PAC-Learning Unambiguous NTS Languages
Non-terminally separated (NTS) languages are a subclass of deterministic context free languages where there is a stable relationship between the substrings of the language and the non-terminals of the grammar. We show that when the distribution of samples is generated by a PCFG, based on the same grammar as the target language, the class of unambiguous NTS languages is PAC-learnable from positive data alone, with polynomial bounds on data and computation.
KeywordsTarget Language Regular Language Context Free Grammar Context Free Language Categorial Grammar
Unable to display preview. Download preview PDF.
- [Adr99]Adriaans, P.: Learning shallow context-free languages under simple distributions. Technical Report ILLC Report PP-1999-13, Institute for Logic, Language and Computation, Amsterdam (1999)Google Scholar
- [Cha01]Charniak, E.: Immediate head parsing for language models. In: Proceedings of the 39th annual meeting of the ACL, Toulouse, France, pp. 116–123 (2001)Google Scholar
- [Cla06]Clark, A.: Learning deterministic context free grammars in the Omphalos competition. Machine Learning (to appear, 2006)Google Scholar
- [CT04b]Clark, A., Thollard, F.: Partially distribution-free learning of regular languages from positive samples. In: Proceedings of COLING, Geneva, Switzerland (2004)Google Scholar
- [Har54]Harris, Z.: Distributional structure. Word 10(2-3), 146–162 (1954)Google Scholar
- [KMR+94]Kearns, M.J., Mansour, Y., Ron, D., Rubinfeld, R., Schapire, R.E., Sellie, L.: On the learnability of discrete distributions. In: Proc. of the 25th Annual ACM Symposium on Theory of Computing, pp. 273–282 (1994)Google Scholar