Matches in SemOpenAlex for { <https://semopenalex.org/work/W2577483721> ?p ?o ?g. }
- W2577483721 endingPage "1408" @default.
- W2577483721 startingPage "1398" @default.
- W2577483721 abstract "Evaluation of machine translation (MT) into morphologically rich languages (MRL) has not been well studied despite posing many challenges. In this paper, we explore the use of embeddings obtained from different levels of lexical and morpho-syntactic linguistic analysis and show that they improve MT evaluation into an MRL. Specifically we report on Arabic, a language with complex and rich morphology. Our results show that using a neural-network model with different input representations produces results that clearly outperform the state-of-the-art for MT evaluation into Arabic, by almost over 75% increase in correlation with human judgments on pairwise MT evaluation quality task. More importantly, we demonstrate the usefulness of morpho-syntactic representations to model sentence similarity for MT evaluation and address complex linguistic phenomena of Arabic." @default.
- W2577483721 created "2017-01-26" @default.
- W2577483721 creator A5025885625 @default.
- W2577483721 creator A5078234452 @default.
- W2577483721 creator A5084517393 @default.
- W2577483721 creator A5086933462 @default.
- W2577483721 date "2016-12-01" @default.
- W2577483721 modified "2023-09-28" @default.
- W2577483721 title "Machine translation evaluation for Arabic using morphologically-enriched embeddings" @default.
- W2577483721 cites W1489525520 @default.
- W2577483721 cites W1533861849 @default.
- W2577483721 cites W1606327999 @default.
- W2577483721 cites W179875071 @default.
- W2577483721 cites W1984052055 @default.
- W2577483721 cites W201141796 @default.
- W2577483721 cites W2018789714 @default.
- W2577483721 cites W2028176545 @default.
- W2577483721 cites W2032494091 @default.
- W2577483721 cites W2078861931 @default.
- W2577483721 cites W2087735403 @default.
- W2577483721 cites W2116492146 @default.
- W2577483721 cites W2121771196 @default.
- W2577483721 cites W2123442489 @default.
- W2577483721 cites W2132339004 @default.
- W2577483721 cites W2133280805 @default.
- W2577483721 cites W2135161317 @default.
- W2577483721 cites W2146502635 @default.
- W2577483721 cites W2147272182 @default.
- W2577483721 cites W2149327368 @default.
- W2577483721 cites W2153579005 @default.
- W2577483721 cites W2157331557 @default.
- W2577483721 cites W2159325621 @default.
- W2577483721 cites W2162499915 @default.
- W2577483721 cites W2163986298 @default.
- W2577483721 cites W2165213242 @default.
- W2577483721 cites W2165894879 @default.
- W2577483721 cites W2250188786 @default.
- W2577483721 cites W2250421192 @default.
- W2577483721 cites W2250597803 @default.
- W2577483721 cites W2250816155 @default.
- W2577483721 cites W2251171083 @default.
- W2577483721 cites W2251496547 @default.
- W2577483721 cites W2251682575 @default.
- W2577483721 cites W2251912507 @default.
- W2577483721 cites W2331726854 @default.
- W2577483721 cites W2512273476 @default.
- W2577483721 cites W2895810819 @default.
- W2577483721 cites W2963042536 @default.
- W2577483721 cites W2964005834 @default.
- W2577483721 cites W2964308564 @default.
- W2577483721 cites W38007939 @default.
- W2577483721 cites W4758264 @default.
- W2577483721 hasPublicationYear "2016" @default.
- W2577483721 type Work @default.
- W2577483721 sameAs 2577483721 @default.
- W2577483721 citedByCount "3" @default.
- W2577483721 countsByYear W25774837212017 @default.
- W2577483721 countsByYear W25774837212020 @default.
- W2577483721 crossrefType "proceedings-article" @default.
- W2577483721 hasAuthorship W2577483721A5025885625 @default.
- W2577483721 hasAuthorship W2577483721A5078234452 @default.
- W2577483721 hasAuthorship W2577483721A5084517393 @default.
- W2577483721 hasAuthorship W2577483721A5086933462 @default.
- W2577483721 hasConcept C103278499 @default.
- W2577483721 hasConcept C115961682 @default.
- W2577483721 hasConcept C135784402 @default.
- W2577483721 hasConcept C138885662 @default.
- W2577483721 hasConcept C148526163 @default.
- W2577483721 hasConcept C154945302 @default.
- W2577483721 hasConcept C162324750 @default.
- W2577483721 hasConcept C184898388 @default.
- W2577483721 hasConcept C187736073 @default.
- W2577483721 hasConcept C203005215 @default.
- W2577483721 hasConcept C204321447 @default.
- W2577483721 hasConcept C24687705 @default.
- W2577483721 hasConcept C2777261249 @default.
- W2577483721 hasConcept C2777530160 @default.
- W2577483721 hasConcept C2780451532 @default.
- W2577483721 hasConcept C41008148 @default.
- W2577483721 hasConcept C41895202 @default.
- W2577483721 hasConcept C59822182 @default.
- W2577483721 hasConcept C86803240 @default.
- W2577483721 hasConcept C96455323 @default.
- W2577483721 hasConceptScore W2577483721C103278499 @default.
- W2577483721 hasConceptScore W2577483721C115961682 @default.
- W2577483721 hasConceptScore W2577483721C135784402 @default.
- W2577483721 hasConceptScore W2577483721C138885662 @default.
- W2577483721 hasConceptScore W2577483721C148526163 @default.
- W2577483721 hasConceptScore W2577483721C154945302 @default.
- W2577483721 hasConceptScore W2577483721C162324750 @default.
- W2577483721 hasConceptScore W2577483721C184898388 @default.
- W2577483721 hasConceptScore W2577483721C187736073 @default.
- W2577483721 hasConceptScore W2577483721C203005215 @default.
- W2577483721 hasConceptScore W2577483721C204321447 @default.
- W2577483721 hasConceptScore W2577483721C24687705 @default.
- W2577483721 hasConceptScore W2577483721C2777261249 @default.
- W2577483721 hasConceptScore W2577483721C2777530160 @default.
- W2577483721 hasConceptScore W2577483721C2780451532 @default.