Matches in SemOpenAlex for { <https://semopenalex.org/work/W143809087> ?p ?o ?g. }
Showing items 1 to 96 of
96
with 100 items per page.
- W143809087 endingPage "125" @default.
- W143809087 startingPage "115" @default.
- W143809087 abstract "AbstractThe word level system combination, which is better than phrase level and sentence level, has emerged as a powerful post-processing method for statistical machine translation (SMT). This paper first give the definition of HyperGraph(HG) as a kind of compact data structure in SMT, and then introduce simple bracket transduction grammar(SBTG) for hypergraph decoding. To optimize the more feature weights, we introduce minimum risk (MR) with deterministic annealing (DA) into the training criterion, and compare two classic training procedures in experiment. The deoding approaches of n-gram model based on hypergraph are shown to be superior to conventional cube pruning in the setting of the Chinese-to-English track of the 2008 NIST Open MT evaluation.KeywordsSystem combinationHyperGraphN-gram modelInside-outside Pruning" @default.
- W143809087 created "2016-06-24" @default.
- W143809087 creator A5038560914 @default.
- W143809087 creator A5053726259 @default.
- W143809087 creator A5059276926 @default.
- W143809087 date "2011-01-01" @default.
- W143809087 modified "2023-09-26" @default.
- W143809087 title "A Decoding Method of System Combination Based on Hypergraph in SMT" @default.
- W143809087 cites W1483849869 @default.
- W143809087 cites W2006019948 @default.
- W143809087 cites W2037894654 @default.
- W143809087 cites W2095683820 @default.
- W143809087 cites W2103149536 @default.
- W143809087 cites W2110660056 @default.
- W143809087 cites W2118439278 @default.
- W143809087 cites W2118536060 @default.
- W143809087 cites W2118972857 @default.
- W143809087 cites W2122489459 @default.
- W143809087 cites W2128232128 @default.
- W143809087 cites W2132001515 @default.
- W143809087 cites W2138414624 @default.
- W143809087 cites W2145033586 @default.
- W143809087 cites W2146113428 @default.
- W143809087 cites W2159358338 @default.
- W143809087 cites W2171802951 @default.
- W143809087 cites W2437005631 @default.
- W143809087 doi "https://doi.org/10.1007/978-3-642-23896-3_14" @default.
- W143809087 hasPublicationYear "2011" @default.
- W143809087 type Work @default.
- W143809087 sameAs 143809087 @default.
- W143809087 citedByCount "0" @default.
- W143809087 crossrefType "book-chapter" @default.
- W143809087 hasAuthorship W143809087A5038560914 @default.
- W143809087 hasAuthorship W143809087A5053726259 @default.
- W143809087 hasAuthorship W143809087A5059276926 @default.
- W143809087 hasConcept C108010975 @default.
- W143809087 hasConcept C11413529 @default.
- W143809087 hasConcept C118615104 @default.
- W143809087 hasConcept C154945302 @default.
- W143809087 hasConcept C203005215 @default.
- W143809087 hasConcept C203357204 @default.
- W143809087 hasConcept C204321447 @default.
- W143809087 hasConcept C2777530160 @default.
- W143809087 hasConcept C2781221856 @default.
- W143809087 hasConcept C33923547 @default.
- W143809087 hasConcept C41008148 @default.
- W143809087 hasConcept C53893814 @default.
- W143809087 hasConcept C57273362 @default.
- W143809087 hasConcept C6557445 @default.
- W143809087 hasConcept C80444323 @default.
- W143809087 hasConcept C86803240 @default.
- W143809087 hasConceptScore W143809087C108010975 @default.
- W143809087 hasConceptScore W143809087C11413529 @default.
- W143809087 hasConceptScore W143809087C118615104 @default.
- W143809087 hasConceptScore W143809087C154945302 @default.
- W143809087 hasConceptScore W143809087C203005215 @default.
- W143809087 hasConceptScore W143809087C203357204 @default.
- W143809087 hasConceptScore W143809087C204321447 @default.
- W143809087 hasConceptScore W143809087C2777530160 @default.
- W143809087 hasConceptScore W143809087C2781221856 @default.
- W143809087 hasConceptScore W143809087C33923547 @default.
- W143809087 hasConceptScore W143809087C41008148 @default.
- W143809087 hasConceptScore W143809087C53893814 @default.
- W143809087 hasConceptScore W143809087C57273362 @default.
- W143809087 hasConceptScore W143809087C6557445 @default.
- W143809087 hasConceptScore W143809087C80444323 @default.
- W143809087 hasConceptScore W143809087C86803240 @default.
- W143809087 hasLocation W1438090871 @default.
- W143809087 hasOpenAccess W143809087 @default.
- W143809087 hasPrimaryLocation W1438090871 @default.
- W143809087 hasRelatedWork W1507220965 @default.
- W143809087 hasRelatedWork W1510052640 @default.
- W143809087 hasRelatedWork W1639395665 @default.
- W143809087 hasRelatedWork W2053323879 @default.
- W143809087 hasRelatedWork W2102695322 @default.
- W143809087 hasRelatedWork W2105132850 @default.
- W143809087 hasRelatedWork W2113000545 @default.
- W143809087 hasRelatedWork W2114550122 @default.
- W143809087 hasRelatedWork W2116494538 @default.
- W143809087 hasRelatedWork W2139635790 @default.
- W143809087 hasRelatedWork W2142333053 @default.
- W143809087 hasRelatedWork W2149747182 @default.
- W143809087 hasRelatedWork W2161586008 @default.
- W143809087 hasRelatedWork W2183896207 @default.
- W143809087 hasRelatedWork W2188071272 @default.
- W143809087 hasRelatedWork W2250918721 @default.
- W143809087 hasRelatedWork W2251844685 @default.
- W143809087 hasRelatedWork W2557984873 @default.
- W143809087 hasRelatedWork W2984080744 @default.
- W143809087 hasRelatedWork W2163863073 @default.
- W143809087 isParatext "false" @default.
- W143809087 isRetracted "false" @default.
- W143809087 magId "143809087" @default.
- W143809087 workType "book-chapter" @default.