Explaining away ambiguity: learning verb selectional preference with Bayesian networks

Massimiliano Ciaramita; Mark Johnson

Explaining away ambiguity: learning verb selectional preference with Bayesian networks

Massimiliano Ciaramita, Mark Johnson

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

19 Downloads (Pure)

Abstract

This paper presents a Bayesian model for unsupervised learning of verb selectional preferences. For each verb the model creates a Bayesian network whose architecture is determined by
the lexical hierarchy of Wordnet and whose parameters are estimated from a list of verb-object pairs found from a corpus. "Explaining away", a well-known property of Bayesian networks, helps the model deal in a natural fashion with word sense ambiguity in the training data. On a word sense disambiguation test our model performed better than other state of the art systems for unsupervised learning of selectional preferences. Computational complexity problems, ways of improving this approach and methods for implementing "explaining away" in other graphical frameworks are discussed.

Original language	English
Title of host publication	Proceedings of the 18th International Conference on Computational Linguistics
Subtitle of host publication	COLINGS 2000
Place of Publication	New Brunswick, NJ
Publisher	Association for Computational Linguistics
Number of pages	7
ISBN (Print)	1-55860-717-X
Publication status	Published - 2000
Externally published	Yes
Event	International Conference on Computational Linguistics (18th : 2000) - Universität des Saarlandes, Saarbrücken, Germany Duration: 31 Jul 2000 → 4 Aug 2000

Conference

Conference	International Conference on Computational Linguistics (18th : 2000)
Abbreviated title	COLING 2000
Country/Territory	Germany
City	Saarbrücken
Period	31/07/00 → 4/08/00

Bibliographical note

Copyright the Publisher 2000. Version archived for private and non-commercial use with the permission of the author/s and according to publisher conditions. For further rights please contact the publisher.

Access to Document

Publisher version (open access)Final published version, 232 KBLicence: CC BY-NC-SA

https://www.aclweb.org/anthology/C00-1028/

Cite this

@inproceedings{5ec06f7d5f6749eda1db42c6e9c1f185,

title = "Explaining away ambiguity: learning verb selectional preference with Bayesian networks",

abstract = "This paper presents a Bayesian model for unsupervised learning of verb selectional preferences. For each verb the model creates a Bayesian network whose architecture is determined bythe lexical hierarchy of Wordnet and whose parameters are estimated from a list of verb-object pairs found from a corpus. {"}Explaining away{"}, a well-known property of Bayesian networks, helps the model deal in a natural fashion with word sense ambiguity in the training data. On a word sense disambiguation test our model performed better than other state of the art systems for unsupervised learning of selectional preferences. Computational complexity problems, ways of improving this approach and methods for implementing {"}explaining away{"} in other graphical frameworks are discussed.",

author = "Massimiliano Ciaramita and Mark Johnson",

note = "Copyright the Publisher 2000. Version archived for private and non-commercial use with the permission of the author/s and according to publisher conditions. For further rights please contact the publisher. ; International Conference on Computational Linguistics (18th : 2000), COLING 2000 ; Conference date: 31-07-2000 Through 04-08-2000",

year = "2000",

language = "English",

isbn = "1-55860-717-X ",

booktitle = "Proceedings of the 18th International Conference on Computational Linguistics",

publisher = "Association for Computational Linguistics",

}

Ciaramita, M & Johnson, M 2000, Explaining away ambiguity: learning verb selectional preference with Bayesian networks. in Proceedings of the 18th International Conference on Computational Linguistics: COLINGS 2000. Association for Computational Linguistics, New Brunswick, NJ, International Conference on Computational Linguistics (18th : 2000), Saarbrücken, Germany, 31/07/00. <https://www.aclweb.org/anthology/C00-1028/>

Explaining away ambiguity: learning verb selectional preference with Bayesian networks. / Ciaramita, Massimiliano; Johnson, Mark.
Proceedings of the 18th International Conference on Computational Linguistics: COLINGS 2000. New Brunswick, NJ: Association for Computational Linguistics, 2000.

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

TY - GEN

T1 - Explaining away ambiguity

T2 - International Conference on Computational Linguistics (18th : 2000)

AU - Ciaramita, Massimiliano

AU - Johnson, Mark

N1 - Copyright the Publisher 2000. Version archived for private and non-commercial use with the permission of the author/s and according to publisher conditions. For further rights please contact the publisher.

PY - 2000

Y1 - 2000

N2 - This paper presents a Bayesian model for unsupervised learning of verb selectional preferences. For each verb the model creates a Bayesian network whose architecture is determined bythe lexical hierarchy of Wordnet and whose parameters are estimated from a list of verb-object pairs found from a corpus. "Explaining away", a well-known property of Bayesian networks, helps the model deal in a natural fashion with word sense ambiguity in the training data. On a word sense disambiguation test our model performed better than other state of the art systems for unsupervised learning of selectional preferences. Computational complexity problems, ways of improving this approach and methods for implementing "explaining away" in other graphical frameworks are discussed.

AB - This paper presents a Bayesian model for unsupervised learning of verb selectional preferences. For each verb the model creates a Bayesian network whose architecture is determined bythe lexical hierarchy of Wordnet and whose parameters are estimated from a list of verb-object pairs found from a corpus. "Explaining away", a well-known property of Bayesian networks, helps the model deal in a natural fashion with word sense ambiguity in the training data. On a word sense disambiguation test our model performed better than other state of the art systems for unsupervised learning of selectional preferences. Computational complexity problems, ways of improving this approach and methods for implementing "explaining away" in other graphical frameworks are discussed.

M3 - Conference proceeding contribution

SN - 1-55860-717-X

BT - Proceedings of the 18th International Conference on Computational Linguistics

PB - Association for Computational Linguistics

CY - New Brunswick, NJ

Y2 - 31 July 2000 through 4 August 2000

ER -

Explaining away ambiguity: learning verb selectional preference with Bayesian networks

Abstract

Conference

Bibliographical note

Access to Document

Fingerprint

Cite this