Matches in SemOpenAlex for { <https://semopenalex.org/work/W2034991102> ?p ?o ?g. }
- W2034991102 endingPage "339" @default.
- W2034991102 startingPage "317" @default.
- W2034991102 abstract "This article describes a method that successfully exploits syntactic features for n-best translation candidate reranking using perceptrons. We motivate the utility of syntax by demonstrating the superior performance of parsers over n-gram language models in differentiating between Statistical Machine Translation output and human translations. Our approach uses discriminative language modelling to rerank the n-best translations generated by a statistical machine translation system. The performance is evaluated for Arabic-to-English translation using NIST’s MT-Eval benchmarks. While deep features extracted from parse trees do not consistently help, we show how features extracted from a shallow Part-of-Speech annotation layer outperform a competitive baseline and a state-of-the-art comparative reranking approach, leading to significant BLEU improvements on three different test sets." @default.
- W2034991102 created "2016-06-24" @default.
- W2034991102 creator A5008032834 @default.
- W2034991102 creator A5021578107 @default.
- W2034991102 date "2011-09-01" @default.
- W2034991102 modified "2023-09-24" @default.
- W2034991102 title "Syntactic discriminative language model rerankers for statistical machine translation" @default.
- W2034991102 cites W1631260214 @default.
- W2034991102 cites W1973923101 @default.
- W2034991102 cites W2017708149 @default.
- W2034991102 cites W2056250865 @default.
- W2034991102 cites W2062323476 @default.
- W2034991102 cites W2066370905 @default.
- W2034991102 cites W2093647425 @default.
- W2034991102 cites W2110417778 @default.
- W2034991102 cites W2111142112 @default.
- W2034991102 cites W2113762394 @default.
- W2034991102 cites W2124445791 @default.
- W2034991102 cites W2124807415 @default.
- W2034991102 cites W2128201184 @default.
- W2034991102 cites W2129727551 @default.
- W2034991102 cites W2140343992 @default.
- W2034991102 cites W2142112143 @default.
- W2034991102 cites W2143564602 @default.
- W2034991102 cites W2146574666 @default.
- W2034991102 cites W2152263452 @default.
- W2034991102 cites W2158025800 @default.
- W2034991102 cites W2158148237 @default.
- W2034991102 cites W2160697141 @default.
- W2034991102 cites W2280403519 @default.
- W2034991102 cites W2437005631 @default.
- W2034991102 cites W2794026841 @default.
- W2034991102 cites W4241645538 @default.
- W2034991102 cites W4249572517 @default.
- W2034991102 doi "https://doi.org/10.1007/s10590-011-9108-7" @default.
- W2034991102 hasPublicationYear "2011" @default.
- W2034991102 type Work @default.
- W2034991102 sameAs 2034991102 @default.
- W2034991102 citedByCount "11" @default.
- W2034991102 countsByYear W20349911022012 @default.
- W2034991102 countsByYear W20349911022014 @default.
- W2034991102 countsByYear W20349911022015 @default.
- W2034991102 countsByYear W20349911022016 @default.
- W2034991102 countsByYear W20349911022019 @default.
- W2034991102 crossrefType "journal-article" @default.
- W2034991102 hasAuthorship W2034991102A5008032834 @default.
- W2034991102 hasAuthorship W2034991102A5021578107 @default.
- W2034991102 hasBestOaLocation W20349911021 @default.
- W2034991102 hasConcept C104317684 @default.
- W2034991102 hasConcept C105580179 @default.
- W2034991102 hasConcept C111219384 @default.
- W2034991102 hasConcept C135784402 @default.
- W2034991102 hasConcept C137293760 @default.
- W2034991102 hasConcept C148526163 @default.
- W2034991102 hasConcept C149364088 @default.
- W2034991102 hasConcept C154945302 @default.
- W2034991102 hasConcept C155092808 @default.
- W2034991102 hasConcept C185592680 @default.
- W2034991102 hasConcept C186644900 @default.
- W2034991102 hasConcept C203005215 @default.
- W2034991102 hasConcept C204321447 @default.
- W2034991102 hasConcept C24687705 @default.
- W2034991102 hasConcept C41008148 @default.
- W2034991102 hasConcept C50644808 @default.
- W2034991102 hasConcept C55493867 @default.
- W2034991102 hasConcept C60048249 @default.
- W2034991102 hasConcept C60908668 @default.
- W2034991102 hasConcept C622187 @default.
- W2034991102 hasConcept C97931131 @default.
- W2034991102 hasConceptScore W2034991102C104317684 @default.
- W2034991102 hasConceptScore W2034991102C105580179 @default.
- W2034991102 hasConceptScore W2034991102C111219384 @default.
- W2034991102 hasConceptScore W2034991102C135784402 @default.
- W2034991102 hasConceptScore W2034991102C137293760 @default.
- W2034991102 hasConceptScore W2034991102C148526163 @default.
- W2034991102 hasConceptScore W2034991102C149364088 @default.
- W2034991102 hasConceptScore W2034991102C154945302 @default.
- W2034991102 hasConceptScore W2034991102C155092808 @default.
- W2034991102 hasConceptScore W2034991102C185592680 @default.
- W2034991102 hasConceptScore W2034991102C186644900 @default.
- W2034991102 hasConceptScore W2034991102C203005215 @default.
- W2034991102 hasConceptScore W2034991102C204321447 @default.
- W2034991102 hasConceptScore W2034991102C24687705 @default.
- W2034991102 hasConceptScore W2034991102C41008148 @default.
- W2034991102 hasConceptScore W2034991102C50644808 @default.
- W2034991102 hasConceptScore W2034991102C55493867 @default.
- W2034991102 hasConceptScore W2034991102C60048249 @default.
- W2034991102 hasConceptScore W2034991102C60908668 @default.
- W2034991102 hasConceptScore W2034991102C622187 @default.
- W2034991102 hasConceptScore W2034991102C97931131 @default.
- W2034991102 hasIssue "4" @default.
- W2034991102 hasLocation W20349911021 @default.
- W2034991102 hasLocation W20349911022 @default.
- W2034991102 hasOpenAccess W2034991102 @default.
- W2034991102 hasPrimaryLocation W20349911021 @default.
- W2034991102 hasRelatedWork W179314280 @default.
- W2034991102 hasRelatedWork W2034991102 @default.
- W2034991102 hasRelatedWork W2113541941 @default.