MaltParser: A language-independent system for data-driven dependency parsing

Parsing unrestricted text is useful for many language technology applications but requires parsing methods that are both robust and efficient. MaltParser is a language-independent system for data-driven dependency parsing that can be used to induce a parser for a new language from a treebank sample...

Celý popis

Uložené v:

Podrobná bibliografia
Vydané v:	Natural language engineering Ročník 13; číslo 2; s. 95 - 135
Hlavní autori:	NIVRE, JOAKIM, HALL, JOHAN, NILSSON, JENS, CHANEV, ATANAS, ERYİGİT, GÜLŞEN, KÜBLER, SANDRA, MARINOV, SVETOSLAV, MARSI, ERWIN
Médium:	Journal Article
Jazyk:	English
Vydavateľské údaje:	Cambridge, UK Cambridge University Press 01.06.2007
Predmet:	Accuracy Algorithms Chinese Computational linguistics Computer Applications Computer Generated Language Analysis Computerized corpora Data Datorlingvistik Dependency Dependency Grammar Germanic Languages HUMANIORA och RELIGIONSVETENSKAP HUMANITIES and RELIGION Italian Language Languages Languages and linguistics Linguistic subjects Lingvistikämnen Machine learning Natural language Natural Language Processing Parsing Slavic Languages Språkvetenskap Systems engineering Tree Structures Turkish Istanbul Turkey Sweden Turkey
ISSN:	1351-3249, 1469-8110
On-line prístup:	Získať plný text
Tagy:	Pridať tag Žiadne tagy, Buďte prvý, kto otaguje tento záznam!

Popis
Shrnutí:	Parsing unrestricted text is useful for many language technology applications but requires parsing methods that are both robust and efficient. MaltParser is a language-independent system for data-driven dependency parsing that can be used to induce a parser for a new language from a treebank sample in a simple yet flexible manner. Experimental evaluation confirms that MaltParser can achieve robust, efficient and accurate parsing for a wide range of languages without language-specific enhancements and with rather limited amounts of training data.
Bibliografia:	PII:S1351324906004505 istex:CA3B13BF2B77BAEBD35B3054BE2E183309D33402 ark:/67375/6GQ-9F3DB52K-Q ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 content type line 23
ISSN:	1351-3249 1469-8110
DOI:	10.1017/S1351324906004505