Matches in SemOpenAlex for { <https://semopenalex.org/work/W2971459527> ?p ?o ?g. }
Showing items 1 to 90 of
90
with 100 items per page.
- W2971459527 abstract "Despite impressive empirical successes of neural machine translation (NMT) on standard benchmarks, limited parallel data impedes the application of NMT models to many language pairs. Data augmentation methods such as back-translation make it possible to use monolingual data to help alleviate these issues, but back-translation itself fails in extreme low-resource scenarios, especially for syntactically divergent languages. In this paper, we propose a simple yet effective solution, whereby target-language sentences are re-ordered to match the order of the source and used as an additional source of training-time supervision. Experiments with simulated low-resource Japanese-to-English, and real low-resource Uyghur-to-English scenarios find significant improvements over other semi-supervised alternatives." @default.
- W2971459527 created "2019-09-12" @default.
- W2971459527 creator A5052828977 @default.
- W2971459527 creator A5068811427 @default.
- W2971459527 creator A5078672329 @default.
- W2971459527 creator A5085263462 @default.
- W2971459527 date "2019-08-30" @default.
- W2971459527 modified "2023-09-23" @default.
- W2971459527 title "Handling Syntactic Divergence in Low-resource Machine Translation" @default.
- W2971459527 cites W1508577659 @default.
- W2971459527 cites W2008961349 @default.
- W2971459527 cites W2117278770 @default.
- W2971459527 cites W2136544838 @default.
- W2971459527 cites W2153508793 @default.
- W2971459527 cites W2155607551 @default.
- W2971459527 cites W2156985047 @default.
- W2971459527 cites W2546938941 @default.
- W2971459527 cites W2576482813 @default.
- W2971459527 cites W2623037479 @default.
- W2971459527 cites W2756566411 @default.
- W2971459527 cites W2887920589 @default.
- W2971459527 cites W2888740011 @default.
- W2971459527 cites W2913659301 @default.
- W2971459527 cites W2963216553 @default.
- W2971459527 cites W2963403868 @default.
- W2971459527 cites W2963506925 @default.
- W2971459527 cites W2963667932 @default.
- W2971459527 cites W2964259010 @default.
- W2971459527 cites W3203149905 @default.
- W2971459527 cites W2250333994 @default.
- W2971459527 doi "https://doi.org/10.48550/arxiv.1909.00040" @default.
- W2971459527 hasPublicationYear "2019" @default.
- W2971459527 type Work @default.
- W2971459527 sameAs 2971459527 @default.
- W2971459527 citedByCount "0" @default.
- W2971459527 crossrefType "posted-content" @default.
- W2971459527 hasAuthorship W2971459527A5052828977 @default.
- W2971459527 hasAuthorship W2971459527A5068811427 @default.
- W2971459527 hasAuthorship W2971459527A5078672329 @default.
- W2971459527 hasAuthorship W2971459527A5085263462 @default.
- W2971459527 hasBestOaLocation W29714595271 @default.
- W2971459527 hasConcept C104317684 @default.
- W2971459527 hasConcept C105580179 @default.
- W2971459527 hasConcept C119857082 @default.
- W2971459527 hasConcept C138885662 @default.
- W2971459527 hasConcept C149364088 @default.
- W2971459527 hasConcept C154945302 @default.
- W2971459527 hasConcept C185592680 @default.
- W2971459527 hasConcept C203005215 @default.
- W2971459527 hasConcept C204321447 @default.
- W2971459527 hasConcept C206345919 @default.
- W2971459527 hasConcept C207390915 @default.
- W2971459527 hasConcept C24687705 @default.
- W2971459527 hasConcept C31258907 @default.
- W2971459527 hasConcept C41008148 @default.
- W2971459527 hasConcept C41895202 @default.
- W2971459527 hasConcept C55493867 @default.
- W2971459527 hasConceptScore W2971459527C104317684 @default.
- W2971459527 hasConceptScore W2971459527C105580179 @default.
- W2971459527 hasConceptScore W2971459527C119857082 @default.
- W2971459527 hasConceptScore W2971459527C138885662 @default.
- W2971459527 hasConceptScore W2971459527C149364088 @default.
- W2971459527 hasConceptScore W2971459527C154945302 @default.
- W2971459527 hasConceptScore W2971459527C185592680 @default.
- W2971459527 hasConceptScore W2971459527C203005215 @default.
- W2971459527 hasConceptScore W2971459527C204321447 @default.
- W2971459527 hasConceptScore W2971459527C206345919 @default.
- W2971459527 hasConceptScore W2971459527C207390915 @default.
- W2971459527 hasConceptScore W2971459527C24687705 @default.
- W2971459527 hasConceptScore W2971459527C31258907 @default.
- W2971459527 hasConceptScore W2971459527C41008148 @default.
- W2971459527 hasConceptScore W2971459527C41895202 @default.
- W2971459527 hasConceptScore W2971459527C55493867 @default.
- W2971459527 hasLocation W29714595271 @default.
- W2971459527 hasOpenAccess W2971459527 @default.
- W2971459527 hasPrimaryLocation W29714595271 @default.
- W2971459527 hasRelatedWork W1559710535 @default.
- W2971459527 hasRelatedWork W2010828773 @default.
- W2971459527 hasRelatedWork W2104127567 @default.
- W2971459527 hasRelatedWork W2122294272 @default.
- W2971459527 hasRelatedWork W2571522432 @default.
- W2971459527 hasRelatedWork W2807593602 @default.
- W2971459527 hasRelatedWork W2886649344 @default.
- W2971459527 hasRelatedWork W3107474891 @default.
- W2971459527 hasRelatedWork W2182786480 @default.
- W2971459527 hasRelatedWork W2186795678 @default.
- W2971459527 isParatext "false" @default.
- W2971459527 isRetracted "false" @default.
- W2971459527 magId "2971459527" @default.
- W2971459527 workType "article" @default.