Katz back-off is a generative n-gram language model that estimates the conditional probability of a word given its history in the n-gram. It accomplishes this estimation by "backing-off" to models with smaller histories under certain conditions. By doing so, the model with the most reliable information about a given history is used to provide the better results.

Property Value
dbo:abstract
  • Katz back-off is a generative n-gram language model that estimates the conditional probability of a word given its history in the n-gram. It accomplishes this estimation by "backing-off" to models with smaller histories under certain conditions. By doing so, the model with the most reliable information about a given history is used to provide the better results. (en)
dbo:wikiPageID
  • 13911197 (xsd:integer)
dbo:wikiPageRevisionID
  • 689075905 (xsd:integer)
dct:subject
http://purl.org/linguistics/gold/hypernym
rdf:type
rdfs:comment
  • Katz back-off is a generative n-gram language model that estimates the conditional probability of a word given its history in the n-gram. It accomplishes this estimation by "backing-off" to models with smaller histories under certain conditions. By doing so, the model with the most reliable information about a given history is used to provide the better results. (en)
rdfs:label
  • Katz's back-off model (en)
owl:sameAs
prov:wasDerivedFrom
foaf:isPrimaryTopicOf
is dbo:wikiPageRedirects of
is foaf:primaryTopic of