aller au contenu
A resource-light approach to morpho-syntactic tagging Aperçu de cet ouvrage
FermerAperçu de cet ouvrage
Vérification...

A resource-light approach to morpho-syntactic tagging

Auteur : Anna Feldman; Jirka Hana
Éditeur: Amsterdam ; New York, NY : Rodopi, 2010.
Collection: Language and computers, no. 70.
Édition/format:   Livre électronique : Document : AnglaisVoir toutes les éditions et tous les formats
Résumé:
While supervised corpus-based methods are highly accurate for different NLP tasks, including morphological tagging, they are difficult to port to other languages because they require resources that are expensive to create. As a result, many languages have no realistic prospect for morpho-syntactic annotation in the foreseeable future. The method presented in this book aims to overcome this problem by significantly  Lire la suite...
Évaluation:

(pas encore évalué) 0 avec des critiques - Soyez le premier.

Sujets
Plus comme ceci

Trouver un exemplaire en ligne

Liens vers cet ouvrage

Trouver un exemplaire dans la bibliothèque

&AllPage.SpinnerRetrieving; Recherche de bibliothèques qui possèdent cet ouvrage...

Détails

Genre/forme: Electronic books
Format – détails additionnels: Print version:
Feldman, Anna.
Resource-light approach to morpho-syntactic tagging.
Amsterdam : Rodopi, 2010
(OCoLC)497573700
Type d’ouvrage: Document, Ressource Internet
Type de document: Ressource Internet, Fichier d'ordinateur
Tous les auteurs / collaborateurs: Anna Feldman; Jirka Hana
ISBN: 9789042027695 904202769X 9042027681 9789042027688
Numéro OCLC: 608352102
Description: 1 online resource (xiv, 185 pages) : illustrations.
Contenu: Preliminary Material --
Introduction --
Common tagging techniques --
Previous resource-light approaches to NLP --
Languages, corpora and tagsets --
Quantifying language properties --
Resource-light morphological analysis --
Cross-language morphological tagging --
Summary and further work --
Bibliography --
Tagsets we use --
Corpora --
Language properties --
Citation Index.
Titre de collection: Language and computers, no. 70.
Responsabilité: Anna Feldman and Jirka Hana.

Résumé:

While supervised corpus-based methods are highly accurate for different NLP tasks, including morphological tagging, they are difficult to port to other languages because they require resources that are expensive to create. As a result, many languages have no realistic prospect for morpho-syntactic annotation in the foreseeable future. The method presented in this book aims to overcome this problem by significantly limiting the necessary data and instead extrapolating the relevant information from another, related language. The approach has been tested on Catalan, Portuguese, and Russian. Although these languages are only relatively resource-poor, the same method can be in principle applied to any inflected language, as long as there is an annotated corpus of a related language available. Time needed for adjusting the system to a new language constitutes a fraction of the time needed for systems with extensive, manually created resources: days instead of years. This book touches upon a number of topics: typology, morphology, corpus linguistics, contrastive linguistics, linguistic annotation, computational linguistics and Natural Language Processing (NLP). Researchers and students who are interested in these scientific areas as well as in cross-lingual studies and applications will greatly benefit from this work. Scholars and practitioners in computer science and linguistics are the prospective readers of this book.

Critiques

Critiques éditoriales

Synopsis de l’éditeur

"F[eldman] & H[ana] have opened a very interesting door, showing us a method with many potential applications to less resourced languages. I suspect there are many other methods behind that door that Lire la suite...

 
Critiques d’utilisateurs
Récupération des critiques de GoodReads...
Récuperation des critiques DOGObooks…

Marqueurs

Tous les marqueurs des utilisateurs (7)

Voir les marqueurs les plus utilisés sous forme de: liste de marqueurs | nuage de marqueurs

Confirmez cette demande

Vous avez peut-être déjà demandé cet ouvrage. Veuillez sélectionner OK si vous voulez poursuivre avec cette demande quand même.

Fermer la fenêtre

Veuillez vous identifier dans WorldCat 

Vous n’avez pas de compte? Vous pouvez facilement créer un compte gratuit.