Matches in SemOpenAlex for { <https://semopenalex.org/work/W4310581413> ?p ?o ?g. }
Showing items 1 to 65 of
65
with 100 items per page.
- W4310581413 abstract "Data size is vital for neural transliteration. But getting lots of transliteration pairs is difficult, especially for low-resource languages. So how much data is sufficient for an often-used neural transliteration model with good performance? Firstly, the Tensor2Tensor (T2T) neural Transformer transliteration model is selected for its good performance in transliteration. Then select all language pair datasets from English to other languages with more than 40k data and freely available from the website (six datasets in total). Afterwards, conduct neural transliteration experiments for the six data sets. According to experimental results, when the training data size is 20k, the accuracy of six tasks is more than 90% of the best accuracy based on all training data, and the accuracy can exceed 0.45. When the training data size is 15k, the accuracy of six tasks is more than 85% of the best accuracy based on all training data. Therefore, 20k training data is likely sufficient for the Tensor2Tensor neural Transformer transliteration model." @default.
- W4310581413 created "2022-12-12" @default.
- W4310581413 creator A5019447527 @default.
- W4310581413 creator A5081411724 @default.
- W4310581413 creator A5085211629 @default.
- W4310581413 date "2022-10-27" @default.
- W4310581413 modified "2023-09-25" @default.
- W4310581413 title "How Much Data is Sufficient for Neural Transliteration?" @default.
- W4310581413 cites W2090755665 @default.
- W4310581413 cites W2757988102 @default.
- W4310581413 cites W2885158679 @default.
- W4310581413 cites W2885242435 @default.
- W4310581413 cites W2885678784 @default.
- W4310581413 cites W2886440583 @default.
- W4310581413 cites W2887185954 @default.
- W4310581413 cites W2890511566 @default.
- W4310581413 cites W2963042536 @default.
- W4310581413 cites W2964343439 @default.
- W4310581413 cites W2887660679 @default.
- W4310581413 doi "https://doi.org/10.1109/ialp57159.2022.9961269" @default.
- W4310581413 hasPublicationYear "2022" @default.
- W4310581413 type Work @default.
- W4310581413 citedByCount "0" @default.
- W4310581413 crossrefType "proceedings-article" @default.
- W4310581413 hasAuthorship W4310581413A5019447527 @default.
- W4310581413 hasAuthorship W4310581413A5081411724 @default.
- W4310581413 hasAuthorship W4310581413A5085211629 @default.
- W4310581413 hasConcept C119599485 @default.
- W4310581413 hasConcept C119857082 @default.
- W4310581413 hasConcept C127413603 @default.
- W4310581413 hasConcept C154945302 @default.
- W4310581413 hasConcept C165801399 @default.
- W4310581413 hasConcept C204321447 @default.
- W4310581413 hasConcept C41008148 @default.
- W4310581413 hasConcept C50644808 @default.
- W4310581413 hasConcept C51632099 @default.
- W4310581413 hasConcept C520968082 @default.
- W4310581413 hasConcept C66322947 @default.
- W4310581413 hasConceptScore W4310581413C119599485 @default.
- W4310581413 hasConceptScore W4310581413C119857082 @default.
- W4310581413 hasConceptScore W4310581413C127413603 @default.
- W4310581413 hasConceptScore W4310581413C154945302 @default.
- W4310581413 hasConceptScore W4310581413C165801399 @default.
- W4310581413 hasConceptScore W4310581413C204321447 @default.
- W4310581413 hasConceptScore W4310581413C41008148 @default.
- W4310581413 hasConceptScore W4310581413C50644808 @default.
- W4310581413 hasConceptScore W4310581413C51632099 @default.
- W4310581413 hasConceptScore W4310581413C520968082 @default.
- W4310581413 hasConceptScore W4310581413C66322947 @default.
- W4310581413 hasLocation W43105814131 @default.
- W4310581413 hasOpenAccess W4310581413 @default.
- W4310581413 hasPrimaryLocation W43105814131 @default.
- W4310581413 hasRelatedWork W1538473846 @default.
- W4310581413 hasRelatedWork W1968084137 @default.
- W4310581413 hasRelatedWork W2019156225 @default.
- W4310581413 hasRelatedWork W2118379766 @default.
- W4310581413 hasRelatedWork W2251215683 @default.
- W4310581413 hasRelatedWork W2505414515 @default.
- W4310581413 hasRelatedWork W3014391559 @default.
- W4310581413 hasRelatedWork W3116443244 @default.
- W4310581413 hasRelatedWork W3166486483 @default.
- W4310581413 hasRelatedWork W1629725936 @default.
- W4310581413 isParatext "false" @default.
- W4310581413 isRetracted "false" @default.
- W4310581413 workType "article" @default.