Matches in SemOpenAlex for { <https://semopenalex.org/work/W2762238293> ?p ?o ?g. }
Showing items 1 to 61 of
61
with 100 items per page.
- W2762238293 abstract "This thesis presents a system for correcting errors from optical character recognition (OCR) software. As a noisy-channel error correction system, it uses a language model to provide a prior over the true text. For this purpose, we introduce a lexicalized version of Klein and Manning's Dependency Model with Valence, a grammar that is trained without structure annotation. The novel language model provides error correction performance that is slightly better than a 4-gram baseline on a corpus of historical English text. When interpolated with the 4-gram model, a relative reduction in word error rate of 32.1% is achieved, which is 2.5% more than the 4-gram model alone. However, the improvement is primarily attributable not to the modeling of dependency structure, but rather to the modeling of word classes, which is included therein. We determined this by achieving a similar improvement while constraining the model to a uniformly right-branching structure." @default.
- W2762238293 created "2017-10-20" @default.
- W2762238293 creator A5030769584 @default.
- W2762238293 date "2021-05-10" @default.
- W2762238293 modified "2023-09-25" @default.
- W2762238293 title "Applying unsupervised grammar induction to OCR error correction" @default.
- W2762238293 doi "https://doi.org/10.17760/d20128346" @default.
- W2762238293 hasPublicationYear "2021" @default.
- W2762238293 type Work @default.
- W2762238293 sameAs 2762238293 @default.
- W2762238293 citedByCount "0" @default.
- W2762238293 crossrefType "dissertation" @default.
- W2762238293 hasAuthorship W2762238293A5030769584 @default.
- W2762238293 hasBestOaLocation W27622382931 @default.
- W2762238293 hasConcept C103088060 @default.
- W2762238293 hasConcept C11413529 @default.
- W2762238293 hasConcept C117884012 @default.
- W2762238293 hasConcept C137293760 @default.
- W2762238293 hasConcept C138885662 @default.
- W2762238293 hasConcept C154945302 @default.
- W2762238293 hasConcept C19768560 @default.
- W2762238293 hasConcept C204321447 @default.
- W2762238293 hasConcept C23224414 @default.
- W2762238293 hasConcept C26022165 @default.
- W2762238293 hasConcept C2776321320 @default.
- W2762238293 hasConcept C28490314 @default.
- W2762238293 hasConcept C40969351 @default.
- W2762238293 hasConcept C41008148 @default.
- W2762238293 hasConcept C41895202 @default.
- W2762238293 hasConceptScore W2762238293C103088060 @default.
- W2762238293 hasConceptScore W2762238293C11413529 @default.
- W2762238293 hasConceptScore W2762238293C117884012 @default.
- W2762238293 hasConceptScore W2762238293C137293760 @default.
- W2762238293 hasConceptScore W2762238293C138885662 @default.
- W2762238293 hasConceptScore W2762238293C154945302 @default.
- W2762238293 hasConceptScore W2762238293C19768560 @default.
- W2762238293 hasConceptScore W2762238293C204321447 @default.
- W2762238293 hasConceptScore W2762238293C23224414 @default.
- W2762238293 hasConceptScore W2762238293C26022165 @default.
- W2762238293 hasConceptScore W2762238293C2776321320 @default.
- W2762238293 hasConceptScore W2762238293C28490314 @default.
- W2762238293 hasConceptScore W2762238293C40969351 @default.
- W2762238293 hasConceptScore W2762238293C41008148 @default.
- W2762238293 hasConceptScore W2762238293C41895202 @default.
- W2762238293 hasLocation W27622382931 @default.
- W2762238293 hasOpenAccess W2762238293 @default.
- W2762238293 hasPrimaryLocation W27622382931 @default.
- W2762238293 hasRelatedWork W2008468404 @default.
- W2762238293 hasRelatedWork W2120010607 @default.
- W2762238293 hasRelatedWork W2124470186 @default.
- W2762238293 hasRelatedWork W2143620265 @default.
- W2762238293 hasRelatedWork W2217717732 @default.
- W2762238293 hasRelatedWork W2374918184 @default.
- W2762238293 hasRelatedWork W2917344756 @default.
- W2762238293 hasRelatedWork W3011988934 @default.
- W2762238293 hasRelatedWork W4205868073 @default.
- W2762238293 hasRelatedWork W80839609 @default.
- W2762238293 isParatext "false" @default.
- W2762238293 isRetracted "false" @default.
- W2762238293 magId "2762238293" @default.
- W2762238293 workType "dissertation" @default.