Learning the Past Tense of English Verbs: The Symbolic Pattern Associator vs. Connectionist Models

  title={Learning the Past Tense of English Verbs: The Symbolic Pattern Associator vs. Connectionist Models},
  author={Charles X. Ling},
  journal={J. Artif. Intell. Res.},
Learning the past tense of English verbs | a seemingly minor aspect of language acquisition | has generated heated debates since 1986, and has become a landmark task for testing the adequacy of cognitive modeling. Several arti cial neural networks (ANNs) have been implemented, and a challenge for better symbolic models has been posed. In this paper, we present a general-purpose Symbolic Pattern Associator (SPA) based upon the decision-tree learning algorithm ID3. We conduct extensive head-to… CONTINUE READING
Highly Cited
This paper has 60 citations. REVIEW CITATIONS


Publications citing this paper.

60 Citations

Citations per Year
Semantic Scholar estimates that this publication has 60 citations based on the available data.

See our FAQ for additional information.


Publications referenced by this paper.
Showing 1-10 of 21 references

Connections and symbols: closing the gap

Cognition • 1993
View 5 Excerpts
Highly Influenced

Generalization of regular and irregular morphological patterns

S. Prasada, S. Pinker
Language and Cognitive Processes, • 1993
View 6 Excerpts
Highly Influenced

Rules of language.

Science • 1991
View 4 Excerpts
Highly Influenced

Beyond rules and exceptions: A connectionist modeling approach to in ectional morphology

K. Daugherty, M. Seidenberg
View 1 Excerpt

Comparison of symbolic, statistical and neural network classi ers

C. Feng, R. King, A. Sutherland, R. Henery

Similar Papers

Loading similar papers…