passa ai contenuti
Grammatical trigrams : a probabilistic model of link grammar Anteprima di questo documento
ChiudiAnteprima di questo documento
Stiamo controllando…

Grammatical trigrams : a probabilistic model of link grammar

Autore: John D Lafferty; Daniel D Sleator; Davy Temperley
Editore: Pittsburgh, Pa. : School of Computer Science, Carnegie Mellon University, [1992]
Serie: Research paper (Carnegie Mellon University. School of Computer Science), CMU-CS-92-181.
Edizione/Formato:   Libro : EnglishVedi tutte le edizioni e i formati
Banca dati:WorldCat
Sommario:
Abstract: "In this paper we present a new class of language models. This class derives from link grammar, a context-free formalism for the description of natural language. We describe an algorithm for determining maximum-likelihood estimates of the parameters of these models. The language models which we present differ from previous models based on stochastic context-free grammars in that they are highly lexical. In  Per saperne di più…
Voto:

(non ancora votato) 0 con commenti - Diventa il primo.

Soggetti
Altri come questo

 

Trova una copia in biblioteca

&AllPage.SpinnerRetrieving; Stiamo ricercando le biblioteche che possiedono questo documento…

Dettagli

Tipo documento: Book
Tutti gli autori / Collaboratori: John D Lafferty; Daniel D Sleator; Davy Temperley
Numero OCLC: 26847322
Note: "To appear in Proc. of the 1992 AAAI Fall Symp. on Probabilistic Approaches to Natural Language."
"September 1992."
Descrizione: 10 p. ; 28 cm.
Titolo della serie: Research paper (Carnegie Mellon University. School of Computer Science), CMU-CS-92-181.
Responsabilità: John Lafferty, Daniel Sleator, Davy Temperley.

Abstract:

Abstract: "In this paper we present a new class of language models. This class derives from link grammar, a context-free formalism for the description of natural language. We describe an algorithm for determining maximum-likelihood estimates of the parameters of these models. The language models which we present differ from previous models based on stochastic context-free grammars in that they are highly lexical. In particular, they include the familiar n-gram models as a natural subclass. The motivation for considering this class is to estimate the contribution which grammar can make to reducing the relative entropy of natural language."

Commenti

Commenti degli utenti
Recuperando commenti GoodReads…
Stiamo recuperando commenti DOGObooks

Etichette

Diventa il primo.

Documenti simili

Conferma questa richiesta

Potresti aver già richiesto questo documento. Seleziona OK se si vuole procedere comunque con questa richiesta.

Dati collegati


<http://www.worldcat.org/oclc/26847322>
library:oclcnum"26847322"
library:placeOfPublication
library:placeOfPublication
owl:sameAs<info:oclcnum/26847322>
rdf:typeschema:Book
schema:about
schema:about
schema:about
<http://id.worldcat.org/fast/1034365>
rdf:typeschema:Intangible
schema:name"Natural language processing (Computer science)"
schema:contributor
schema:contributor
schema:creator
schema:datePublished"1992"
schema:description"Abstract: "In this paper we present a new class of language models. This class derives from link grammar, a context-free formalism for the description of natural language. We describe an algorithm for determining maximum-likelihood estimates of the parameters of these models. The language models which we present differ from previous models based on stochastic context-free grammars in that they are highly lexical. In particular, they include the familiar n-gram models as a natural subclass. The motivation for considering this class is to estimate the contribution which grammar can make to reducing the relative entropy of natural language.""
schema:exampleOfWork<http://worldcat.org/entity/work/id/29987363>
schema:inLanguage"en"
schema:name"Grammatical trigrams : a probabilistic model of link grammar"
schema:numberOfPages"10"
schema:publisher
schema:url

Content-negotiable representations

Chiudi finestra

Per favore entra in WorldCat 

Non hai un account? Puoi facilmente crearne uno gratuito.