FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4307874711> ?p ?o ?g. }

• W4307874711 endingPage "2815" @default.
• W4307874711 startingPage "2803" @default.
• W4307874711 abstract "When the Transformer proposed by Google in 2017, it was first used for machine translation tasks and achieved the state of the art at that time. Although the current neural machine translation model can generate high quality translation results, there are still mistranslations and omissions in the translation of key information of long sentences. On the other hand, the most important part in traditional translation tasks is the translation of key information. In the translation results, as long as the key information is translated accurately and completely, even if other parts of the results are translated incorrect, the final translation results’ quality can still be guaranteed. In order to solve the problem of mistranslation and missed translation effectively, and improve the accuracy and completeness of long sentence translation in machine translation, this paper proposes a key information fused neural machine translation model based on Transformer. The model proposed in this paper extracts the keywords of the source language text separately as the input of the encoder. After the same encoding as the source language text, it is fused with the output of the source language text encoded by the encoder, then the key information is processed and input into the decoder. With incorporating keyword information from the source language sentence, the model’s performance in the task of translating long sentences is very reliable. In order to verify the effectiveness of the method of fusion of key information proposed in this paper, a series of experiments were carried out on the verification set. The experimental results show that the Bilingual Evaluation Understudy (BLEU) score of the model proposed in this paper on the Workshop on Machine Translation (WMT) 2017 test dataset is higher than the BLEU score of Transformer proposed by Google on the WMT2017 test dataset. The experimental results show the advantages of the model proposed in this paper." @default.
• W4307874711 created "2022-11-06" @default.
• W4307874711 creator A5009035849 @default.
• W4307874711 creator A5024284011 @default.
• W4307874711 creator A5025625195 @default.
• W4307874711 creator A5049459342 @default.
• W4307874711 creator A5056660601 @default.
• W4307874711 creator A5068186954 @default.
• W4307874711 creator A5072548035 @default.
• W4307874711 creator A5074734978 @default.
• W4307874711 creator A5081601993 @default.
• W4307874711 creator A5082020327 @default.
• W4307874711 creator A5091508492 @default.
• W4307874711 date "2023-01-01" @default.
• W4307874711 modified "2023-09-29" @default.
• W4307874711 title "Neural Machine Translation by Fusing Key Information of Text" @default.
• W4307874711 cites W2132083787 @default.
• W4307874711 cites W2531207078 @default.
• W4307874711 cites W2807006873 @default.
• W4307874711 cites W2973226110 @default.
• W4307874711 cites W3007146536 @default.
• W4307874711 cites W3038500142 @default.
• W4307874711 cites W3043276386 @default.
• W4307874711 cites W3167289674 @default.
• W4307874711 cites W3194589868 @default.
• W4307874711 cites W3197777794 @default.
• W4307874711 doi "https://doi.org/10.32604/cmc.2023.032732" @default.
• W4307874711 hasPublicationYear "2023" @default.
• W4307874711 type Work @default.
• W4307874711 citedByCount "0" @default.
• W4307874711 crossrefType "journal-article" @default.
• W4307874711 hasAuthorship W4307874711A5009035849 @default.
• W4307874711 hasAuthorship W4307874711A5024284011 @default.
• W4307874711 hasAuthorship W4307874711A5025625195 @default.
• W4307874711 hasAuthorship W4307874711A5049459342 @default.
• W4307874711 hasAuthorship W4307874711A5056660601 @default.
• W4307874711 hasAuthorship W4307874711A5068186954 @default.
• W4307874711 hasAuthorship W4307874711A5072548035 @default.
• W4307874711 hasAuthorship W4307874711A5074734978 @default.
• W4307874711 hasAuthorship W4307874711A5081601993 @default.
• W4307874711 hasAuthorship W4307874711A5082020327 @default.
• W4307874711 hasAuthorship W4307874711A5091508492 @default.
• W4307874711 hasBestOaLocation W43078747111 @default.
• W4307874711 hasConcept C104317684 @default.
• W4307874711 hasConcept C105580179 @default.
• W4307874711 hasConcept C111919701 @default.
• W4307874711 hasConcept C118505674 @default.
• W4307874711 hasConcept C120012220 @default.
• W4307874711 hasConcept C121332964 @default.
• W4307874711 hasConcept C130597682 @default.
• W4307874711 hasConcept C135784402 @default.
• W4307874711 hasConcept C137293760 @default.
• W4307874711 hasConcept C148526163 @default.
• W4307874711 hasConcept C149364088 @default.
• W4307874711 hasConcept C154945302 @default.
• W4307874711 hasConcept C165801399 @default.
• W4307874711 hasConcept C185592680 @default.
• W4307874711 hasConcept C203005215 @default.
• W4307874711 hasConcept C204321447 @default.
• W4307874711 hasConcept C24687705 @default.
• W4307874711 hasConcept C26517878 @default.
• W4307874711 hasConcept C2777530160 @default.
• W4307874711 hasConcept C28490314 @default.
• W4307874711 hasConcept C38652104 @default.
• W4307874711 hasConcept C41008148 @default.
• W4307874711 hasConcept C53893814 @default.
• W4307874711 hasConcept C55493867 @default.
• W4307874711 hasConcept C62520636 @default.
• W4307874711 hasConcept C66322947 @default.
• W4307874711 hasConceptScore W4307874711C104317684 @default.
• W4307874711 hasConceptScore W4307874711C105580179 @default.
• W4307874711 hasConceptScore W4307874711C111919701 @default.
• W4307874711 hasConceptScore W4307874711C118505674 @default.
• W4307874711 hasConceptScore W4307874711C120012220 @default.
• W4307874711 hasConceptScore W4307874711C121332964 @default.
• W4307874711 hasConceptScore W4307874711C130597682 @default.
• W4307874711 hasConceptScore W4307874711C135784402 @default.
• W4307874711 hasConceptScore W4307874711C137293760 @default.
• W4307874711 hasConceptScore W4307874711C148526163 @default.
• W4307874711 hasConceptScore W4307874711C149364088 @default.
• W4307874711 hasConceptScore W4307874711C154945302 @default.
• W4307874711 hasConceptScore W4307874711C165801399 @default.
• W4307874711 hasConceptScore W4307874711C185592680 @default.
• W4307874711 hasConceptScore W4307874711C203005215 @default.
• W4307874711 hasConceptScore W4307874711C204321447 @default.
• W4307874711 hasConceptScore W4307874711C24687705 @default.
• W4307874711 hasConceptScore W4307874711C26517878 @default.
• W4307874711 hasConceptScore W4307874711C2777530160 @default.
• W4307874711 hasConceptScore W4307874711C28490314 @default.
• W4307874711 hasConceptScore W4307874711C38652104 @default.
• W4307874711 hasConceptScore W4307874711C41008148 @default.
• W4307874711 hasConceptScore W4307874711C53893814 @default.
• W4307874711 hasConceptScore W4307874711C55493867 @default.
• W4307874711 hasConceptScore W4307874711C62520636 @default.
• W4307874711 hasConceptScore W4307874711C66322947 @default.
• W4307874711 hasIssue "2" @default.
• W4307874711 hasLocation W43078747111 @default.
• W4307874711 hasOpenAccess W4307874711 @default.

• next