Reassessing combinatorial productivity exhibited by simple recurrent networks in language acquisition

Francis C.K. Wong; James W. Minett; William S.Y. Wang

doi:10.1109/ijcnn.2006.246624

Reassessing combinatorial productivity exhibited by simple recurrent networks in language acquisition

Francis C.K. Wong^*, James W. Minett, William S.Y. Wang

^*Corresponding author for this work

Chinese University of Hong Kong

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

Abstract

it has long been criticized that connectionist models are inappropriate models for language acquisition since one of the important properties, the property of generalization beyond the training space, cannot be exhibited by the networks. Recently van der Velde et al. have discussed the issue of the combinatorial productivity, arguing that simple recurrent networks (SRNs) fail in this regard. They have attempted to show that performance of SRNs on generalization is limited to word-word association. In this paper, we report our follow-up study with two simulations demonstrating that (i) bi-gram does not play the dominant role as claimed (ii) SRNs are indeed able to exhibit combinatorial productivity when appropriately trained.

Original language	English
Title of host publication	International Joint Conference on Neural Networks 2006, IJCNN '06
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	1596-1603
Number of pages	8
ISBN (Print)	0780394909, 9780780394902
DOIs	https://doi.org/10.1109/ijcnn.2006.246624
Publication status	Published - 2006
Externally published	Yes
Event	International Joint Conference on Neural Networks 2006, IJCNN '06 - Vancouver, BC, Canada Duration: Jul 16 2006 → Jul 21 2006

Publication series

Name	IEEE International Conference on Neural Networks - Conference Proceedings
ISSN (Print)	1098-7576

Conference

Conference	International Joint Conference on Neural Networks 2006, IJCNN '06
Country/Territory	Canada
City	Vancouver, BC
Period	7/16/06 → 7/21/06

ASJC Scopus Subject Areas

Software

Access to Document

10.1109/ijcnn.2006.246624

Cite this

Wong, F. C. K., Minett, J. W., & Wang, W. S. Y. (2006). Reassessing combinatorial productivity exhibited by simple recurrent networks in language acquisition. In International Joint Conference on Neural Networks 2006, IJCNN '06 (pp. 1596-1603). Article 1716297 (IEEE International Conference on Neural Networks - Conference Proceedings). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ijcnn.2006.246624

Wong, Francis C.K. ; Minett, James W. ; Wang, William S.Y. / Reassessing combinatorial productivity exhibited by simple recurrent networks in language acquisition. International Joint Conference on Neural Networks 2006, IJCNN '06. Institute of Electrical and Electronics Engineers Inc., 2006. pp. 1596-1603 (IEEE International Conference on Neural Networks - Conference Proceedings).

@inproceedings{1b3a281061734d32a2e2868c987a1993,

title = "Reassessing combinatorial productivity exhibited by simple recurrent networks in language acquisition",

abstract = "it has long been criticized that connectionist models are inappropriate models for language acquisition since one of the important properties, the property of generalization beyond the training space, cannot be exhibited by the networks. Recently van der Velde et al. have discussed the issue of the combinatorial productivity, arguing that simple recurrent networks (SRNs) fail in this regard. They have attempted to show that performance of SRNs on generalization is limited to word-word association. In this paper, we report our follow-up study with two simulations demonstrating that (i) bi-gram does not play the dominant role as claimed (ii) SRNs are indeed able to exhibit combinatorial productivity when appropriately trained.",

author = "Wong, \{Francis C.K.\} and Minett, \{James W.\} and Wang, \{William S.Y.\}",

year = "2006",

doi = "10.1109/ijcnn.2006.246624",

language = "English",

isbn = "0780394909",

series = "IEEE International Conference on Neural Networks - Conference Proceedings",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "1596--1603",

booktitle = "International Joint Conference on Neural Networks 2006, IJCNN '06",

address = "United States",

note = "International Joint Conference on Neural Networks 2006, IJCNN '06 ; Conference date: 16-07-2006 Through 21-07-2006",

}

Wong, FCK, Minett, JW & Wang, WSY 2006, Reassessing combinatorial productivity exhibited by simple recurrent networks in language acquisition. in International Joint Conference on Neural Networks 2006, IJCNN '06., 1716297, IEEE International Conference on Neural Networks - Conference Proceedings, Institute of Electrical and Electronics Engineers Inc., pp. 1596-1603, International Joint Conference on Neural Networks 2006, IJCNN '06, Vancouver, BC, Canada, 7/16/06. https://doi.org/10.1109/ijcnn.2006.246624

Reassessing combinatorial productivity exhibited by simple recurrent networks in language acquisition. / Wong, Francis C.K.; Minett, James W.; Wang, William S.Y.
International Joint Conference on Neural Networks 2006, IJCNN '06. Institute of Electrical and Electronics Engineers Inc., 2006. p. 1596-1603 1716297 (IEEE International Conference on Neural Networks - Conference Proceedings).

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

TY - GEN

T1 - Reassessing combinatorial productivity exhibited by simple recurrent networks in language acquisition

AU - Wong, Francis C.K.

AU - Minett, James W.

AU - Wang, William S.Y.

PY - 2006

Y1 - 2006

N2 - it has long been criticized that connectionist models are inappropriate models for language acquisition since one of the important properties, the property of generalization beyond the training space, cannot be exhibited by the networks. Recently van der Velde et al. have discussed the issue of the combinatorial productivity, arguing that simple recurrent networks (SRNs) fail in this regard. They have attempted to show that performance of SRNs on generalization is limited to word-word association. In this paper, we report our follow-up study with two simulations demonstrating that (i) bi-gram does not play the dominant role as claimed (ii) SRNs are indeed able to exhibit combinatorial productivity when appropriately trained.

AB - it has long been criticized that connectionist models are inappropriate models for language acquisition since one of the important properties, the property of generalization beyond the training space, cannot be exhibited by the networks. Recently van der Velde et al. have discussed the issue of the combinatorial productivity, arguing that simple recurrent networks (SRNs) fail in this regard. They have attempted to show that performance of SRNs on generalization is limited to word-word association. In this paper, we report our follow-up study with two simulations demonstrating that (i) bi-gram does not play the dominant role as claimed (ii) SRNs are indeed able to exhibit combinatorial productivity when appropriately trained.

UR - http://www.scopus.com/inward/record.url?scp=40649106990&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=40649106990&partnerID=8YFLogxK

U2 - 10.1109/ijcnn.2006.246624

DO - 10.1109/ijcnn.2006.246624

M3 - Conference contribution

AN - SCOPUS:40649106990

SN - 0780394909

SN - 9780780394902

T3 - IEEE International Conference on Neural Networks - Conference Proceedings

SP - 1596

EP - 1603

BT - International Joint Conference on Neural Networks 2006, IJCNN '06

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - International Joint Conference on Neural Networks 2006, IJCNN '06

Y2 - 16 July 2006 through 21 July 2006

ER -

Wong FCK, Minett JW, Wang WSY. Reassessing combinatorial productivity exhibited by simple recurrent networks in language acquisition. In International Joint Conference on Neural Networks 2006, IJCNN '06. Institute of Electrical and Electronics Engineers Inc. 2006. p. 1596-1603. 1716297. (IEEE International Conference on Neural Networks - Conference Proceedings). doi: 10.1109/ijcnn.2006.246624

Reassessing combinatorial productivity exhibited by simple recurrent networks in language acquisition

Abstract

Publication series

Conference

ASJC Scopus Subject Areas

Access to Document

Other files and links

Fingerprint

Cite this