @default.
- W2897826647 cites W2531738943 @default.
- W2897826647 cites W2885942871 @default.
- W2897826647 cites W2949888546 @default.
- W2897826647 cites W2950635152 @default.
- W2897826647 cites W2953033958 @default.
- W2897826647 doi "https://doi.org/10.48550/arxiv.1810.04428" @default.
- W2897826647 hasPublicationYear "2018" @default.
- W2897826647 type Work @default.
- W2897826647 sameAs 2897826647 @default.
- W2897826647 citedByCount "4" @default.
- W2897826647 countsByYear W28978266472021 @default.
- W2897826647 crossrefType "posted-content" @default.
- W2897826647 hasAuthorship W2897826647A5062724090 @default.
- W2897826647 hasBestOaLocation W28978266471 @default.
- W2897826647 hasConcept C104317684 @default.
- W2897826647 hasConcept C105580179 @default.
- W2897826647 hasConcept C111919701 @default.
- W2897826647 hasConcept C118505674 @default.
- W2897826647 hasConcept C138885662 @default.
- W2897826647 hasConcept C149364088 @default.
- W2897826647 hasConcept C154945302 @default.
- W2897826647 hasConcept C185592680 @default.
- W2897826647 hasConcept C203005215 @default.
- W2897826647 hasConcept C204321447 @default.
- W2897826647 hasConcept C2777413886 @default.
- W2897826647 hasConcept C2777530160 @default.
- W2897826647 hasConcept C28490314 @default.
- W2897826647 hasConcept C41008148 @default.
- W2897826647 hasConcept C41895202 @default.
- W2897826647 hasConcept C46686674 @default.
- W2897826647 hasConcept C50644808 @default.
- W2897826647 hasConcept C55493867 @default.
- W2897826647 hasConcept C59415355 @default.
- W2897826647 hasConceptScore W2897826647C104317684 @default.
- W2897826647 hasConceptScore W2897826647C105580179 @default.
- W2897826647 hasConceptScore W2897826647C111919701 @default.
- W2897826647 hasConceptScore W2897826647C118505674 @default.
- W2897826647 hasConceptScore W2897826647C138885662 @default.
- W2897826647 hasConceptScore W2897826647C149364088 @default.
- W2897826647 hasConceptScore W2897826647C154945302 @default.
- W2897826647 hasConceptScore W2897826647C185592680 @default.
- W2897826647 hasConceptScore W2897826647C203005215 @default.
- W2897826647 hasConceptScore W2897826647C204321447 @default.
- W2897826647 hasConceptScore W2897826647C2777413886 @default.
- W2897826647 hasConceptScore W2897826647C2777530160 @default.
- W2897826647 hasConceptScore W2897826647C28490314 @default.
- W2897826647 hasConceptScore W2897826647C41008148 @default.
- W2897826647 hasConceptScore W2897826647C41895202 @default.
- W2897826647 hasConceptScore W2897826647C46686674 @default.
- W2897826647 hasConceptScore W2897826647C50644808 @default.
- W2897826647 hasConceptScore W2897826647C55493867 @default.
- W2897826647 hasConceptScore W2897826647C59415355 @default.
- W2897826647 hasLocation W28978266471 @default.
- W2897826647 hasOpenAccess W2897826647 @default.
- W2897826647 hasPrimaryLocation W28978266471 @default.
- W2897826647 hasRelatedWork W170118632 @default.
- W2897826647 hasRelatedWork W1947252915 @default.
- W2897826647 hasRelatedWork W1978971213 @default.
- W2897826647 hasRelatedWork W2156422881 @default.
- W2897826647 hasRelatedWork W2507994462 @default.
- W2897826647 hasRelatedWork W2552838200 @default.
- W2897826647 hasRelatedWork W2606032440 @default.
- W2897826647 hasRelatedWork W2946260846 @default.
- W2897826647 hasRelatedWork W2964093087 @default.
- W2897826647 hasRelatedWork W3107474891 @default.
- W2897826647 isParatext "false" @default.
- W2897826647 isRetracted "false" @default.
- W2897826647 magId "2897826647" @default.
- W2897826647 workType "article" @default.