Matches in SemOpenAlex for { <https://semopenalex.org/work/W4328006266> ?p ?o ?g. }
Showing items 1 to 86 of
86
with 100 items per page.
- W4328006266 abstract "Existing document-level neural machine translation (NMT) models have sufficiently explored different context settings to provide guidance for target generation. However, little attention is paid to inaugurate more diverse contexts for abundant context information. In this paper, we propose a Selective Memory-augmented Neural Document Translation model (SMDT) to expand the context and reduce the hypothesis space of attention. Specifically, we retrieve similar bilingual sentence pairs from the training corpus to augment global context and then extend the two-stream attention model with a selection mechanism to capture local context and diverse global contexts. This unified approach allows our model to be trained elegantly on three publicly document-level machine translation datasets and significantly outperforms previous document-level NMT models." @default.
- W4328006266 created "2023-03-22" @default.
- W4328006266 creator A5024042896 @default.
- W4328006266 creator A5073568638 @default.
- W4328006266 creator A5086155499 @default.
- W4328006266 date "2022-08-01" @default.
- W4328006266 modified "2023-09-27" @default.
- W4328006266 title "Selective Memory-Augmented Document Translation with Diverse Global Context" @default.
- W4328006266 cites W2101105183 @default.
- W4328006266 cites W2514722822 @default.
- W4328006266 cites W2758310181 @default.
- W4328006266 cites W2906152891 @default.
- W4328006266 cites W2952446148 @default.
- W4328006266 cites W2962712961 @default.
- W4328006266 cites W2962784628 @default.
- W4328006266 cites W2962943802 @default.
- W4328006266 cites W2963109507 @default.
- W4328006266 cites W2963842551 @default.
- W4328006266 cites W2964202354 @default.
- W4328006266 cites W2964289193 @default.
- W4328006266 cites W2964291396 @default.
- W4328006266 cites W2970311224 @default.
- W4328006266 cites W2970529093 @default.
- W4328006266 cites W2971278086 @default.
- W4328006266 cites W3001434439 @default.
- W4328006266 cites W3034351728 @default.
- W4328006266 cites W3034700448 @default.
- W4328006266 cites W3035520602 @default.
- W4328006266 cites W3102507836 @default.
- W4328006266 cites W3205775125 @default.
- W4328006266 doi "https://doi.org/10.1109/bigcom57025.2022.00030" @default.
- W4328006266 hasPublicationYear "2022" @default.
- W4328006266 type Work @default.
- W4328006266 citedByCount "0" @default.
- W4328006266 crossrefType "proceedings-article" @default.
- W4328006266 hasAuthorship W4328006266A5024042896 @default.
- W4328006266 hasAuthorship W4328006266A5073568638 @default.
- W4328006266 hasAuthorship W4328006266A5086155499 @default.
- W4328006266 hasConcept C104317684 @default.
- W4328006266 hasConcept C105580179 @default.
- W4328006266 hasConcept C149364088 @default.
- W4328006266 hasConcept C151730666 @default.
- W4328006266 hasConcept C154945302 @default.
- W4328006266 hasConcept C183322885 @default.
- W4328006266 hasConcept C185592680 @default.
- W4328006266 hasConcept C203005215 @default.
- W4328006266 hasConcept C204321447 @default.
- W4328006266 hasConcept C2777530160 @default.
- W4328006266 hasConcept C2779343474 @default.
- W4328006266 hasConcept C2781238097 @default.
- W4328006266 hasConcept C41008148 @default.
- W4328006266 hasConcept C55493867 @default.
- W4328006266 hasConcept C81917197 @default.
- W4328006266 hasConcept C86803240 @default.
- W4328006266 hasConceptScore W4328006266C104317684 @default.
- W4328006266 hasConceptScore W4328006266C105580179 @default.
- W4328006266 hasConceptScore W4328006266C149364088 @default.
- W4328006266 hasConceptScore W4328006266C151730666 @default.
- W4328006266 hasConceptScore W4328006266C154945302 @default.
- W4328006266 hasConceptScore W4328006266C183322885 @default.
- W4328006266 hasConceptScore W4328006266C185592680 @default.
- W4328006266 hasConceptScore W4328006266C203005215 @default.
- W4328006266 hasConceptScore W4328006266C204321447 @default.
- W4328006266 hasConceptScore W4328006266C2777530160 @default.
- W4328006266 hasConceptScore W4328006266C2779343474 @default.
- W4328006266 hasConceptScore W4328006266C2781238097 @default.
- W4328006266 hasConceptScore W4328006266C41008148 @default.
- W4328006266 hasConceptScore W4328006266C55493867 @default.
- W4328006266 hasConceptScore W4328006266C81917197 @default.
- W4328006266 hasConceptScore W4328006266C86803240 @default.
- W4328006266 hasLocation W43280062661 @default.
- W4328006266 hasOpenAccess W4328006266 @default.
- W4328006266 hasPrimaryLocation W43280062661 @default.
- W4328006266 hasRelatedWork W170118632 @default.
- W4328006266 hasRelatedWork W1947252915 @default.
- W4328006266 hasRelatedWork W1964392734 @default.
- W4328006266 hasRelatedWork W1978971213 @default.
- W4328006266 hasRelatedWork W2359582629 @default.
- W4328006266 hasRelatedWork W2507994462 @default.
- W4328006266 hasRelatedWork W2606032440 @default.
- W4328006266 hasRelatedWork W2946260846 @default.
- W4328006266 hasRelatedWork W3107474891 @default.
- W4328006266 hasRelatedWork W4287208387 @default.
- W4328006266 isParatext "false" @default.
- W4328006266 isRetracted "false" @default.
- W4328006266 workType "article" @default.