Matches in SemOpenAlex for { <https://semopenalex.org/work/W3199704633> ?p ?o ?g. }
Showing items 1 to 97 of
97
with 100 items per page.
- W3199704633 abstract "While various neural machine translation (NMT) methods have integrated multiple prior knowledge to guide the translation, no research is available on combining with source-target bilingual translation template. In this paper, we firstly propose a maximal-length noun phrase template (MNP-Template), which constructs a novel translation template focusing on the constituency syntactic structure. Secondly, building on the multi-source transformer framework, we design a template-based machine translation (TBMT) model to integrate the syntactic knowledge of the retrieved target template similar to the ground-truth translation in the NMT decoder. Experiment results show the effectiveness of MNP- Template and TBMT on test subsets filtered by the fuzzy match score. Moreover, our method achieves significant improvement in out-of-domain test sets, which well-validated the university across diverse domains." @default.
- W3199704633 created "2021-09-27" @default.
- W3199704633 creator A5008063608 @default.
- W3199704633 creator A5039878486 @default.
- W3199704633 creator A5065176335 @default.
- W3199704633 creator A5066140774 @default.
- W3199704633 date "2021-07-18" @default.
- W3199704633 modified "2023-09-23" @default.
- W3199704633 title "Guiding Neural Machine Translation with Retrieved Translation Template" @default.
- W3199704633 cites W1902237438 @default.
- W3199704633 cites W2058335193 @default.
- W3199704633 cites W2112900913 @default.
- W3199704633 cites W2124807415 @default.
- W3199704633 cites W2153800732 @default.
- W3199704633 cites W2400065810 @default.
- W3199704633 cites W2759932073 @default.
- W3199704633 cites W2891713103 @default.
- W3199704633 cites W2903533908 @default.
- W3199704633 cites W2950563121 @default.
- W3199704633 cites W2962708992 @default.
- W3199704633 cites W2962826395 @default.
- W3199704633 cites W2963212250 @default.
- W3199704633 cites W2963352809 @default.
- W3199704633 cites W2963829526 @default.
- W3199704633 cites W2964029788 @default.
- W3199704633 cites W2964034111 @default.
- W3199704633 cites W2970235285 @default.
- W3199704633 cites W3021915462 @default.
- W3199704633 cites W3035636774 @default.
- W3199704633 doi "https://doi.org/10.1109/ijcnn52387.2021.9533734" @default.
- W3199704633 hasPublicationYear "2021" @default.
- W3199704633 type Work @default.
- W3199704633 sameAs 3199704633 @default.
- W3199704633 citedByCount "3" @default.
- W3199704633 countsByYear W31997046332022 @default.
- W3199704633 countsByYear W31997046332023 @default.
- W3199704633 crossrefType "proceedings-article" @default.
- W3199704633 hasAuthorship W3199704633A5008063608 @default.
- W3199704633 hasAuthorship W3199704633A5039878486 @default.
- W3199704633 hasAuthorship W3199704633A5065176335 @default.
- W3199704633 hasAuthorship W3199704633A5066140774 @default.
- W3199704633 hasConcept C104317684 @default.
- W3199704633 hasConcept C105580179 @default.
- W3199704633 hasConcept C119599485 @default.
- W3199704633 hasConcept C121934690 @default.
- W3199704633 hasConcept C127413603 @default.
- W3199704633 hasConcept C130597682 @default.
- W3199704633 hasConcept C149364088 @default.
- W3199704633 hasConcept C153962237 @default.
- W3199704633 hasConcept C154945302 @default.
- W3199704633 hasConcept C165801399 @default.
- W3199704633 hasConcept C185592680 @default.
- W3199704633 hasConcept C203005215 @default.
- W3199704633 hasConcept C204321447 @default.
- W3199704633 hasConcept C24687705 @default.
- W3199704633 hasConcept C2776224158 @default.
- W3199704633 hasConcept C41008148 @default.
- W3199704633 hasConcept C51802942 @default.
- W3199704633 hasConcept C55493867 @default.
- W3199704633 hasConcept C66322947 @default.
- W3199704633 hasConceptScore W3199704633C104317684 @default.
- W3199704633 hasConceptScore W3199704633C105580179 @default.
- W3199704633 hasConceptScore W3199704633C119599485 @default.
- W3199704633 hasConceptScore W3199704633C121934690 @default.
- W3199704633 hasConceptScore W3199704633C127413603 @default.
- W3199704633 hasConceptScore W3199704633C130597682 @default.
- W3199704633 hasConceptScore W3199704633C149364088 @default.
- W3199704633 hasConceptScore W3199704633C153962237 @default.
- W3199704633 hasConceptScore W3199704633C154945302 @default.
- W3199704633 hasConceptScore W3199704633C165801399 @default.
- W3199704633 hasConceptScore W3199704633C185592680 @default.
- W3199704633 hasConceptScore W3199704633C203005215 @default.
- W3199704633 hasConceptScore W3199704633C204321447 @default.
- W3199704633 hasConceptScore W3199704633C24687705 @default.
- W3199704633 hasConceptScore W3199704633C2776224158 @default.
- W3199704633 hasConceptScore W3199704633C41008148 @default.
- W3199704633 hasConceptScore W3199704633C51802942 @default.
- W3199704633 hasConceptScore W3199704633C55493867 @default.
- W3199704633 hasConceptScore W3199704633C66322947 @default.
- W3199704633 hasFunder F4320321001 @default.
- W3199704633 hasLocation W31997046331 @default.
- W3199704633 hasOpenAccess W3199704633 @default.
- W3199704633 hasPrimaryLocation W31997046331 @default.
- W3199704633 hasRelatedWork W1674885750 @default.
- W3199704633 hasRelatedWork W171331851 @default.
- W3199704633 hasRelatedWork W2007433094 @default.
- W3199704633 hasRelatedWork W2081122336 @default.
- W3199704633 hasRelatedWork W2136332941 @default.
- W3199704633 hasRelatedWork W2250821182 @default.
- W3199704633 hasRelatedWork W2294868251 @default.
- W3199704633 hasRelatedWork W4254664587 @default.
- W3199704633 hasRelatedWork W49707343 @default.
- W3199704633 hasRelatedWork W626175318 @default.
- W3199704633 isParatext "false" @default.
- W3199704633 isRetracted "false" @default.
- W3199704633 magId "3199704633" @default.
- W3199704633 workType "article" @default.