PNNL: A supervised maximum entropy approach to Word Sense Disambiguation

Stephen Tratz; Antonio Sanfilippo; Michelle Gregory; Alan Chappell; Christian Posse; Paul Whitney

PNNL: A supervised maximum entropy approach to Word Sense Disambiguation

Stephen Tratz, Antonio Sanfilippo, Michelle Gregory, Alan Chappell, Christian Posse, Paul Whitney

Research output: Contribution to conference › Paper › peer-review

Abstract

In this paper, we described the PNNL Word Sense Disambiguation system as applied to the English all-word task in SemEval 2007. We use a supervised learning approach, employing a large number of features and using Information Gain for dimension reduction. The rich feature set combined with a Maximum Entropy classifier produces results that are significantly better than baseline and are the highest Fscore for the fined-grained English allwords subtask of SemEval.

Original language	English
Pages	264-267
Number of pages	4
State	Published - 2007
Externally published	Yes
Event	4th International Workshop on Semantic Evaluations, SemEval 2007 - Prague, Czech Republic Duration: Jun 23 2007 → Jun 24 2007

Conference

Conference	4th International Workshop on Semantic Evaluations, SemEval 2007
Country/Territory	Czech Republic
City	Prague
Period	06/23/07 → 06/24/07

Cite this

@conference{8a072d4bd34f468aa62ff80023abd3bc,

title = "PNNL: A supervised maximum entropy approach to Word Sense Disambiguation",

abstract = "In this paper, we described the PNNL Word Sense Disambiguation system as applied to the English all-word task in SemEval 2007. We use a supervised learning approach, employing a large number of features and using Information Gain for dimension reduction. The rich feature set combined with a Maximum Entropy classifier produces results that are significantly better than baseline and are the highest Fscore for the fined-grained English allwords subtask of SemEval.",

author = "Stephen Tratz and Antonio Sanfilippo and Michelle Gregory and Alan Chappell and Christian Posse and Paul Whitney",

note = "Publisher Copyright: {\textcopyright} 2007 Association for Computational Linguistics.; 4th International Workshop on Semantic Evaluations, SemEval 2007 ; Conference date: 23-06-2007 Through 24-06-2007",

year = "2007",

language = "Ingl{\'e}s",

pages = "264--267",

}

TY - CONF

T1 - PNNL

T2 - 4th International Workshop on Semantic Evaluations, SemEval 2007

AU - Tratz, Stephen

AU - Sanfilippo, Antonio

AU - Gregory, Michelle

AU - Chappell, Alan

AU - Posse, Christian

AU - Whitney, Paul

PY - 2007

Y1 - 2007

N2 - In this paper, we described the PNNL Word Sense Disambiguation system as applied to the English all-word task in SemEval 2007. We use a supervised learning approach, employing a large number of features and using Information Gain for dimension reduction. The rich feature set combined with a Maximum Entropy classifier produces results that are significantly better than baseline and are the highest Fscore for the fined-grained English allwords subtask of SemEval.

AB - In this paper, we described the PNNL Word Sense Disambiguation system as applied to the English all-word task in SemEval 2007. We use a supervised learning approach, employing a large number of features and using Information Gain for dimension reduction. The rich feature set combined with a Maximum Entropy classifier produces results that are significantly better than baseline and are the highest Fscore for the fined-grained English allwords subtask of SemEval.

UR - http://www.scopus.com/inward/record.url?scp=85036476413&partnerID=8YFLogxK

M3 - Artículo

AN - SCOPUS:85036476413

SP - 264

EP - 267

Y2 - 23 June 2007 through 24 June 2007

ER -

PNNL: A supervised maximum entropy approach to Word Sense Disambiguation

Abstract

Conference

Other files and links

Fingerprint

Cite this