naar inhoud
A resource-light approach to morpho-syntactic tagging Voorbeeld van dit item
SluitenVoorbeeld van dit item
Bezig met controle...

A resource-light approach to morpho-syntactic tagging

Auteur: Anna Feldman; Jirka Hana
Uitgever: Amsterdam ; New York, NY : Rodopi, 2010.
Reeks: Language and computers, no. 70.
Editie/materiaalsoort:   eBoek : Document : EngelsAlle edities en materiaalsoorten bekijken.
Samenvatting:
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  Meer lezen...
Beoordeling:

(nog niet beoordeeld) 0 met beoordelingen - U bent de eerste

Onderwerpen
Meer in deze trant

Zoeken naar een online exemplaar

Links naar dit item

Zoeken een exemplaar in de bibliotheek

&AllPage.SpinnerRetrieving; Zoekt bibliotheken met dit item…

Gegevens

Genre/vorm: Electronic books
Aanvullende fysieke materiaalsoort: Print version:
Feldman, Anna.
Resource-light approach to morpho-syntactic tagging.
Amsterdam : Rodopi, 2010
(OCoLC)497573700
Materiaalsoort: Document, Internetbron
Soort document: Internetbron, Computerbestand
Alle auteurs / bijdragers: Anna Feldman; Jirka Hana
ISBN: 9789042027695 904202769X 9042027681 9789042027688
OCLC-nummer: 608352102
Beschrijving: 1 online resource (xiv, 185 pages) : illustrations.
Inhoud: 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.
Titel reeks: Language and computers, no. 70.
Verantwoordelijkheid: Anna Feldman and Jirka Hana.

Samenvatting:

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.

Beoordelingen

Professionele beoordelingen

Synopsis uitgever

"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 Meer lezen...

 
Beoordelingen door gebruikers
Beoordelingen van GoodReads worden opgehaald...
Bezig met opvragen DOGObooks-reviews...

Tags

Alle gebruiker-tags (7)

De meest populaire tags bekijken als: Tag-lijst | Tag-wolk

Bevestig deze aanvraag

Misschien heeft u dit item al aangevraagd. Selecteer OK als u toch wilt doorgaan met deze aanvraag.

Venster sluiten

Meld u aan bij WorldCat 

Heeft u geen account? U kunt eenvoudig een nieuwe gratis account aanmaken.