Connectionist-Inspired Incremental PCFG Parsing

Marten van Schijndel; Andy Exley; William Schuler

Connectionist-Inspired Incremental PCFG Parsing

Marten van Schijndel, Andy Exley, William Schuler

Computer Science and Engineering

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

4 Scopus citations

Abstract

Probabilistic context-free grammars (PCFGs) are a popular cognitive model of syntax (Jurafsky, 1996). These can be formulated to be sensitive to human working memory constraints by application of a right-corner transform (Schuler, 2009). One side-effect of the transform is that it guarantees at most a single expansion (push) and at most a single reduction (pop) during a syntactic parse. The primary finding of this paper is that this property of right-corner parsing can be exploited to obtain a dramatic reduction in the number of random variables in a probabilistic sequence model parser. This yields a simpler structure that more closely resembles existing simple recurrent network models of sentence comprehension.

Original language	English (US)
Title of host publication	Proceedings of the 2012 Workshop on Cognitive Modeling and Computational Linguistics, CMCL 2012 at the 2012 Conference of the North American Chapter of the Association for Computational Linguistics
Subtitle of host publication	Human Language Technologies, NAACL-HLT 2012
Editors	David Reitter, David Reitter, Roger Levy
Publisher	Association for Computational Linguistics (ACL)
Pages	51-60
Number of pages	10
ISBN (Electronic)	1937284204, 9781937284206
State	Published - 2012
Event	3rd Workshop on Cognitive Modeling and Computational Linguistics, CMCL 2012 at the 2012 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT 2012 - Montreal, Canada Duration: Jun 7 2012 → …

Publication series

Name	Proceedings of the Annual Meeting of the Association for Computational Linguistics
Volume	2012-June
ISSN (Print)	0736-587X

Conference

Conference	3rd Workshop on Cognitive Modeling and Computational Linguistics, CMCL 2012 at the 2012 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT 2012
Country/Territory	Canada
City	Montreal
Period	6/7/12 → …

Bibliographical note

Publisher Copyright:
© 2012 Association for Computational Linguistics

OpenUrl availability

Full text

Cite this

van Schijndel, M., Exley, A., & Schuler, W. (2012). Connectionist-Inspired Incremental PCFG Parsing. In D. Reitter, D. Reitter, & R. Levy (Eds.), Proceedings of the 2012 Workshop on Cognitive Modeling and Computational Linguistics, CMCL 2012 at the 2012 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT 2012 (pp. 51-60). (Proceedings of the Annual Meeting of the Association for Computational Linguistics; Vol. 2012-June). Association for Computational Linguistics (ACL).

Connectionist-Inspired Incremental PCFG Parsing. / van Schijndel, Marten; Exley, Andy; Schuler, William.
Proceedings of the 2012 Workshop on Cognitive Modeling and Computational Linguistics, CMCL 2012 at the 2012 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT 2012. ed. / David Reitter; David Reitter; Roger Levy. Association for Computational Linguistics (ACL), 2012. p. 51-60 (Proceedings of the Annual Meeting of the Association for Computational Linguistics; Vol. 2012-June).

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

van Schijndel, M, Exley, A & Schuler, W 2012, Connectionist-Inspired Incremental PCFG Parsing. in D Reitter, D Reitter & R Levy (eds), Proceedings of the 2012 Workshop on Cognitive Modeling and Computational Linguistics, CMCL 2012 at the 2012 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT 2012. Proceedings of the Annual Meeting of the Association for Computational Linguistics, vol. 2012-June, Association for Computational Linguistics (ACL), pp. 51-60, 3rd Workshop on Cognitive Modeling and Computational Linguistics, CMCL 2012 at the 2012 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT 2012, Montreal, Canada, 6/7/12.

van Schijndel M, Exley A, Schuler W. Connectionist-Inspired Incremental PCFG Parsing. In Reitter D, Reitter D, Levy R, editors, Proceedings of the 2012 Workshop on Cognitive Modeling and Computational Linguistics, CMCL 2012 at the 2012 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT 2012. Association for Computational Linguistics (ACL). 2012. p. 51-60. (Proceedings of the Annual Meeting of the Association for Computational Linguistics).

van Schijndel, Marten ; Exley, Andy ; Schuler, William. / Connectionist-Inspired Incremental PCFG Parsing. Proceedings of the 2012 Workshop on Cognitive Modeling and Computational Linguistics, CMCL 2012 at the 2012 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT 2012. editor / David Reitter ; David Reitter ; Roger Levy. Association for Computational Linguistics (ACL), 2012. pp. 51-60 (Proceedings of the Annual Meeting of the Association for Computational Linguistics).

@inproceedings{6e4c153052d14f5584dd677aee0e3ce7,

title = "Connectionist-Inspired Incremental PCFG Parsing",

abstract = "Probabilistic context-free grammars (PCFGs) are a popular cognitive model of syntax (Jurafsky, 1996). These can be formulated to be sensitive to human working memory constraints by application of a right-corner transform (Schuler, 2009). One side-effect of the transform is that it guarantees at most a single expansion (push) and at most a single reduction (pop) during a syntactic parse. The primary finding of this paper is that this property of right-corner parsing can be exploited to obtain a dramatic reduction in the number of random variables in a probabilistic sequence model parser. This yields a simpler structure that more closely resembles existing simple recurrent network models of sentence comprehension.",

author = "{van Schijndel}, Marten and Andy Exley and William Schuler",

note = "Publisher Copyright: {\textcopyright} 2012 Association for Computational Linguistics; 3rd Workshop on Cognitive Modeling and Computational Linguistics, CMCL 2012 at the 2012 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT 2012 ; Conference date: 07-06-2012",

year = "2012",

language = "English (US)",

series = "Proceedings of the Annual Meeting of the Association for Computational Linguistics",

publisher = "Association for Computational Linguistics (ACL)",

pages = "51--60",

editor = "David Reitter and David Reitter and Roger Levy",

booktitle = "Proceedings of the 2012 Workshop on Cognitive Modeling and Computational Linguistics, CMCL 2012 at the 2012 Conference of the North American Chapter of the Association for Computational Linguistics",

}

TY - GEN

T1 - Connectionist-Inspired Incremental PCFG Parsing

AU - van Schijndel, Marten

AU - Exley, Andy

AU - Schuler, William

PY - 2012

Y1 - 2012

N2 - Probabilistic context-free grammars (PCFGs) are a popular cognitive model of syntax (Jurafsky, 1996). These can be formulated to be sensitive to human working memory constraints by application of a right-corner transform (Schuler, 2009). One side-effect of the transform is that it guarantees at most a single expansion (push) and at most a single reduction (pop) during a syntactic parse. The primary finding of this paper is that this property of right-corner parsing can be exploited to obtain a dramatic reduction in the number of random variables in a probabilistic sequence model parser. This yields a simpler structure that more closely resembles existing simple recurrent network models of sentence comprehension.

AB - Probabilistic context-free grammars (PCFGs) are a popular cognitive model of syntax (Jurafsky, 1996). These can be formulated to be sensitive to human working memory constraints by application of a right-corner transform (Schuler, 2009). One side-effect of the transform is that it guarantees at most a single expansion (push) and at most a single reduction (pop) during a syntactic parse. The primary finding of this paper is that this property of right-corner parsing can be exploited to obtain a dramatic reduction in the number of random variables in a probabilistic sequence model parser. This yields a simpler structure that more closely resembles existing simple recurrent network models of sentence comprehension.

UR - http://www.scopus.com/inward/record.url?scp=85021637485&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85021637485&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:85021637485

T3 - Proceedings of the Annual Meeting of the Association for Computational Linguistics

SP - 51

EP - 60

BT - Proceedings of the 2012 Workshop on Cognitive Modeling and Computational Linguistics, CMCL 2012 at the 2012 Conference of the North American Chapter of the Association for Computational Linguistics

A2 - Reitter, David

A2 - Levy, Roger

PB - Association for Computational Linguistics (ACL)

T2 - 3rd Workshop on Cognitive Modeling and Computational Linguistics, CMCL 2012 at the 2012 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT 2012

Y2 - 7 June 2012

ER -

Connectionist-Inspired Incremental PCFG Parsing

Abstract

Publication series

Conference

Bibliographical note

OpenUrl availability

Other files and links

Fingerprint

Cite this