Learnability and Overgeneration in Computational Syntax
- Yiding Hao (Yale University)
Abstract
This paper addresses the hypothesis that unnatural patterns generated by grammar formalisms can be eliminated on the grounds that they are unlearnable. I consider three examples of formal languages thought to represent dependencies unattested in natural language syntax, and show that all three can be learned by grammar induction algorithms following the Distributional Learning paradigm of Clark and Eyraud (2007). While learnable language classes are restrictive by necessity (Gold, 1967), these facts suggest that learnability alone may be insufficient for addressing concerns of overgeneration in syntax.
Keywords: learnability, mathematical linguistics, computational linguistics, syntax, poverty of the stimulus, overgeneration, context-free grammars, multiple context-free grammars, minimalist grammars, distributional learning, grammatical inference, machine learning, formal language theory
How to Cite:
Hao, Y., (2019) “Learnability and Overgeneration in Computational Syntax”, Society for Computation in Linguistics 2(1), 124-134. doi: https://doi.org/10.7275/1qmz-bg76
Downloads:
Download PDF