Efficient Learning of Context-Free Grammars from Positive Structural Examples

Learning k-Reversible Context-Free Grammars from Positive Structural Examples

Leveraging Lexical Semantics to Infer Context-Free Grammars

Context-free grammars cannot be identified in the limit from positive examples (Gold, 1967), yet natural language grammars are more powerful than context-free grammars and humans learn them with remarkable ease from positive examples (Marcus, 1993). Identifiability results for formal languages ignore a potentially powerful source of information available to learners of natural languages, namely...

Learning context-free grammars from stochastic structural information

We consider the problem of learning context-free grammars from stochastic structural data. For this purpose, we have developed an algorithm (tlips) which identiies any rational tree set from stochastic samples and approximates the probability distribution of the trees in the language. The procedure identiies equivalent subtrees in the sample and outputs the hypothesis in linear time with the nu...

Meaning to Learn: Bootstrapping Semantics to Infer Syntax

Context-free grammars cannot be identified in the limit from positive examples (Gold 1967), yet natural language grammars are more powerful than context-free grammars and humans learn them with remarkable ease from positive examples (Marcus 1993). Identifiability results for formal languages ignore a potentially powerful source of information available to learners of natural languages, namely, ...

Learning Context Free Grammars in the Limit Aided by the Sample Distribution

We present an algorithm for learning context free grammars from positive structural examples (unlabeled parse trees). The algorithm receives a parameter in the form of a finite set of structures and the class of languages learnable by the algorithm depends on this parameter. Every context free language belongs to many such learnable classes. A second part of the algorithm is then used to determ...