Matches in SemOpenAlex for { <https://semopenalex.org/work/W2808417541> ?p ?o ?g. }
Showing items 1 to 77 of
77
with 100 items per page.
- W2808417541 abstract "In sentence classification tasks, additional contexts, such as the neighboring sentences, may improve the accuracy of the classifier. However, such contexts are domain-dependent and thus cannot be used for another classification task with an inappropriate domain. In contrast, we propose the use of translated sentences as context that is always available regardless of the domain. We find that naive feature expansion of translations gains only marginal improvements and may decrease the performance of the classifier, due to possible inaccurate translations thus producing noisy sentence vectors. To this end, we present multiple context fixing attachment (MCFA), a series of modules attached to multiple sentence vectors to fix the noise in the vectors using the other sentence vectors as context. We show that our method performs competitively compared to previous models, achieving best classification performance on multiple data sets. We are the first to use translations as domain-free contexts for sentence classification." @default.
- W2808417541 created "2018-06-21" @default.
- W2808417541 creator A5002722298 @default.
- W2808417541 creator A5009993083 @default.
- W2808417541 creator A5024873601 @default.
- W2808417541 creator A5087095491 @default.
- W2808417541 date "2018-06-14" @default.
- W2808417541 modified "2023-09-23" @default.
- W2808417541 title "Translations as Additional Contexts for Sentence Classification" @default.
- W2808417541 cites W2097726431 @default.
- W2808417541 cites W2107620532 @default.
- W2808417541 cites W2114524997 @default.
- W2808417541 cites W2130339025 @default.
- W2808417541 cites W2160660844 @default.
- W2808417541 cites W2164019165 @default.
- W2808417541 cites W2194775991 @default.
- W2808417541 cites W2251849926 @default.
- W2808417541 cites W2271328876 @default.
- W2808417541 cites W2550821151 @default.
- W2808417541 cites W2610120229 @default.
- W2808417541 cites W2949437134 @default.
- W2808417541 cites W2950910987 @default.
- W2808417541 cites W2952186591 @default.
- W2808417541 cites W2952566282 @default.
- W2808417541 cites W2964308564 @default.
- W2808417541 doi "https://doi.org/10.48550/arxiv.1806.05516" @default.
- W2808417541 hasPublicationYear "2018" @default.
- W2808417541 type Work @default.
- W2808417541 sameAs 2808417541 @default.
- W2808417541 citedByCount "0" @default.
- W2808417541 crossrefType "posted-content" @default.
- W2808417541 hasAuthorship W2808417541A5002722298 @default.
- W2808417541 hasAuthorship W2808417541A5009993083 @default.
- W2808417541 hasAuthorship W2808417541A5024873601 @default.
- W2808417541 hasAuthorship W2808417541A5087095491 @default.
- W2808417541 hasBestOaLocation W28084175411 @default.
- W2808417541 hasConcept C134306372 @default.
- W2808417541 hasConcept C151730666 @default.
- W2808417541 hasConcept C154945302 @default.
- W2808417541 hasConcept C204321447 @default.
- W2808417541 hasConcept C2777530160 @default.
- W2808417541 hasConcept C2779343474 @default.
- W2808417541 hasConcept C28490314 @default.
- W2808417541 hasConcept C33923547 @default.
- W2808417541 hasConcept C36503486 @default.
- W2808417541 hasConcept C41008148 @default.
- W2808417541 hasConcept C86803240 @default.
- W2808417541 hasConcept C95623464 @default.
- W2808417541 hasConceptScore W2808417541C134306372 @default.
- W2808417541 hasConceptScore W2808417541C151730666 @default.
- W2808417541 hasConceptScore W2808417541C154945302 @default.
- W2808417541 hasConceptScore W2808417541C204321447 @default.
- W2808417541 hasConceptScore W2808417541C2777530160 @default.
- W2808417541 hasConceptScore W2808417541C2779343474 @default.
- W2808417541 hasConceptScore W2808417541C28490314 @default.
- W2808417541 hasConceptScore W2808417541C33923547 @default.
- W2808417541 hasConceptScore W2808417541C36503486 @default.
- W2808417541 hasConceptScore W2808417541C41008148 @default.
- W2808417541 hasConceptScore W2808417541C86803240 @default.
- W2808417541 hasConceptScore W2808417541C95623464 @default.
- W2808417541 hasLocation W28084175411 @default.
- W2808417541 hasOpenAccess W2808417541 @default.
- W2808417541 hasPrimaryLocation W28084175411 @default.
- W2808417541 hasRelatedWork W1517743118 @default.
- W2808417541 hasRelatedWork W1567338489 @default.
- W2808417541 hasRelatedWork W159132833 @default.
- W2808417541 hasRelatedWork W1978971213 @default.
- W2808417541 hasRelatedWork W2163556058 @default.
- W2808417541 hasRelatedWork W2369835347 @default.
- W2808417541 hasRelatedWork W3107474891 @default.
- W2808417541 hasRelatedWork W3171566221 @default.
- W2808417541 hasRelatedWork W38394648 @default.
- W2808417541 hasRelatedWork W4200223488 @default.
- W2808417541 isParatext "false" @default.
- W2808417541 isRetracted "false" @default.
- W2808417541 magId "2808417541" @default.
- W2808417541 workType "article" @default.