FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2014845239> ?p ?o ?g. }

• W2014845239 abstract "The recurrent neural network language model (RNNLM) is a discriminative, non-Markovian model that can capture long-span word history in natural language. It has been proved to be successful in automatic speech recognition and machine translation. In this work, we applied RNNLM to the n-best rescoring stage of the state-of-the-art BBN Byblos OCR (optical character recognition) system for handwriting recognition.1 With RNNLM scores as additional features, our system achieved significant improvement (p <; 0.001), a 3.5% relative reduction on OCR word error rate, compared with a high baseline that uses n-gram language model for rescoring. We have also developed a novel method to integrate the OCR n-best RNNLM scores into the word posterior probabilities in OCR confusion networks, which resulted in consistent observable improvements in word spotting for OCR'ed handwritten documents, as measured by both mean average precision (MAP) and detection-error tradeoff (DET) curves." @default.
• W2014845239 created "2016-06-24" @default.
• W2014845239 creator A5015105154 @default.
• W2014845239 creator A5037095141 @default.
• W2014845239 creator A5045473616 @default.
• W2014845239 creator A5059948202 @default.
• W2014845239 creator A5066184920 @default.
• W2014845239 date "2014-09-01" @default.
• W2014845239 modified "2023-10-12" @default.
• W2014845239 title "Applications of Recurrent Neural Network Language Model in Offline Handwriting Recognition and Word Spotting" @default.
• W2014845239 cites W1586405805 @default.
• W2014845239 cites W159523117 @default.
• W2014845239 cites W179875071 @default.
• W2014845239 cites W1969203589 @default.
• W2014845239 cites W1995889372 @default.
• W2014845239 cites W2008973672 @default.
• W2014845239 cites W2009389931 @default.
• W2014845239 cites W2028252982 @default.
• W2014845239 cites W2053406980 @default.
• W2014845239 cites W2058695628 @default.
• W2014845239 cites W2072350286 @default.
• W2014845239 cites W2078549297 @default.
• W2014845239 cites W2081393665 @default.
• W2014845239 cites W2098355803 @default.
• W2014845239 cites W2110415041 @default.
• W2014845239 cites W2111417594 @default.
• W2014845239 cites W2116930768 @default.
• W2014845239 cites W2122585011 @default.
• W2014845239 cites W2139922515 @default.
• W2014845239 cites W2144533356 @default.
• W2014845239 cites W2146871184 @default.
• W2014845239 cites W2153817962 @default.
• W2014845239 cites W2156301828 @default.
• W2014845239 cites W2161199684 @default.
• W2014845239 cites W2171928131 @default.
• W2014845239 cites W2293185259 @default.
• W2014845239 cites W2594610113 @default.
• W2014845239 cites W4254816979 @default.
• W2014845239 doi "https://doi.org/10.1109/icfhr.2014.30" @default.
• W2014845239 hasPublicationYear "2014" @default.
• W2014845239 type Work @default.
• W2014845239 sameAs 2014845239 @default.
• W2014845239 citedByCount "7" @default.
• W2014845239 countsByYear W20148452392014 @default.
• W2014845239 countsByYear W20148452392017 @default.
• W2014845239 countsByYear W20148452392018 @default.
• W2014845239 countsByYear W20148452392021 @default.
• W2014845239 countsByYear W20148452392023 @default.
• W2014845239 crossrefType "proceedings-article" @default.
• W2014845239 hasAuthorship W2014845239A5015105154 @default.
• W2014845239 hasAuthorship W2014845239A5037095141 @default.
• W2014845239 hasAuthorship W2014845239A5045473616 @default.
• W2014845239 hasAuthorship W2014845239A5059948202 @default.
• W2014845239 hasAuthorship W2014845239A5066184920 @default.
• W2014845239 hasConcept C115961682 @default.
• W2014845239 hasConcept C137293760 @default.
• W2014845239 hasConcept C138885662 @default.
• W2014845239 hasConcept C147168706 @default.
• W2014845239 hasConcept C150856459 @default.
• W2014845239 hasConcept C153180895 @default.
• W2014845239 hasConcept C154945302 @default.
• W2014845239 hasConcept C17744445 @default.
• W2014845239 hasConcept C199539241 @default.
• W2014845239 hasConcept C204321447 @default.
• W2014845239 hasConcept C23224414 @default.
• W2014845239 hasConcept C2779506182 @default.
• W2014845239 hasConcept C28490314 @default.
• W2014845239 hasConcept C40969351 @default.
• W2014845239 hasConcept C41008148 @default.
• W2014845239 hasConcept C41895202 @default.
• W2014845239 hasConcept C50644808 @default.
• W2014845239 hasConcept C546480517 @default.
• W2014845239 hasConcept C554936623 @default.
• W2014845239 hasConcept C90805587 @default.
• W2014845239 hasConcept C97931131 @default.
• W2014845239 hasConceptScore W2014845239C115961682 @default.
• W2014845239 hasConceptScore W2014845239C137293760 @default.
• W2014845239 hasConceptScore W2014845239C138885662 @default.
• W2014845239 hasConceptScore W2014845239C147168706 @default.
• W2014845239 hasConceptScore W2014845239C150856459 @default.
• W2014845239 hasConceptScore W2014845239C153180895 @default.
• W2014845239 hasConceptScore W2014845239C154945302 @default.
• W2014845239 hasConceptScore W2014845239C17744445 @default.
• W2014845239 hasConceptScore W2014845239C199539241 @default.
• W2014845239 hasConceptScore W2014845239C204321447 @default.
• W2014845239 hasConceptScore W2014845239C23224414 @default.
• W2014845239 hasConceptScore W2014845239C2779506182 @default.
• W2014845239 hasConceptScore W2014845239C28490314 @default.
• W2014845239 hasConceptScore W2014845239C40969351 @default.
• W2014845239 hasConceptScore W2014845239C41008148 @default.
• W2014845239 hasConceptScore W2014845239C41895202 @default.
• W2014845239 hasConceptScore W2014845239C50644808 @default.
• W2014845239 hasConceptScore W2014845239C546480517 @default.
• W2014845239 hasConceptScore W2014845239C554936623 @default.
• W2014845239 hasConceptScore W2014845239C90805587 @default.
• W2014845239 hasConceptScore W2014845239C97931131 @default.
• W2014845239 hasLocation W20148452391 @default.
• W2014845239 hasOpenAccess W2014845239 @default.
• W2014845239 hasPrimaryLocation W20148452391 @default.
• W2014845239 hasRelatedWork W1570102481 @default.

• next