Unsupervised Syntax Learning with Categorial Grammars using Inference Rules
Xuewen Yao, James Ma, Sofia A. Duarte, Çağrı Çöltekin, T. Icard · 2009
We propose a learning method with categorial grammars using inference rules. The proposed learning method has been tested on an artificial language fragment that contains both ambiguity and recursion. We demonstrate that our learner has successfully converged to the target grammar using a relatively small set of initial assumptions. We also show that our method is successful at one of the celebrated problems of language acquisition literature: learning the English auxiliary order. 1.