Matches in SemOpenAlex for { <https://semopenalex.org/work/W2129400979> ?p ?o ?g. }
- W2129400979 abstract "Languages that have no explicit word delimiters often have to be segmented for statistical machine translation (SMT). This is commonly performed by automated segmenters trained on manually annotated corpora. However, the word segmentation (WS) schemes of these annotated corpora are handcrafted for general usage, and may not be suitable for SMT. An analysis was performed to test this hypothesis using a manually annotated word alignment (WA) corpus for Chinese-English SMT. An analysis revealed that 74.60% of the sentences in the WA corpus if segmented using an automated segmenter trained on the Penn Chinese Treebank (CTB) will contain conflicts with the gold WA annotations. We formulated an approach based on word splitting with reference to the annotated WA to alleviate these conflicts. Experimental results show that the refined WS reduced word alignment error rate by 6.82% and achieved the highest BLEU improvement (0.63 on average) on the Chinese-English open machine translation (OpenMT) corpora compared to related work." @default.
- W2129400979 created "2016-06-24" @default.
- W2129400979 creator A5021667085 @default.
- W2129400979 creator A5033318800 @default.
- W2129400979 creator A5048473316 @default.
- W2129400979 creator A5081198426 @default.
- W2129400979 date "2014-01-01" @default.
- W2129400979 modified "2023-09-27" @default.
- W2129400979 title "Refining Word Segmentation Using a Manually Aligned Corpus for Statistical Machine Translation" @default.
- W2129400979 cites W1979102019 @default.
- W2129400979 cites W1981791873 @default.
- W2129400979 cites W2033295622 @default.
- W2129400979 cites W2036516910 @default.
- W2129400979 cites W2095907708 @default.
- W2129400979 cites W2096765155 @default.
- W2129400979 cites W2101105183 @default.
- W2129400979 cites W2111798208 @default.
- W2129400979 cites W2124807415 @default.
- W2129400979 cites W2131988669 @default.
- W2129400979 cites W2133229022 @default.
- W2129400979 cites W2141532438 @default.
- W2129400979 cites W2144783305 @default.
- W2129400979 cites W2146574666 @default.
- W2129400979 cites W2147880316 @default.
- W2129400979 cites W2149230967 @default.
- W2129400979 cites W2151197196 @default.
- W2129400979 cites W2156985047 @default.
- W2129400979 cites W2162465526 @default.
- W2129400979 cites W2164454850 @default.
- W2129400979 cites W2169724380 @default.
- W2129400979 cites W2293111166 @default.
- W2129400979 cites W2425667873 @default.
- W2129400979 cites W2467575451 @default.
- W2129400979 cites W3112842904 @default.
- W2129400979 cites W61894391 @default.
- W2129400979 cites W76894688 @default.
- W2129400979 doi "https://doi.org/10.3115/v1/d14-1173" @default.
- W2129400979 hasPublicationYear "2014" @default.
- W2129400979 type Work @default.
- W2129400979 sameAs 2129400979 @default.
- W2129400979 citedByCount "6" @default.
- W2129400979 countsByYear W21294009792016 @default.
- W2129400979 countsByYear W21294009792017 @default.
- W2129400979 countsByYear W21294009792019 @default.
- W2129400979 countsByYear W21294009792021 @default.
- W2129400979 countsByYear W21294009792023 @default.
- W2129400979 crossrefType "proceedings-article" @default.
- W2129400979 hasAuthorship W2129400979A5021667085 @default.
- W2129400979 hasAuthorship W2129400979A5033318800 @default.
- W2129400979 hasAuthorship W2129400979A5048473316 @default.
- W2129400979 hasAuthorship W2129400979A5081198426 @default.
- W2129400979 hasBestOaLocation W21294009792 @default.
- W2129400979 hasConcept C104317684 @default.
- W2129400979 hasConcept C105580179 @default.
- W2129400979 hasConcept C138885662 @default.
- W2129400979 hasConcept C149364088 @default.
- W2129400979 hasConcept C154945302 @default.
- W2129400979 hasConcept C185592680 @default.
- W2129400979 hasConcept C191897082 @default.
- W2129400979 hasConcept C192562407 @default.
- W2129400979 hasConcept C203005215 @default.
- W2129400979 hasConcept C204321447 @default.
- W2129400979 hasConcept C24687705 @default.
- W2129400979 hasConcept C28490314 @default.
- W2129400979 hasConcept C41008148 @default.
- W2129400979 hasConcept C41895202 @default.
- W2129400979 hasConcept C55493867 @default.
- W2129400979 hasConcept C60044698 @default.
- W2129400979 hasConcept C89600930 @default.
- W2129400979 hasConcept C90805587 @default.
- W2129400979 hasConcept C98501671 @default.
- W2129400979 hasConceptScore W2129400979C104317684 @default.
- W2129400979 hasConceptScore W2129400979C105580179 @default.
- W2129400979 hasConceptScore W2129400979C138885662 @default.
- W2129400979 hasConceptScore W2129400979C149364088 @default.
- W2129400979 hasConceptScore W2129400979C154945302 @default.
- W2129400979 hasConceptScore W2129400979C185592680 @default.
- W2129400979 hasConceptScore W2129400979C191897082 @default.
- W2129400979 hasConceptScore W2129400979C192562407 @default.
- W2129400979 hasConceptScore W2129400979C203005215 @default.
- W2129400979 hasConceptScore W2129400979C204321447 @default.
- W2129400979 hasConceptScore W2129400979C24687705 @default.
- W2129400979 hasConceptScore W2129400979C28490314 @default.
- W2129400979 hasConceptScore W2129400979C41008148 @default.
- W2129400979 hasConceptScore W2129400979C41895202 @default.
- W2129400979 hasConceptScore W2129400979C55493867 @default.
- W2129400979 hasConceptScore W2129400979C60044698 @default.
- W2129400979 hasConceptScore W2129400979C89600930 @default.
- W2129400979 hasConceptScore W2129400979C90805587 @default.
- W2129400979 hasConceptScore W2129400979C98501671 @default.
- W2129400979 hasLocation W21294009791 @default.
- W2129400979 hasLocation W21294009792 @default.
- W2129400979 hasOpenAccess W2129400979 @default.
- W2129400979 hasPrimaryLocation W21294009791 @default.
- W2129400979 hasRelatedWork W1412698887 @default.
- W2129400979 hasRelatedWork W2121524931 @default.
- W2129400979 hasRelatedWork W2129400979 @default.
- W2129400979 hasRelatedWork W2251488256 @default.
- W2129400979 hasRelatedWork W2542068976 @default.
- W2129400979 hasRelatedWork W2578428189 @default.