splitSVM: Fast, space-efficient, non-heuristic, polynomial kernel computation for NLP applications

Yoav Goldberg; Michael Elhadad

splitSVM: Fast, space-efficient, non-heuristic, polynomial kernel computation for NLP applications

Yoav Goldberg, Michael Elhadad

Department of Computer Science

Research output: Contribution to journal › Conference article › peer-review

2 Scopus citations

Abstract

We present a fast, space efficient and non-heuristic method for calculating the decision function of polynomial kernel classifiers for NLP applications. We apply the method to the MaltParser system, resulting in a Java parser that parses over 50 sentences per second on modest hardware without loss of accuracy (a 30 time speedup over existing methods). The method implementation is available as the open-source splitSVM Java library.

Original language	English
Pages (from-to)	237-240
Number of pages	4
Journal	Proceedings of the Annual Meeting of the Association for Computational Linguistics
State	Published - 1 Jan 2008
Event	46th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, ACL 2008 - Columbus, United States Duration: 16 Jun 2008 → 17 Jun 2008

ASJC Scopus subject areas

Computer Science Applications
Linguistics and Language
Language and Linguistics

Cite this

@article{70dd4fa95771488eb49177caf5ac104f,

title = "splitSVM: Fast, space-efficient, non-heuristic, polynomial kernel computation for NLP applications",

abstract = "We present a fast, space efficient and non-heuristic method for calculating the decision function of polynomial kernel classifiers for NLP applications. We apply the method to the MaltParser system, resulting in a Java parser that parses over 50 sentences per second on modest hardware without loss of accuracy (a 30 time speedup over existing methods). The method implementation is available as the open-source splitSVM Java library.",

author = "Yoav Goldberg and Michael Elhadad",

note = "Publisher Copyright: {\textcopyright} 2008 Association for Computational Linguistics.; 46th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, ACL 2008 ; Conference date: 16-06-2008 Through 17-06-2008",

year = "2008",

month = jan,

day = "1",

language = "English",

pages = "237--240",

journal = "Proceedings of the Annual Meeting of the Association for Computational Linguistics",

issn = "0736-587X",

publisher = "Association for Computational Linguistics (ACL)",

}

TY - JOUR

T1 - splitSVM

T2 - 46th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, ACL 2008

AU - Goldberg, Yoav

AU - Elhadad, Michael

PY - 2008/1/1

Y1 - 2008/1/1

N2 - We present a fast, space efficient and non-heuristic method for calculating the decision function of polynomial kernel classifiers for NLP applications. We apply the method to the MaltParser system, resulting in a Java parser that parses over 50 sentences per second on modest hardware without loss of accuracy (a 30 time speedup over existing methods). The method implementation is available as the open-source splitSVM Java library.

AB - We present a fast, space efficient and non-heuristic method for calculating the decision function of polynomial kernel classifiers for NLP applications. We apply the method to the MaltParser system, resulting in a Java parser that parses over 50 sentences per second on modest hardware without loss of accuracy (a 30 time speedup over existing methods). The method implementation is available as the open-source splitSVM Java library.

UR - http://www.scopus.com/inward/record.url?scp=85048457779&partnerID=8YFLogxK

M3 - Conference article

AN - SCOPUS:85048457779

SN - 0736-587X

SP - 237

EP - 240

JO - Proceedings of the Annual Meeting of the Association for Computational Linguistics

JF - Proceedings of the Annual Meeting of the Association for Computational Linguistics

Y2 - 16 June 2008 through 17 June 2008

ER -

splitSVM: Fast, space-efficient, non-heuristic, polynomial kernel computation for NLP applications

Abstract

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this