Matches in SemOpenAlex for { <https://semopenalex.org/work/W2078008248> ?p ?o ?g. }
- W2078008248 endingPage "816" @default.
- W2078008248 startingPage "807" @default.
- W2078008248 abstract "Language modeling (LM), providing a principled mechanism to associate quantitative scores to sequences of words or tokens, has long been an interesting yet challenging problem in the field of speech and language processing. The n-gram model is still the predominant method, while a number of disparate LM methods, exploring either lexical co-occurrence or topic cues, have been developed to complement the n-gram model with some success. In this paper, we explore a novel language modeling framework built on top of the notion of relevance for speech recognition, where the relationship between a search history and the word being predicted is discovered through different granularities of semantic context for relevance modeling. Empirical experiments on a large vocabulary continuous speech recognition (LVCSR) task seem to demonstrate that the various language models deduced from our framework are very comparable to existing language models both in terms of perplexity and recognition error rate reductions." @default.
- W2078008248 created "2016-06-24" @default.
- W2078008248 creator A5053222355 @default.
- W2078008248 creator A5056367345 @default.
- W2078008248 date "2013-07-01" @default.
- W2078008248 modified "2023-10-17" @default.
- W2078008248 title "Leveraging relevance cues for language modeling in speech recognition" @default.
- W2078008248 cites W103963444 @default.
- W2078008248 cites W1644652583 @default.
- W2078008248 cites W1932968309 @default.
- W2078008248 cites W1966093341 @default.
- W2078008248 cites W1972594981 @default.
- W2078008248 cites W2001082470 @default.
- W2078008248 cites W2002890640 @default.
- W2078008248 cites W2020073413 @default.
- W2078008248 cites W2027942651 @default.
- W2078008248 cites W2046932483 @default.
- W2078008248 cites W2069712814 @default.
- W2078008248 cites W2072223048 @default.
- W2078008248 cites W2087743880 @default.
- W2078008248 cites W2095368471 @default.
- W2078008248 cites W2097927681 @default.
- W2078008248 cites W2100506586 @default.
- W2078008248 cites W2102439588 @default.
- W2078008248 cites W2104448323 @default.
- W2078008248 cites W2107326178 @default.
- W2078008248 cites W2117987986 @default.
- W2078008248 cites W2127836646 @default.
- W2078008248 cites W2134731454 @default.
- W2078008248 cites W2136103482 @default.
- W2078008248 cites W2136583886 @default.
- W2078008248 cites W2159382562 @default.
- W2078008248 cites W2161301211 @default.
- W2078008248 cites W2165932888 @default.
- W2078008248 cites W2482821414 @default.
- W2078008248 cites W3149335959 @default.
- W2078008248 cites W4206765718 @default.
- W2078008248 cites W4231856373 @default.
- W2078008248 cites W4246858749 @default.
- W2078008248 cites W2149200625 @default.
- W2078008248 cites W2162959225 @default.
- W2078008248 doi "https://doi.org/10.1016/j.ipm.2013.01.005" @default.
- W2078008248 hasPublicationYear "2013" @default.
- W2078008248 type Work @default.
- W2078008248 sameAs 2078008248 @default.
- W2078008248 citedByCount "15" @default.
- W2078008248 countsByYear W20780082482013 @default.
- W2078008248 countsByYear W20780082482014 @default.
- W2078008248 countsByYear W20780082482015 @default.
- W2078008248 countsByYear W20780082482017 @default.
- W2078008248 countsByYear W20780082482018 @default.
- W2078008248 countsByYear W20780082482020 @default.
- W2078008248 countsByYear W20780082482022 @default.
- W2078008248 countsByYear W20780082482023 @default.
- W2078008248 crossrefType "journal-article" @default.
- W2078008248 hasAuthorship W2078008248A5053222355 @default.
- W2078008248 hasAuthorship W2078008248A5056367345 @default.
- W2078008248 hasConcept C100279451 @default.
- W2078008248 hasConcept C104317684 @default.
- W2078008248 hasConcept C112313634 @default.
- W2078008248 hasConcept C127716648 @default.
- W2078008248 hasConcept C129353971 @default.
- W2078008248 hasConcept C137293760 @default.
- W2078008248 hasConcept C138885662 @default.
- W2078008248 hasConcept C151730666 @default.
- W2078008248 hasConcept C154945302 @default.
- W2078008248 hasConcept C158154518 @default.
- W2078008248 hasConcept C162324750 @default.
- W2078008248 hasConcept C17744445 @default.
- W2078008248 hasConcept C185592680 @default.
- W2078008248 hasConcept C187736073 @default.
- W2078008248 hasConcept C188082640 @default.
- W2078008248 hasConcept C195324797 @default.
- W2078008248 hasConcept C199539241 @default.
- W2078008248 hasConcept C202444582 @default.
- W2078008248 hasConcept C204321447 @default.
- W2078008248 hasConcept C2777601683 @default.
- W2078008248 hasConcept C2779343474 @default.
- W2078008248 hasConcept C2780451532 @default.
- W2078008248 hasConcept C28490314 @default.
- W2078008248 hasConcept C33923547 @default.
- W2078008248 hasConcept C39608478 @default.
- W2078008248 hasConcept C40969351 @default.
- W2078008248 hasConcept C41008148 @default.
- W2078008248 hasConcept C41895202 @default.
- W2078008248 hasConcept C55493867 @default.
- W2078008248 hasConcept C83479923 @default.
- W2078008248 hasConcept C86803240 @default.
- W2078008248 hasConcept C9652623 @default.
- W2078008248 hasConceptScore W2078008248C100279451 @default.
- W2078008248 hasConceptScore W2078008248C104317684 @default.
- W2078008248 hasConceptScore W2078008248C112313634 @default.
- W2078008248 hasConceptScore W2078008248C127716648 @default.
- W2078008248 hasConceptScore W2078008248C129353971 @default.
- W2078008248 hasConceptScore W2078008248C137293760 @default.
- W2078008248 hasConceptScore W2078008248C138885662 @default.
- W2078008248 hasConceptScore W2078008248C151730666 @default.
- W2078008248 hasConceptScore W2078008248C154945302 @default.