Matches in SemOpenAlex for { <https://semopenalex.org/work/W1554769004> ?p ?o ?g. }
- W1554769004 abstract "Automatic segmentation of text into minimal content-bearing units is an unsolved problem even for languages like English. Spaces between words offer an easy first approximation, but this approximation is not good enough for machine translation (MT), where many word sequences are not translated word-for-word. This paper presents an efficient automatic method for discovering sequences of words that are translated as a unit. The method proceeds by comparing pairs of statistical translation models induced from parallel texts in two languages. It can discover hundreds of non-compositional compounds on each iteration, and constructs longer compounds out of shorter ones. Objective evaluation on a simple machine translation task has shown the method's potential to improve the quality of MT output. The method makes few assumptions about the data, so it can be applied to parallel data other than parallel texts, such as word spellings and pronunciations." @default.
- W1554769004 created "2016-06-24" @default.
- W1554769004 creator A5030467789 @default.
- W1554769004 date "1997-01-01" @default.
- W1554769004 modified "2023-09-24" @default.
- W1554769004 title "Automatic Discovery of Non-Compositional Compounds in Parallel Data" @default.
- W1554769004 cites W1480519300 @default.
- W1554769004 cites W1510951099 @default.
- W1554769004 cites W1558333962 @default.
- W1554769004 cites W1794601440 @default.
- W1554769004 cites W2006969979 @default.
- W1554769004 cites W203873490 @default.
- W1554769004 cites W2041167939 @default.
- W1554769004 cites W2096071381 @default.
- W1554769004 cites W2120234416 @default.
- W1554769004 cites W2121227244 @default.
- W1554769004 cites W2123282296 @default.
- W1554769004 cites W2127314673 @default.
- W1554769004 cites W2129706127 @default.
- W1554769004 cites W2137638032 @default.
- W1554769004 cites W2138553032 @default.
- W1554769004 cites W2138787466 @default.
- W1554769004 cites W2162172169 @default.
- W1554769004 cites W2745142526 @default.
- W1554769004 cites W2963010813 @default.
- W1554769004 cites W3005278268 @default.
- W1554769004 hasPublicationYear "1997" @default.
- W1554769004 type Work @default.
- W1554769004 sameAs 1554769004 @default.
- W1554769004 citedByCount "47" @default.
- W1554769004 countsByYear W15547690042012 @default.
- W1554769004 countsByYear W15547690042013 @default.
- W1554769004 countsByYear W15547690042014 @default.
- W1554769004 countsByYear W15547690042016 @default.
- W1554769004 countsByYear W15547690042017 @default.
- W1554769004 crossrefType "proceedings-article" @default.
- W1554769004 hasAuthorship W1554769004A5030467789 @default.
- W1554769004 hasConcept C104317684 @default.
- W1554769004 hasConcept C105580179 @default.
- W1554769004 hasConcept C111472728 @default.
- W1554769004 hasConcept C138885662 @default.
- W1554769004 hasConcept C149364088 @default.
- W1554769004 hasConcept C154945302 @default.
- W1554769004 hasConcept C162324750 @default.
- W1554769004 hasConcept C185592680 @default.
- W1554769004 hasConcept C187736073 @default.
- W1554769004 hasConcept C203005215 @default.
- W1554769004 hasConcept C204321447 @default.
- W1554769004 hasConcept C2524010 @default.
- W1554769004 hasConcept C2780451532 @default.
- W1554769004 hasConcept C2780586882 @default.
- W1554769004 hasConcept C33923547 @default.
- W1554769004 hasConcept C41008148 @default.
- W1554769004 hasConcept C55493867 @default.
- W1554769004 hasConcept C89600930 @default.
- W1554769004 hasConcept C90805587 @default.
- W1554769004 hasConcept C98501671 @default.
- W1554769004 hasConceptScore W1554769004C104317684 @default.
- W1554769004 hasConceptScore W1554769004C105580179 @default.
- W1554769004 hasConceptScore W1554769004C111472728 @default.
- W1554769004 hasConceptScore W1554769004C138885662 @default.
- W1554769004 hasConceptScore W1554769004C149364088 @default.
- W1554769004 hasConceptScore W1554769004C154945302 @default.
- W1554769004 hasConceptScore W1554769004C162324750 @default.
- W1554769004 hasConceptScore W1554769004C185592680 @default.
- W1554769004 hasConceptScore W1554769004C187736073 @default.
- W1554769004 hasConceptScore W1554769004C203005215 @default.
- W1554769004 hasConceptScore W1554769004C204321447 @default.
- W1554769004 hasConceptScore W1554769004C2524010 @default.
- W1554769004 hasConceptScore W1554769004C2780451532 @default.
- W1554769004 hasConceptScore W1554769004C2780586882 @default.
- W1554769004 hasConceptScore W1554769004C33923547 @default.
- W1554769004 hasConceptScore W1554769004C41008148 @default.
- W1554769004 hasConceptScore W1554769004C55493867 @default.
- W1554769004 hasConceptScore W1554769004C89600930 @default.
- W1554769004 hasConceptScore W1554769004C90805587 @default.
- W1554769004 hasConceptScore W1554769004C98501671 @default.
- W1554769004 hasLocation W15547690041 @default.
- W1554769004 hasOpenAccess W1554769004 @default.
- W1554769004 hasPrimaryLocation W15547690041 @default.
- W1554769004 hasRelatedWork W1480519300 @default.
- W1554769004 hasRelatedWork W1489181569 @default.
- W1554769004 hasRelatedWork W1498763386 @default.
- W1554769004 hasRelatedWork W1543107604 @default.
- W1554769004 hasRelatedWork W1574901103 @default.
- W1554769004 hasRelatedWork W1593045043 @default.
- W1554769004 hasRelatedWork W1940278502 @default.
- W1554769004 hasRelatedWork W1969178697 @default.
- W1554769004 hasRelatedWork W2006969979 @default.
- W1554769004 hasRelatedWork W2097333193 @default.
- W1554769004 hasRelatedWork W2101105183 @default.
- W1554769004 hasRelatedWork W2116780029 @default.
- W1554769004 hasRelatedWork W2123282296 @default.
- W1554769004 hasRelatedWork W2126168798 @default.
- W1554769004 hasRelatedWork W2138753018 @default.
- W1554769004 hasRelatedWork W2153653739 @default.
- W1554769004 hasRelatedWork W2154384676 @default.
- W1554769004 hasRelatedWork W2156985047 @default.
- W1554769004 hasRelatedWork W2439228446 @default.
- W1554769004 hasRelatedWork W2949523069 @default.