Matches in SemOpenAlex for { <https://semopenalex.org/work/W2892961366> ?p ?o ?g. }
Showing items 1 to 79 of
79
with 100 items per page.
- W2892961366 endingPage "1183" @default.
- W2892961366 startingPage "1163" @default.
- W2892961366 abstract "Machine translation is an important field of research and development. Word reordering is one of the main problems in machine translation. It is an important factor of quality and efficiency of machine translations and becomes more difficult when it deals with structurally divergent language pairs. To overcome this problem, we introduce a neural reordering model, using phrasal dependency trees which depict dependency relations among contiguous non-syntactic phrases. The model makes the use of reordering rules, which are automatically learned by a probabilistic neural network classifier from a reordered phrasal dependency tree bank. The proposed model combines the power of the lexical reordering and syntactic pre-ordering models by performing long-distance reorderings. The proposed reordering model is integrated into a standard phrase-based statistical machine translation system to translate input sentences. Our method is evaluated on syntactically divergent language-pairs, English → Persian and English → German using WMT07 benchmark. The results illustrate the superiority of the proposed method in terms of BLEU, TER and LRscore on both translation tasks. On average the proposed method retrieves a significant impact on precision and recall values respect to the hierarchical, lexicalized and distortion reordering models." @default.
- W2892961366 created "2018-10-05" @default.
- W2892961366 creator A5012248611 @default.
- W2892961366 creator A5047175258 @default.
- W2892961366 creator A5055598777 @default.
- W2892961366 date "2018-09-26" @default.
- W2892961366 modified "2023-09-27" @default.
- W2892961366 title "A neural reordering model based on phrasal dependency tree for statistical machine translation" @default.
- W2892961366 cites W100623710 @default.
- W2892961366 cites W1970689298 @default.
- W2892961366 cites W1973923101 @default.
- W2892961366 cites W2020029245 @default.
- W2892961366 cites W2036291627 @default.
- W2892961366 cites W2039289813 @default.
- W2892961366 cites W2043908551 @default.
- W2892961366 cites W2044804339 @default.
- W2892961366 cites W2073710650 @default.
- W2892961366 cites W2105245376 @default.
- W2892961366 cites W2117130368 @default.
- W2892961366 cites W2118536060 @default.
- W2892961366 cites W2119168550 @default.
- W2892961366 cites W2124807415 @default.
- W2892961366 cites W2143263475 @default.
- W2892961366 cites W2144946927 @default.
- W2892961366 cites W2146574666 @default.
- W2892961366 cites W2152263452 @default.
- W2892961366 cites W2153653739 @default.
- W2892961366 cites W2153800732 @default.
- W2892961366 cites W2162245945 @default.
- W2892961366 cites W2165828367 @default.
- W2892961366 cites W2247119764 @default.
- W2892961366 cites W2437005631 @default.
- W2892961366 cites W4255634348 @default.
- W2892961366 doi "https://doi.org/10.3233/ida-173582" @default.
- W2892961366 hasPublicationYear "2018" @default.
- W2892961366 type Work @default.
- W2892961366 sameAs 2892961366 @default.
- W2892961366 citedByCount "5" @default.
- W2892961366 countsByYear W28929613662020 @default.
- W2892961366 countsByYear W28929613662022 @default.
- W2892961366 crossrefType "journal-article" @default.
- W2892961366 hasAuthorship W2892961366A5012248611 @default.
- W2892961366 hasAuthorship W2892961366A5047175258 @default.
- W2892961366 hasAuthorship W2892961366A5055598777 @default.
- W2892961366 hasConcept C137293760 @default.
- W2892961366 hasConcept C154945302 @default.
- W2892961366 hasConcept C19768560 @default.
- W2892961366 hasConcept C203005215 @default.
- W2892961366 hasConcept C204321447 @default.
- W2892961366 hasConcept C2776224158 @default.
- W2892961366 hasConcept C41008148 @default.
- W2892961366 hasConceptScore W2892961366C137293760 @default.
- W2892961366 hasConceptScore W2892961366C154945302 @default.
- W2892961366 hasConceptScore W2892961366C19768560 @default.
- W2892961366 hasConceptScore W2892961366C203005215 @default.
- W2892961366 hasConceptScore W2892961366C204321447 @default.
- W2892961366 hasConceptScore W2892961366C2776224158 @default.
- W2892961366 hasConceptScore W2892961366C41008148 @default.
- W2892961366 hasIssue "5" @default.
- W2892961366 hasLocation W28929613661 @default.
- W2892961366 hasOpenAccess W2892961366 @default.
- W2892961366 hasPrimaryLocation W28929613661 @default.
- W2892961366 hasRelatedWork W1555786581 @default.
- W2892961366 hasRelatedWork W1954109191 @default.
- W2892961366 hasRelatedWork W1989367739 @default.
- W2892961366 hasRelatedWork W2104554525 @default.
- W2892961366 hasRelatedWork W2125823897 @default.
- W2892961366 hasRelatedWork W2289817541 @default.
- W2892961366 hasRelatedWork W2560869699 @default.
- W2892961366 hasRelatedWork W2739533097 @default.
- W2892961366 hasRelatedWork W2763920727 @default.
- W2892961366 hasRelatedWork W3003568313 @default.
- W2892961366 hasVolume "22" @default.
- W2892961366 isParatext "false" @default.
- W2892961366 isRetracted "false" @default.
- W2892961366 magId "2892961366" @default.
- W2892961366 workType "article" @default.