Matches in SemOpenAlex for { <https://semopenalex.org/work/W43096115> ?p ?o ?g. }
Showing items 1 to 54 of
54
with 100 items per page.
- W43096115 abstract "The Structured Language Model (SLM) recently introduced by Chelba and Jelinek is a powerful general formalism for exploiting syntactic dependencies in a left-to-right language model for applications such as speech and handwriting recognition, spelling correction, machine translation, etc. Unlik e traditional N-gram models, optimal smoothing techniques ‐ discounting methods and hierarchical structures for back-off ‐ are still being de veloped for the SLM. In the SLM, the statistical dependencies of a word on immediately preceding words, preceding syntactic heads, non-terminal labels, etc., are parameterized as o verlapping N-gram dependencies. Statistical dependencies in the parser and tagger used by the SLM also have N-gram like structure. Deleted interpolation has been used to combine these N-gram lik e models. We demonstrate on two different corpora ‐ WSJ and Switchboard ‐ that more recent modified back-off strategies and nonlinear interpolation methods considerably lower the perplexity of the SLM. Improvement in word error rate is also demonstrated on the Switchboard corpus." @default.
- W43096115 created "2016-06-24" @default.
- W43096115 creator A5010122901 @default.
- W43096115 creator A5041308812 @default.
- W43096115 creator A5072718837 @default.
- W43096115 date "2001-09-03" @default.
- W43096115 modified "2023-10-06" @default.
- W43096115 title "Smoothing issues in the structured language model" @default.
- W43096115 cites W1497026191 @default.
- W43096115 cites W1632114991 @default.
- W43096115 cites W1934041838 @default.
- W43096115 cites W1989705153 @default.
- W43096115 cites W2110882317 @default.
- W43096115 cites W2114858359 @default.
- W43096115 cites W2158195707 @default.
- W43096115 cites W2166637769 @default.
- W43096115 cites W2343954916 @default.
- W43096115 doi "https://doi.org/10.21437/eurospeech.2001-216" @default.
- W43096115 hasPublicationYear "2001" @default.
- W43096115 type Work @default.
- W43096115 sameAs 43096115 @default.
- W43096115 citedByCount "6" @default.
- W43096115 countsByYear W430961152015 @default.
- W43096115 crossrefType "proceedings-article" @default.
- W43096115 hasAuthorship W43096115A5010122901 @default.
- W43096115 hasAuthorship W43096115A5041308812 @default.
- W43096115 hasAuthorship W43096115A5072718837 @default.
- W43096115 hasConcept C137293760 @default.
- W43096115 hasConcept C204321447 @default.
- W43096115 hasConcept C31972630 @default.
- W43096115 hasConcept C3770464 @default.
- W43096115 hasConcept C41008148 @default.
- W43096115 hasConceptScore W43096115C137293760 @default.
- W43096115 hasConceptScore W43096115C204321447 @default.
- W43096115 hasConceptScore W43096115C31972630 @default.
- W43096115 hasConceptScore W43096115C3770464 @default.
- W43096115 hasConceptScore W43096115C41008148 @default.
- W43096115 hasLocation W430961151 @default.
- W43096115 hasOpenAccess W43096115 @default.
- W43096115 hasPrimaryLocation W430961151 @default.
- W43096115 hasRelatedWork W1972594981 @default.
- W43096115 hasRelatedWork W1989705153 @default.
- W43096115 hasRelatedWork W2136542423 @default.
- W43096115 hasRelatedWork W2293457016 @default.
- W43096115 hasRelatedWork W2351428524 @default.
- W43096115 hasRelatedWork W2359001871 @default.
- W43096115 hasRelatedWork W2496228846 @default.
- W43096115 hasRelatedWork W2789919619 @default.
- W43096115 hasRelatedWork W2896411932 @default.
- W43096115 hasRelatedWork W3169305685 @default.
- W43096115 isParatext "false" @default.
- W43096115 isRetracted "false" @default.
- W43096115 magId "43096115" @default.
- W43096115 workType "article" @default.