Partially Distribution-Free Learning of Regular Languages from Positive Samples
نویسندگان
چکیده
Regular languages are widely used in NLP today in spite of their shortcomings. Efficient algorithms that can reliably learn these languages, and which must in realistic applications only use positive samples, are necessary. These languages are not learnable under traditional distribution free criteria. We claim that an appropriate learning framework is PAC learning where the distributions are constrained to be generated by a class of stochastic automata with support equal to the target concept. We discuss how this is related to other learning paradigms. We then present a simple learning algorithm for regular languages, and a self-contained proof that it learns according to this partially distribution free criterion.
منابع مشابه
Grammatical Inference and the Argument from the Poverty of the Stimulus
Formal results in grammatical inference clearly have some relevance to first language acquisition. Initial formalisations of the problem (Gold 1967) are however inapplicable to this particular situation. In this paper we construct an appropriate formalisation of the problem using a modern vocabulary drawn from statistical learning theory and grammatical inference and looking in detail at the re...
متن کاملGrammatical Inference And First Language Acquisition
One argument for parametric models of language has been learnability in the context of first language acquisition. The claim is made that “logical” arguments from learnability theory require non-trivial constraints on the class of languages. Initial formalisations of the problem (Gold, 1967) are however inapplicable to this particular situation. In this paper we construct an appropriate formali...
متن کاملPAC-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 positi...
متن کاملUsing Contextual Representations to Efficiently Learn Context-Free Languages
We present a polynomial update time algorithm for the inductive inference of a large class of context-free languages using the paradigm of positive data and a membership oracle. We achieve this result by moving to a novel representation, called Contextual Binary Feature Grammars (CBFGs), which are capable of representing richly structured context-free languages as well as some context sensitive...
متن کاملCharacterizing PAC-Learnability of Semilinear Sets
The learnability of the class of letter-counts of regular languages (semilinear sets) and other related classes of subsets of N d with respect to the distribution-free learning model of Valiant (PAC-learning model) is characterized. Using the notion of reducibility among learning problems due to Pitt and Warmuth called \prediction preserving reducibility," and a special case thereof, a number o...
متن کامل