A language learning model for finite parameter spaces

@article{Niyogi1996ALL,
  title={A language learning model for finite parameter spaces},
  author={P. Niyogi and R. Berwick},
  journal={Cognition},
  year={1996},
  volume={61},
  pages={161-193}
}
This paper shows how to formally characterize language learning in a finite parameter space, for instance, in the principles-and-parameters approach to language, as a Markov structure. New language learning results follow directly; we can explicitly calculate how many positive examples on average ("sample complexity") it will take for a learner to correctly identify a target language with high probability. We show how sample complexity varies with input distributions and learning regimes. In… Expand
Prior Knowledge in Learning Finite Parameter Spaces
Complexity in Language Acquisition
A Formal Theory of Language Development
Language Learning in Large Parameter Spaces
Analyzing the Rate at Which Languages Lose the Influence of a Common Ancestor
Necessary bias in natural language learning
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 23 REFERENCES
The Logical Problem of Language Change
Language Identification in the Limit
A computational learning model for metrical phonology
A computational model of language learnability and language chance
  • Robin Clark
  • Philosophy, Computer Science
  • 1992
Aspects of the Theory of Syntax
Parsing the LOB Corpus
Language identification in the limit
  • Triggers. Linguistic Inquiry,
  • 1994
...
1
2
3
...