Matches in SemOpenAlex for { <https://semopenalex.org/work/W3044112470> ?p ?o ?g. }
- W3044112470 endingPage "404" @default.
- W3044112470 startingPage "387" @default.
- W3044112470 abstract "Neural Machine Translation (NMT) is an end-to-end learning approach for automated translation, overcoming the weaknesses of conventional phrase-based translation systems. Although NMT based systems have gained their popularity in commercial translation applications, there is still plenty of room for improvement. Being the most popular search algorithm in NMT, beam search is vital to the translation result. However, traditional beam search can produce duplicate or missing translation due to its target sequence selection strategy. Aiming to alleviate this problem, this paper proposed neural machine translation improvements based on a novel beam search evaluation function. And we use reinforcement learning to train a translation evaluation system to select better candidate words for generating translations. In the experiments, we conducted extensive experiments to evaluate our methods. CASIA corpus and the 1,000,000 pairs of bilingual corpora of NiuTrans are used in our experiments. The experiment results prove that the proposed methods can effectively improve the English to Chinese translation quality." @default.
- W3044112470 created "2020-07-29" @default.
- W3044112470 creator A5021324317 @default.
- W3044112470 creator A5037839370 @default.
- W3044112470 creator A5058982256 @default.
- W3044112470 creator A5067580558 @default.
- W3044112470 date "2020-01-01" @default.
- W3044112470 modified "2023-10-10" @default.
- W3044112470 title "A Novel Beam Search to Improve Neural Machine Translation for English-Chinese" @default.
- W3044112470 cites W1753482797 @default.
- W3044112470 cites W1810943226 @default.
- W3044112470 cites W1816313093 @default.
- W3044112470 cites W1968594024 @default.
- W3044112470 cites W2525778437 @default.
- W3044112470 cites W2531409750 @default.
- W3044112470 cites W2782578088 @default.
- W3044112470 cites W2801521191 @default.
- W3044112470 cites W2801540583 @default.
- W3044112470 cites W2949888546 @default.
- W3044112470 cites W2950438065 @default.
- W3044112470 cites W2950580142 @default.
- W3044112470 cites W2950635152 @default.
- W3044112470 cites W2953333557 @default.
- W3044112470 cites W2964461714 @default.
- W3044112470 cites W3004860639 @default.
- W3044112470 doi "https://doi.org/10.32604/cmc.2020.010984" @default.
- W3044112470 hasPublicationYear "2020" @default.
- W3044112470 type Work @default.
- W3044112470 sameAs 3044112470 @default.
- W3044112470 citedByCount "4" @default.
- W3044112470 countsByYear W30441124702021 @default.
- W3044112470 countsByYear W30441124702022 @default.
- W3044112470 countsByYear W30441124702023 @default.
- W3044112470 crossrefType "journal-article" @default.
- W3044112470 hasAuthorship W3044112470A5021324317 @default.
- W3044112470 hasAuthorship W3044112470A5037839370 @default.
- W3044112470 hasAuthorship W3044112470A5058982256 @default.
- W3044112470 hasAuthorship W3044112470A5067580558 @default.
- W3044112470 hasBestOaLocation W30441124701 @default.
- W3044112470 hasConcept C104317684 @default.
- W3044112470 hasConcept C105580179 @default.
- W3044112470 hasConcept C111472728 @default.
- W3044112470 hasConcept C11413529 @default.
- W3044112470 hasConcept C119857082 @default.
- W3044112470 hasConcept C125583679 @default.
- W3044112470 hasConcept C135784402 @default.
- W3044112470 hasConcept C138885662 @default.
- W3044112470 hasConcept C148526163 @default.
- W3044112470 hasConcept C149364088 @default.
- W3044112470 hasConcept C154945302 @default.
- W3044112470 hasConcept C15744967 @default.
- W3044112470 hasConcept C185592680 @default.
- W3044112470 hasConcept C19889080 @default.
- W3044112470 hasConcept C203005215 @default.
- W3044112470 hasConcept C204321447 @default.
- W3044112470 hasConcept C24687705 @default.
- W3044112470 hasConcept C2776224158 @default.
- W3044112470 hasConcept C2779530757 @default.
- W3044112470 hasConcept C2780586970 @default.
- W3044112470 hasConcept C41008148 @default.
- W3044112470 hasConcept C55493867 @default.
- W3044112470 hasConcept C77805123 @default.
- W3044112470 hasConcept C81917197 @default.
- W3044112470 hasConceptScore W3044112470C104317684 @default.
- W3044112470 hasConceptScore W3044112470C105580179 @default.
- W3044112470 hasConceptScore W3044112470C111472728 @default.
- W3044112470 hasConceptScore W3044112470C11413529 @default.
- W3044112470 hasConceptScore W3044112470C119857082 @default.
- W3044112470 hasConceptScore W3044112470C125583679 @default.
- W3044112470 hasConceptScore W3044112470C135784402 @default.
- W3044112470 hasConceptScore W3044112470C138885662 @default.
- W3044112470 hasConceptScore W3044112470C148526163 @default.
- W3044112470 hasConceptScore W3044112470C149364088 @default.
- W3044112470 hasConceptScore W3044112470C154945302 @default.
- W3044112470 hasConceptScore W3044112470C15744967 @default.
- W3044112470 hasConceptScore W3044112470C185592680 @default.
- W3044112470 hasConceptScore W3044112470C19889080 @default.
- W3044112470 hasConceptScore W3044112470C203005215 @default.
- W3044112470 hasConceptScore W3044112470C204321447 @default.
- W3044112470 hasConceptScore W3044112470C24687705 @default.
- W3044112470 hasConceptScore W3044112470C2776224158 @default.
- W3044112470 hasConceptScore W3044112470C2779530757 @default.
- W3044112470 hasConceptScore W3044112470C2780586970 @default.
- W3044112470 hasConceptScore W3044112470C41008148 @default.
- W3044112470 hasConceptScore W3044112470C55493867 @default.
- W3044112470 hasConceptScore W3044112470C77805123 @default.
- W3044112470 hasConceptScore W3044112470C81917197 @default.
- W3044112470 hasIssue "1" @default.
- W3044112470 hasLocation W30441124701 @default.
- W3044112470 hasOpenAccess W3044112470 @default.
- W3044112470 hasPrimaryLocation W30441124701 @default.
- W3044112470 hasRelatedWork W2122287718 @default.
- W3044112470 hasRelatedWork W2384400852 @default.
- W3044112470 hasRelatedWork W2532807140 @default.
- W3044112470 hasRelatedWork W2587602790 @default.
- W3044112470 hasRelatedWork W2962780935 @default.
- W3044112470 hasRelatedWork W3196981096 @default.
- W3044112470 hasRelatedWork W3204448004 @default.