Generalisation towards combinatorial productivity in language acquisition by simple recurrent networks

Francis C.K. Wong; William S.Y. Wang

doi:10.1109/KIMAS.2007.369799

Generalisation towards combinatorial productivity in language acquisition by simple recurrent networks

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

^*Corresponding author for this work

Chinese University of Hong Kong

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

10 Citations (Scopus)

Abstract

Language exhibits combinatorial productivity as complex constructions are composed of simple elements In a linear or hierarchical fashion. Complexity arises as one cannot be exposed to all possible combinations during ontogeny and yet to master a language one need to be, and very often is, able to generalise to process and comprehend constructions that are of novel combinations. Accounting for such an ability is a current challenge being tackled In connectionist research. In this study, we will first demonstrate that connectionist networks do generalise towards combinatorial productivity followed by an investigation of how the networks could achieve that.

Original language	English
Title of host publication	2007 International Conference on Integration of Knowledge Intensive Multi-Agent Systems, KIMAS 2007
Pages	139-144
Number of pages	6
DOIs	https://doi.org/10.1109/KIMAS.2007.369799
Publication status	Published - 2007
Externally published	Yes
Event	2007 International Conference on Integration of Knowledge Intensive Multi-Agent Systems, KIMAS 2007 - Waltham, MA, United States Duration: Apr 30 2007 → May 3 2007

Publication series

Name	2007 International Conference on Integration of Knowledge Intensive Multi-Agent Systems, KIMAS 2007

Conference

Conference	2007 International Conference on Integration of Knowledge Intensive Multi-Agent Systems, KIMAS 2007
Country/Territory	United States
City	Waltham, MA
Period	4/30/07 → 5/3/07

ASJC Scopus Subject Areas

General Computer Science

Access to Document

10.1109/KIMAS.2007.369799

Cite this

Wong, F. C. K., & Wang, W. S. Y. (2007). Generalisation towards combinatorial productivity in language acquisition by simple recurrent networks. In 2007 International Conference on Integration of Knowledge Intensive Multi-Agent Systems, KIMAS 2007 (pp. 139-144). Article 4227538 (2007 International Conference on Integration of Knowledge Intensive Multi-Agent Systems, KIMAS 2007). https://doi.org/10.1109/KIMAS.2007.369799

@inproceedings{e8e8fe17c3ad4ca79c804bec890f8780,

title = "Generalisation towards combinatorial productivity in language acquisition by simple recurrent networks",

abstract = "Language exhibits combinatorial productivity as complex constructions are composed of simple elements In a linear or hierarchical fashion. Complexity arises as one cannot be exposed to all possible combinations during ontogeny and yet to master a language one need to be, and very often is, able to generalise to process and comprehend constructions that are of novel combinations. Accounting for such an ability is a current challenge being tackled In connectionist research. In this study, we will first demonstrate that connectionist networks do generalise towards combinatorial productivity followed by an investigation of how the networks could achieve that.",

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

year = "2007",

doi = "10.1109/KIMAS.2007.369799",

language = "English",

isbn = "1424409454",

series = "2007 International Conference on Integration of Knowledge Intensive Multi-Agent Systems, KIMAS 2007",

pages = "139--144",

booktitle = "2007 International Conference on Integration of Knowledge Intensive Multi-Agent Systems, KIMAS 2007",

note = "2007 International Conference on Integration of Knowledge Intensive Multi-Agent Systems, KIMAS 2007 ; Conference date: 30-04-2007 Through 03-05-2007",

}

Wong, FCK & Wang, WSY 2007, Generalisation towards combinatorial productivity in language acquisition by simple recurrent networks. in 2007 International Conference on Integration of Knowledge Intensive Multi-Agent Systems, KIMAS 2007., 4227538, 2007 International Conference on Integration of Knowledge Intensive Multi-Agent Systems, KIMAS 2007, pp. 139-144, 2007 International Conference on Integration of Knowledge Intensive Multi-Agent Systems, KIMAS 2007, Waltham, MA, United States, 4/30/07. https://doi.org/10.1109/KIMAS.2007.369799

Generalisation towards combinatorial productivity in language acquisition by simple recurrent networks. / Wong, Francis C.K.; Wang, William S.Y.
2007 International Conference on Integration of Knowledge Intensive Multi-Agent Systems, KIMAS 2007. 2007. p. 139-144 4227538 (2007 International Conference on Integration of Knowledge Intensive Multi-Agent Systems, KIMAS 2007).

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

TY - GEN

T1 - Generalisation towards combinatorial productivity in language acquisition by simple recurrent networks

AU - Wong, Francis C.K.

AU - Wang, William S.Y.

PY - 2007

Y1 - 2007

N2 - Language exhibits combinatorial productivity as complex constructions are composed of simple elements In a linear or hierarchical fashion. Complexity arises as one cannot be exposed to all possible combinations during ontogeny and yet to master a language one need to be, and very often is, able to generalise to process and comprehend constructions that are of novel combinations. Accounting for such an ability is a current challenge being tackled In connectionist research. In this study, we will first demonstrate that connectionist networks do generalise towards combinatorial productivity followed by an investigation of how the networks could achieve that.

AB - Language exhibits combinatorial productivity as complex constructions are composed of simple elements In a linear or hierarchical fashion. Complexity arises as one cannot be exposed to all possible combinations during ontogeny and yet to master a language one need to be, and very often is, able to generalise to process and comprehend constructions that are of novel combinations. Accounting for such an ability is a current challenge being tackled In connectionist research. In this study, we will first demonstrate that connectionist networks do generalise towards combinatorial productivity followed by an investigation of how the networks could achieve that.

UR - http://www.scopus.com/inward/record.url?scp=34548715939&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=34548715939&partnerID=8YFLogxK

U2 - 10.1109/KIMAS.2007.369799

DO - 10.1109/KIMAS.2007.369799

M3 - Conference contribution

AN - SCOPUS:34548715939

SN - 1424409454

SN - 9781424409457

T3 - 2007 International Conference on Integration of Knowledge Intensive Multi-Agent Systems, KIMAS 2007

SP - 139

EP - 144

BT - 2007 International Conference on Integration of Knowledge Intensive Multi-Agent Systems, KIMAS 2007

T2 - 2007 International Conference on Integration of Knowledge Intensive Multi-Agent Systems, KIMAS 2007

Y2 - 30 April 2007 through 3 May 2007

ER -

Wong FCK, Wang WSY. Generalisation towards combinatorial productivity in language acquisition by simple recurrent networks. In 2007 International Conference on Integration of Knowledge Intensive Multi-Agent Systems, KIMAS 2007. 2007. p. 139-144. 4227538. (2007 International Conference on Integration of Knowledge Intensive Multi-Agent Systems, KIMAS 2007). doi: 10.1109/KIMAS.2007.369799

Generalisation towards combinatorial productivity in language acquisition by simple recurrent networks

Abstract

Publication series

Conference

ASJC Scopus Subject Areas

Access to Document

Other files and links

Fingerprint

Cite this