Automatic Acquisition and Efficient Representation of Syntactic Structures

Zach Solan; Eytan Ruppin; David Horn; Shimon Edelman

Automatic Acquisition and Efficient Representation of Syntactic Structures

Zach Solan, Eytan Ruppin, David Horn, Shimon Edelman

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

7 Scopus citations

Abstract

The distributional principle according to which morphemes that occur in identical contexts belong, in some sense, to the same category [1] has been advanced as a means for extracting syntactic structures from corpus data. We extend this principle by applying it recursively, and by using mutual information for estimating category coherence. The resulting model learns, in an unsupervised fashion, highly structured, distributed representations of syntactic knowledge from corpora. It also exhibits promising behavior in tasks usually thought to require representations anchored in a grammar, such as systematicity.

Original language	English
Title of host publication	NIPS 2002
Subtitle of host publication	Proceedings of the 15th International Conference on Neural Information Processing Systems
Editors	Suzanna Becker, Sebastian Thrun, Klaus Obermayer
Publisher	MIT Press
Pages	91-98
Number of pages	8
ISBN (Electronic)	0262025507, 9780262025508
State	Published - 2002
Event	15th International Conference on Neural Information Processing Systems, NIPS 2002 - Vancouver, Canada Duration: 9 Dec 2002 → 14 Dec 2002

Publication series

Name	NIPS 2002: Proceedings of the 15th International Conference on Neural Information Processing Systems

Conference

Conference	15th International Conference on Neural Information Processing Systems, NIPS 2002
Country/Territory	Canada
City	Vancouver
Period	9/12/02 → 14/12/02

Funding

Funders	Funder number
Dan David Prize Foundation
Horowitz Center for Complexity Science
Lillian Lee and Bo Pang
United States-Israel Binational Science Foundation
Tel Aviv University

Cite this

Solan, Z., Ruppin, E., Horn, D., & Edelman, S. (2002). Automatic Acquisition and Efficient Representation of Syntactic Structures. In S. Becker, S. Thrun, & K. Obermayer (Eds.), NIPS 2002: Proceedings of the 15th International Conference on Neural Information Processing Systems (pp. 91-98). (NIPS 2002: Proceedings of the 15th International Conference on Neural Information Processing Systems). MIT Press.

Solan, Zach ; Ruppin, Eytan ; Horn, David et al. / Automatic Acquisition and Efficient Representation of Syntactic Structures. NIPS 2002: Proceedings of the 15th International Conference on Neural Information Processing Systems. editor / Suzanna Becker ; Sebastian Thrun ; Klaus Obermayer. MIT Press, 2002. pp. 91-98 (NIPS 2002: Proceedings of the 15th International Conference on Neural Information Processing Systems).

@inproceedings{c2c6b9e9928a4f1aba61e763ad629be0,

title = "Automatic Acquisition and Efficient Representation of Syntactic Structures",

abstract = "The distributional principle according to which morphemes that occur in identical contexts belong, in some sense, to the same category [1] has been advanced as a means for extracting syntactic structures from corpus data. We extend this principle by applying it recursively, and by using mutual information for estimating category coherence. The resulting model learns, in an unsupervised fashion, highly structured, distributed representations of syntactic knowledge from corpora. It also exhibits promising behavior in tasks usually thought to require representations anchored in a grammar, such as systematicity.",

author = "Zach Solan and Eytan Ruppin and David Horn and Shimon Edelman",

note = "Publisher Copyright: {\textcopyright} NIPS 2002: Proceedings of the 15th International Conference on Neural Information Processing Systems. All rights reserved.; 15th International Conference on Neural Information Processing Systems, NIPS 2002 ; Conference date: 09-12-2002 Through 14-12-2002",

year = "2002",

language = "אנגלית",

series = "NIPS 2002: Proceedings of the 15th International Conference on Neural Information Processing Systems",

publisher = "MIT Press",

pages = "91--98",

editor = "Suzanna Becker and Sebastian Thrun and Klaus Obermayer",

booktitle = "NIPS 2002",

address = "ארצות הברית",

}

Solan, Z, Ruppin, E , Horn, D & Edelman, S 2002, Automatic Acquisition and Efficient Representation of Syntactic Structures. in S Becker, S Thrun & K Obermayer (eds), NIPS 2002: Proceedings of the 15th International Conference on Neural Information Processing Systems. NIPS 2002: Proceedings of the 15th International Conference on Neural Information Processing Systems, MIT Press, pp. 91-98, 15th International Conference on Neural Information Processing Systems, NIPS 2002, Vancouver, Canada, 9/12/02.

Automatic Acquisition and Efficient Representation of Syntactic Structures. / Solan, Zach; Ruppin, Eytan ; Horn, David et al.
NIPS 2002: Proceedings of the 15th International Conference on Neural Information Processing Systems. ed. / Suzanna Becker; Sebastian Thrun; Klaus Obermayer. MIT Press, 2002. p. 91-98 (NIPS 2002: Proceedings of the 15th International Conference on Neural Information Processing Systems).

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

TY - GEN

T1 - Automatic Acquisition and Efficient Representation of Syntactic Structures

AU - Solan, Zach

AU - Ruppin, Eytan

AU - Horn, David

AU - Edelman, Shimon

PY - 2002

Y1 - 2002

N2 - The distributional principle according to which morphemes that occur in identical contexts belong, in some sense, to the same category [1] has been advanced as a means for extracting syntactic structures from corpus data. We extend this principle by applying it recursively, and by using mutual information for estimating category coherence. The resulting model learns, in an unsupervised fashion, highly structured, distributed representations of syntactic knowledge from corpora. It also exhibits promising behavior in tasks usually thought to require representations anchored in a grammar, such as systematicity.

AB - The distributional principle according to which morphemes that occur in identical contexts belong, in some sense, to the same category [1] has been advanced as a means for extracting syntactic structures from corpus data. We extend this principle by applying it recursively, and by using mutual information for estimating category coherence. The resulting model learns, in an unsupervised fashion, highly structured, distributed representations of syntactic knowledge from corpora. It also exhibits promising behavior in tasks usually thought to require representations anchored in a grammar, such as systematicity.

UR - http://www.scopus.com/inward/record.url?scp=85100109225&partnerID=8YFLogxK

M3 - ???researchoutput.researchoutputtypes.contributiontobookanthology.conference???

AN - SCOPUS:85100109225

T3 - NIPS 2002: Proceedings of the 15th International Conference on Neural Information Processing Systems

SP - 91

EP - 98

BT - NIPS 2002

A2 - Becker, Suzanna

A2 - Thrun, Sebastian

A2 - Obermayer, Klaus

PB - MIT Press

T2 - 15th International Conference on Neural Information Processing Systems, NIPS 2002

Y2 - 9 December 2002 through 14 December 2002

ER -

Solan Z, Ruppin E , Horn D, Edelman S. Automatic Acquisition and Efficient Representation of Syntactic Structures. In Becker S, Thrun S, Obermayer K, editors, NIPS 2002: Proceedings of the 15th International Conference on Neural Information Processing Systems. MIT Press. 2002. p. 91-98. (NIPS 2002: Proceedings of the 15th International Conference on Neural Information Processing Systems).

Automatic Acquisition and Efficient Representation of Syntactic Structures

Abstract

Publication series

Conference

Funding

Other files and links

Fingerprint

Cite this