Volltext-Downloads (blau) und Frontdoor-Views (grau)

Convolution Kernels for Subjectivity Detection

  • In this paper, we explore different linguistic structures encoded as convolution kernels for the detection of subjective expressions. The advantage of convolution kernels is that complex structures can be directly provided to a classifier without deriving explicit features. The feature design for the detection of subjective expressions is fairly difficult and there currently exists no commonly accepted feature set. We consider various structures, such as constituency parse structures, dependency parse structures, and predicate-argument structures. In order to generalize from lexical information, we additionally augment these structures with clustering information and the task-specific knowledge of subjective words. The convolution kernels will be compared with a standard vector kernel.

Export metadata

Additional Services

Search Google Scholar

Statistics

frontdoor_oas
Metadaten
Author:Michael WiegandGND, Dietrich Klakow
URN:urn:nbn:de:bsz:mh39-85032
Handle:http://hdl.handle.net/10062/17338
ISSN:1736-6305
Parent Title (English):Proceedings of the 18th Nordic Conference of Computational Linguistics (NODALIDA 2011), May 11-13, 2011, Riga, Latvia
Series (Serial Number):NEALT Proceedings Series (11)
Publisher:Northern European Association for Language Technology
Place of publication:Uppsala
Editor:Bolette Sandford Pedersen, Gunta Nešpore, Inguna Skadiņa
Document Type:Conference Proceeding
Language:English
Year of first Publication:2011
Date of Publication (online):2019/02/21
Publicationstate:Veröffentlichungsversion
Reviewstate:Peer-Review
Tag:Sentimentanalyse
GND Keyword:Computerlinguistik; Maschinelles Lernen; Natürliche Sprache; Subjektivität; Text Mining
First Page:254
Last Page:261
DDC classes:400 Sprache / 400 Sprache, Linguistik
Open Access?:ja
Linguistics-Classification:Computerlinguistik
Licence (German):License LogoUrheberrechtlich geschützt