Shared context probabilistic transducers

Yoshua Bengio; Samy Berigio; Jean Frangois Isabelle; Yorarn Singer

Shared context probabilistic transducers

Yoshua Bengio, Samy Berigio, Jean Frangois Isabelle, Yorarn Singer

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

Abstract

Recently, a model for supervised learning of probabilistic transducers represented by suffix trees was introduced. However, this algorithm tends to build very large trees, requiring very large amounts of computer memory. In this paper, we propose a new, more compact, transducer model in which one shares the parameters of distributions associated to contexts yielding similar conditional output distributions. We illustrate the advantages of the proposed algorithm with comparative experiments on inducing a noun phrase recognizer.

Original language	English (US)
Title of host publication	Advances in Neural Information Processing Systems 10 - Proceedings of the 1997 Conference, NIPS 1997
Publisher	Neural information processing systems foundation
Pages	409-415
Number of pages	7
ISBN (Print)	0262100762, 9780262100762
State	Published - 1998
Event	11th Annual Conference on Neural Information Processing Systems, NIPS 1997 - Denver, CO, United States Duration: Dec 1 1997 → Dec 6 1997

Publication series

Name	Advances in Neural Information Processing Systems
ISSN (Print)	1049-5258

Other

Other	11th Annual Conference on Neural Information Processing Systems, NIPS 1997
Country/Territory	United States
City	Denver, CO
Period	12/1/97 → 12/6/97

All Science Journal Classification (ASJC) codes

Computer Networks and Communications
Information Systems
Signal Processing

Cite this

@inproceedings{a6a00c50fd624cfc93724c54a0cc9459,

title = "Shared context probabilistic transducers",

abstract = "Recently, a model for supervised learning of probabilistic transducers represented by suffix trees was introduced. However, this algorithm tends to build very large trees, requiring very large amounts of computer memory. In this paper, we propose a new, more compact, transducer model in which one shares the parameters of distributions associated to contexts yielding similar conditional output distributions. We illustrate the advantages of the proposed algorithm with comparative experiments on inducing a noun phrase recognizer.",

author = "Yoshua Bengio and Samy Berigio and Isabelle, {Jean Frangois} and Yorarn Singer",

year = "1998",

language = "English (US)",

isbn = "0262100762",

series = "Advances in Neural Information Processing Systems",

publisher = "Neural information processing systems foundation",

pages = "409--415",

booktitle = "Advances in Neural Information Processing Systems 10 - Proceedings of the 1997 Conference, NIPS 1997",

note = "11th Annual Conference on Neural Information Processing Systems, NIPS 1997 ; Conference date: 01-12-1997 Through 06-12-1997",

}

Bengio, Y, Berigio, S, Isabelle, JF & Singer, Y 1998, Shared context probabilistic transducers. in Advances in Neural Information Processing Systems 10 - Proceedings of the 1997 Conference, NIPS 1997. Advances in Neural Information Processing Systems, Neural information processing systems foundation, pp. 409-415, 11th Annual Conference on Neural Information Processing Systems, NIPS 1997, Denver, CO, United States, 12/1/97.

Shared context probabilistic transducers. / Bengio, Yoshua; Berigio, Samy; Isabelle, Jean Frangois et al.
Advances in Neural Information Processing Systems 10 - Proceedings of the 1997 Conference, NIPS 1997. Neural information processing systems foundation, 1998. p. 409-415 (Advances in Neural Information Processing Systems).

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

TY - GEN

T1 - Shared context probabilistic transducers

AU - Bengio, Yoshua

AU - Berigio, Samy

AU - Isabelle, Jean Frangois

AU - Singer, Yorarn

PY - 1998

Y1 - 1998

N2 - Recently, a model for supervised learning of probabilistic transducers represented by suffix trees was introduced. However, this algorithm tends to build very large trees, requiring very large amounts of computer memory. In this paper, we propose a new, more compact, transducer model in which one shares the parameters of distributions associated to contexts yielding similar conditional output distributions. We illustrate the advantages of the proposed algorithm with comparative experiments on inducing a noun phrase recognizer.

AB - Recently, a model for supervised learning of probabilistic transducers represented by suffix trees was introduced. However, this algorithm tends to build very large trees, requiring very large amounts of computer memory. In this paper, we propose a new, more compact, transducer model in which one shares the parameters of distributions associated to contexts yielding similar conditional output distributions. We illustrate the advantages of the proposed algorithm with comparative experiments on inducing a noun phrase recognizer.

UR - http://www.scopus.com/inward/record.url?scp=84898974147&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84898974147&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84898974147

SN - 0262100762

SN - 9780262100762

T3 - Advances in Neural Information Processing Systems

SP - 409

EP - 415

BT - Advances in Neural Information Processing Systems 10 - Proceedings of the 1997 Conference, NIPS 1997

PB - Neural information processing systems foundation

T2 - 11th Annual Conference on Neural Information Processing Systems, NIPS 1997

Y2 - 1 December 1997 through 6 December 1997

ER -

Shared context probabilistic transducers

Abstract

Publication series

Other

All Science Journal Classification (ASJC) codes

Other files and links

Fingerprint

Cite this