Evaluating Smoothing Algorithms against Plausibility Judgements

Maria Lapata; Frank Keller; Scott McDonald

Evaluating Smoothing Algorithms against Plausibility Judgements

Maria Lapata, Frank Keller, Scott McDonald

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

Abstract

Previous research has shown that the plausibility of an adjective-noun combination is correlated with its corpus co-occurrence frequency. In this paper, we estimate the co-occurrence frequencies of adjective-noun pairs that fail to occur in a 100 million word corpus using smoothing techniques and compare them to human plausibility ratings. Both class-based smoothing and distance-weighted averaging yield frequency estimates that are significant predictors of rated plausibility, which provides independent evidence for the
validity of these smoothing techniques.

Original language	English
Title of host publication	Proceedings of the 39th Annual Meeting of the Association for Computational Linguistics
Publisher	Association for Computational Linguistics
Pages	346-353
Number of pages	8
Publication status	Published - 2001
Event	39th Annual Meeting of the Association for Computational Linguistics - Toulouse, France Duration: 6 Jul 2011 → 11 Jul 2011

Conference

Conference	39th Annual Meeting of the Association for Computational Linguistics
Country/Territory	France
Period	6/07/11 → 11/07/11

Access to Document

P01-1046Final published version, 59.6 KB

http://aclweb.org/anthology/P01-1046

Cite this

@inproceedings{0bd5a8c1a1ec468c89045c0a58f27602,

title = "Evaluating Smoothing Algorithms against Plausibility Judgements",

abstract = "Previous research has shown that the plausibility of an adjective-noun combination is correlated with its corpus co-occurrence frequency. In this paper, we estimate the co-occurrence frequencies of adjective-noun pairs that fail to occur in a 100 million word corpus using smoothing techniques and compare them to human plausibility ratings. Both class-based smoothing and distance-weighted averaging yield frequency estimates that are significant predictors of rated plausibility, which provides independent evidence for thevalidity of these smoothing techniques.",

author = "Maria Lapata and Frank Keller and Scott McDonald",

year = "2001",

language = "English",

pages = "346--353",

booktitle = "Proceedings of the 39th Annual Meeting of the Association for Computational Linguistics",

publisher = "Association for Computational Linguistics",

note = "39th Annual Meeting of the Association for Computational Linguistics ; Conference date: 06-07-2011 Through 11-07-2011",

}

Lapata, M , Keller, F & McDonald, S 2001, Evaluating Smoothing Algorithms against Plausibility Judgements. in Proceedings of the 39th Annual Meeting of the Association for Computational Linguistics. Association for Computational Linguistics, pp. 346-353, 39th Annual Meeting of the Association for Computational Linguistics, France, 6/07/11. <http://aclweb.org/anthology/P01-1046>

TY - GEN

T1 - Evaluating Smoothing Algorithms against Plausibility Judgements

AU - Lapata, Maria

AU - Keller, Frank

AU - McDonald, Scott

PY - 2001

Y1 - 2001

N2 - Previous research has shown that the plausibility of an adjective-noun combination is correlated with its corpus co-occurrence frequency. In this paper, we estimate the co-occurrence frequencies of adjective-noun pairs that fail to occur in a 100 million word corpus using smoothing techniques and compare them to human plausibility ratings. Both class-based smoothing and distance-weighted averaging yield frequency estimates that are significant predictors of rated plausibility, which provides independent evidence for thevalidity of these smoothing techniques.

AB - Previous research has shown that the plausibility of an adjective-noun combination is correlated with its corpus co-occurrence frequency. In this paper, we estimate the co-occurrence frequencies of adjective-noun pairs that fail to occur in a 100 million word corpus using smoothing techniques and compare them to human plausibility ratings. Both class-based smoothing and distance-weighted averaging yield frequency estimates that are significant predictors of rated plausibility, which provides independent evidence for thevalidity of these smoothing techniques.

M3 - Conference contribution

SP - 346

EP - 353

BT - Proceedings of the 39th Annual Meeting of the Association for Computational Linguistics

PB - Association for Computational Linguistics

T2 - 39th Annual Meeting of the Association for Computational Linguistics

Y2 - 6 July 2011 through 11 July 2011

ER -

Evaluating Smoothing Algorithms against Plausibility Judgements

Abstract

Conference

Access to Document

Fingerprint

Cite this