Header

UZH-Logo

Maintenance Infos

Fast, deep-linguistic statistical minimalist dependency parsing


Schneider, G; Rinaldi, Fabio; Dowdall, J (2004). Fast, deep-linguistic statistical minimalist dependency parsing. In: COLING-2004 Recent Advances in Dependency Grammars, Geneva, Switzerland, 2004 - 2004, 33-40.

Abstract

We present and evaluate an implemented statistical minimal parsing strategy exploiting DG charateristics to permit fast, robust, deeplinguistic analysis of unrestricted text, and compare its probability model to (Collins, 1999) and an adaptation, (Dubey and Keller, 2003). We show that DG allows for the expression of the majority of English LDDs in a context-free way and offers simple yet powerful statistical models.

Abstract

We present and evaluate an implemented statistical minimal parsing strategy exploiting DG charateristics to permit fast, robust, deeplinguistic analysis of unrestricted text, and compare its probability model to (Collins, 1999) and an adaptation, (Dubey and Keller, 2003). We show that DG allows for the expression of the majority of English LDDs in a context-free way and offers simple yet powerful statistical models.

Statistics

Additional indexing

Item Type:Conference or Workshop Item (Paper), refereed, original work
Communities & Collections:06 Faculty of Arts > Institute of Computational Linguistics
Dewey Decimal Classification:410 Linguistics
000 Computer science, knowledge & systems
Language:English
Event End Date:2004
Deposited On:06 Aug 2009 12:22
Last Modified:06 Jun 2017 10:54

Download

Full text not available from this repository.

TrendTerms

TrendTerms displays relevant terms of the abstract of this publication and related documents on a map. The terms and their relations were extracted from ZORA using word statistics. Their timelines are taken from ZORA as well. The bubble size of a term is proportional to the number of documents where the term occurs. Red, orange, yellow and green colors are used for terms that occur in the current document; red indicates high interlinkedness of a term with other terms, orange, yellow and green decreasing interlinkedness. Blue is used for terms that have a relation with the terms in this document, but occur in other documents.
You can navigate and zoom the map. Mouse-hovering a term displays its timeline, clicking it yields the associated documents.

Author Collaborations