Constructing Semantic Space Models from Parsed Corpora

Sebastian Padó; Mirella Lapata

Constructing Semantic Space Models from Parsed Corpora

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

Traditional vector-based models use word co-occurrence counts from large corpora to represent lexical meaning. In this paper we present a novel approach for constructing semantic spaces that takes syntactic relations into account. We introduce a formalisation for this class of models and evaluate their adequacy on two modelling tasks: semantic priming and automatic discrimination of lexical relations.

Original language	English
Title of host publication	Proceedings of the 41st Annual Meeting of the Association for Computational Linguistics
Publisher	Association for Computational Linguistics
Pages	126-135
Number of pages	8
Publication status	Published - 2003
Event	41st Annual Meeting of the Association for Computational Linguistics - Sapporo Convention Centre, Sapporo, Japan Duration: 7 Jul 2003 → 12 Jul 2003

Conference

Conference	41st Annual Meeting of the Association for Computational Linguistics
Country/Territory	Japan
City	Sapporo
Period	7/07/03 → 12/07/03

Access to Document

P03-1017Final published version, 98.4 KB

http://aclweb.org/anthology/P03-1017

Cite this

@inproceedings{212a00efbe3a4fe590a9de74808a76cf,

title = "Constructing Semantic Space Models from Parsed Corpora",

abstract = "Traditional vector-based models use word co-occurrence counts from large corpora to represent lexical meaning. In this paper we present a novel approach for constructing semantic spaces that takes syntactic relations into account. We introduce a formalisation for this class of models and evaluate their adequacy on two modelling tasks: semantic priming and automatic discrimination of lexical relations.",

author = "Sebastian Pad{\'o} and Mirella Lapata",

year = "2003",

language = "English",

pages = "126--135",

booktitle = "Proceedings of the 41st Annual Meeting of the Association for Computational Linguistics",

publisher = "Association for Computational Linguistics",

note = " 41st Annual Meeting of the Association for Computational Linguistics ; Conference date: 07-07-2003 Through 12-07-2003",

}

TY - GEN

T1 - Constructing Semantic Space Models from Parsed Corpora

AU - Padó, Sebastian

AU - Lapata, Mirella

PY - 2003

Y1 - 2003

N2 - Traditional vector-based models use word co-occurrence counts from large corpora to represent lexical meaning. In this paper we present a novel approach for constructing semantic spaces that takes syntactic relations into account. We introduce a formalisation for this class of models and evaluate their adequacy on two modelling tasks: semantic priming and automatic discrimination of lexical relations.

AB - Traditional vector-based models use word co-occurrence counts from large corpora to represent lexical meaning. In this paper we present a novel approach for constructing semantic spaces that takes syntactic relations into account. We introduce a formalisation for this class of models and evaluate their adequacy on two modelling tasks: semantic priming and automatic discrimination of lexical relations.

M3 - Conference contribution

SP - 126

EP - 135

BT - Proceedings of the 41st Annual Meeting of the Association for Computational Linguistics

PB - Association for Computational Linguistics

T2 - 41st Annual Meeting of the Association for Computational Linguistics

Y2 - 7 July 2003 through 12 July 2003

ER -

Constructing Semantic Space Models from Parsed Corpora

Abstract

Conference

Access to Document

Fingerprint

Cite this