From Exemplar to Grammar: A Probabilistic Analogy-Based Model of Language Learning

@article{Bod2009FromET,
  title={From Exemplar to Grammar: A Probabilistic Analogy-Based Model of Language Learning},
  author={Rens Bod},
  journal={Cognitive science},
  year={2009},
  volume={33 5},
  pages={752-93}
}
While rules and exemplars are usually viewed as opposites, this paper argues that they form end points of the same distribution. By representing both rules and exemplars as (partial) trees, we can take into account the fluid middle ground between the two extremes. This insight is the starting point for a new theory of language learning that is based on the following idea: If a language learner does not know which phrase-structure trees should be assigned to initial sentences, s/he allows… CONTINUE READING

Citations

Publications citing this paper.
Showing 1-10 of 43 extracted citations

Starting from Scratch in Semantic Role Labeling: Early Indirect Supervision

Cognitive Aspects of Computational Language Acquisition • 2013
View 4 Excerpts
Highly Influenced

The problem of multimodal concurrent serial order in behavior.

Neuroscience and biobehavioral reviews • 2015
View 1 Excerpt
Highly Influenced

"Process and perish" or multiple buffers with push-down stacks?

The Behavioral and brain sciences • 2016
View 1 Excerpt

References

Publications referenced by this paper.
Showing 1-10 of 87 references

Foundations of Statistical Natural Language Processing

Computational Linguistics • 2000
View 6 Excerpts
Highly Influenced

Structural analogy and universal grammar

J. Anderson
Lingua, • 2006
View 4 Excerpts
Highly Influenced

Sentence memory: Storage vs. computation of frequent sentences

R. Bod
2001
View 3 Excerpts
Highly Influenced

Structure dependence in grammar formation

S. Crain, M. Nakayama
1987
View 3 Excerpts
Highly Influenced

Distributional structure

Z. Harris
Word • 1954
View 1 Excerpt
Highly Influenced

Similar Papers

Loading similar papers…