Matches in SemOpenAlex for { <https://semopenalex.org/work/W2113998052> ?p ?o ?g. }
- W2113998052 abstract "Efficiency is a prime concern in syntactic MT decoding, yet significant developments in statistical parsing with respect to asymptotic efficiency haven't yet been explored in MT. Recently, McDonald et al. (2005b) formalized dependency parsing as a maximum spanning tree (MST) problem, which can be solved in quadratic time relative to the length of the sentence. They show that MST parsing is almost as accurate as cubic-time dependency parsing in the case of English, and that it is more accurate with free word order languages. This paper applies MST parsing to MT, and describes how it can be integrated into a phrase-based decoder to compute dependency language model scores. Our results show that augmenting a state-of-the-art phrase-based system with this dependency language model leads to significant improvements in TER (0.92%) and BLEU (0.45%) scores on five NIST Chinese-English evaluation test sets." @default.
- W2113998052 created "2016-06-24" @default.
- W2113998052 creator A5037066465 @default.
- W2113998052 creator A5046006076 @default.
- W2113998052 date "2009-01-01" @default.
- W2113998052 modified "2023-09-25" @default.
- W2113998052 title "Quadratic-time dependency parsing for machine translation" @default.
- W2113998052 cites W1555286493 @default.
- W2113998052 cites W1631260214 @default.
- W2113998052 cites W1714704734 @default.
- W2113998052 cites W1988615825 @default.
- W2113998052 cites W1996430422 @default.
- W2113998052 cites W1998325433 @default.
- W2113998052 cites W2005712418 @default.
- W2113998052 cites W2052449326 @default.
- W2113998052 cites W2096466920 @default.
- W2113998052 cites W2101105183 @default.
- W2113998052 cites W2105891181 @default.
- W2113998052 cites W2109664771 @default.
- W2113998052 cites W2116410915 @default.
- W2113998052 cites W2116957398 @default.
- W2113998052 cites W2117086786 @default.
- W2113998052 cites W2119168550 @default.
- W2113998052 cites W2120354757 @default.
- W2113998052 cites W2122922578 @default.
- W2113998052 cites W2124807415 @default.
- W2113998052 cites W2131988669 @default.
- W2113998052 cites W2144279206 @default.
- W2113998052 cites W2146418175 @default.
- W2113998052 cites W2146574666 @default.
- W2113998052 cites W2149327368 @default.
- W2113998052 cites W2152263452 @default.
- W2113998052 cites W2153653739 @default.
- W2113998052 cites W2153800732 @default.
- W2113998052 cites W2158522418 @default.
- W2113998052 cites W2160382364 @default.
- W2113998052 cites W2161227214 @default.
- W2113998052 cites W2166905217 @default.
- W2113998052 cites W2171332413 @default.
- W2113998052 cites W2171421863 @default.
- W2113998052 cites W2242975712 @default.
- W2113998052 cites W2280403519 @default.
- W2113998052 cites W23077562 @default.
- W2113998052 cites W2963847008 @default.
- W2113998052 cites W81000870 @default.
- W2113998052 cites W2188521008 @default.
- W2113998052 doi "https://doi.org/10.3115/1690219.1690255" @default.
- W2113998052 hasPublicationYear "2009" @default.
- W2113998052 type Work @default.
- W2113998052 sameAs 2113998052 @default.
- W2113998052 citedByCount "41" @default.
- W2113998052 countsByYear W21139980522012 @default.
- W2113998052 countsByYear W21139980522013 @default.
- W2113998052 countsByYear W21139980522014 @default.
- W2113998052 countsByYear W21139980522018 @default.
- W2113998052 countsByYear W21139980522019 @default.
- W2113998052 countsByYear W21139980522020 @default.
- W2113998052 countsByYear W21139980522022 @default.
- W2113998052 crossrefType "proceedings-article" @default.
- W2113998052 hasAuthorship W2113998052A5037066465 @default.
- W2113998052 hasAuthorship W2113998052A5046006076 @default.
- W2113998052 hasBestOaLocation W21139980521 @default.
- W2113998052 hasConcept C104317684 @default.
- W2113998052 hasConcept C105580179 @default.
- W2113998052 hasConcept C129844170 @default.
- W2113998052 hasConcept C149364088 @default.
- W2113998052 hasConcept C154945302 @default.
- W2113998052 hasConcept C164883195 @default.
- W2113998052 hasConcept C185592680 @default.
- W2113998052 hasConcept C186644900 @default.
- W2113998052 hasConcept C19768560 @default.
- W2113998052 hasConcept C199360897 @default.
- W2113998052 hasConcept C203005215 @default.
- W2113998052 hasConcept C204321447 @default.
- W2113998052 hasConcept C2524010 @default.
- W2113998052 hasConcept C33923547 @default.
- W2113998052 hasConcept C41008148 @default.
- W2113998052 hasConcept C42560504 @default.
- W2113998052 hasConcept C55493867 @default.
- W2113998052 hasConcept C60690694 @default.
- W2113998052 hasConceptScore W2113998052C104317684 @default.
- W2113998052 hasConceptScore W2113998052C105580179 @default.
- W2113998052 hasConceptScore W2113998052C129844170 @default.
- W2113998052 hasConceptScore W2113998052C149364088 @default.
- W2113998052 hasConceptScore W2113998052C154945302 @default.
- W2113998052 hasConceptScore W2113998052C164883195 @default.
- W2113998052 hasConceptScore W2113998052C185592680 @default.
- W2113998052 hasConceptScore W2113998052C186644900 @default.
- W2113998052 hasConceptScore W2113998052C19768560 @default.
- W2113998052 hasConceptScore W2113998052C199360897 @default.
- W2113998052 hasConceptScore W2113998052C203005215 @default.
- W2113998052 hasConceptScore W2113998052C204321447 @default.
- W2113998052 hasConceptScore W2113998052C2524010 @default.
- W2113998052 hasConceptScore W2113998052C33923547 @default.
- W2113998052 hasConceptScore W2113998052C41008148 @default.
- W2113998052 hasConceptScore W2113998052C42560504 @default.
- W2113998052 hasConceptScore W2113998052C55493867 @default.
- W2113998052 hasConceptScore W2113998052C60690694 @default.
- W2113998052 hasLocation W21139980521 @default.
- W2113998052 hasOpenAccess W2113998052 @default.