@article{Crepinsek:2006:ENTCS,
        title = {Inferring Context-Free Grammars for Domain-Specific
                 Languages},
        author = {Matej Crepinsek and Marjan Mernik and Barrett R. Bryant and Faizan Javed and Alan Sprague},
        journal = {Electronic Notes in Theoretical Computer Science},
        month = {12 December},
        note = {Proceedings of the Fifth Workshop on Language
                 Descriptions, Tools, and Applications (LDTA 2005)},
        number = 4,
        pages = {99--116},
        volume = 141,
        year = 2005,
        issn = {1571-0661},
	doi = {doi:10.1016/j.entcs.2005.02.055},
	abstract = {In the area of programming languages, context-free
                 grammars (CFGs) are of special importance since almost
                 all programming languages employ CFG's in their design.
                 Recent approaches to CFG induction are not able to
                 infer context-free grammars for general-purpose
                 programming languages. In this paper it is shown that
                 syntax of a small domain-specific language can be
                 inferred from positive and negative programs provided
                 by domain experts. In our work we are using the genetic
                 programming approach in grammatical inference.
                 Grammar-specific heuristic operators and nonrandom
                 construction of the initial population are proposed to
                 achieve this task. Suitability of the approach is shown
                 by examples where underlying context-free grammars are
                 successfully inferred.},
	biburl = {http://www.bibsonomy.org/bibtex/2b359032acefed37074158ec1c5cb61bc/brazovayeye},
	keywords = {Learning inference, from examples, Exhaustive and programming, search genetic algorithms, negative positive Grammar induction,}
}

@mastersthesis{rennie2001naive,
        title = {Improving Multi-class Text Classification with Naive Bayes},
        author = {Jason D. M. Rennie},
        school = {Massachusetts Institute of Technology},
        year = 2001,
        url = {http://people.csail.mit.edu/~jrennie/papers/sm-thesis.pdf},
        abstract = {There are numerous text documents available in electronic form. More and more
are becoming available every day. Such documents represent a massive amount of
information that is easily accessible. Seeking value in this huge collection requires
organization; much of the work of organizing documents can be automated through
text classification. The accuracy and our understanding of such systems greatly
influences their usefulness. In this paper, we seek 1) to advance the understanding
of commonly used text classification techniques, and 2) through that understanding,
improve the tools that are available for text classification. We begin by clarifying
the assumptions made in the derivation of Naive Bayes, noting basic properties and
proposing ways for its extension and improvement. Next, we investigate the quality
of Naive Bayes parameter estimates and their impact on classification. Our analysis
leads to a theorem which gives an explanation for the improvements that can be
found in multiclass classification with Naive Bayes using Error-Correcting Output
Codes. We use experimental evidence on two commonly-used data sets to exhibit an
application of the theorem. Finally, we show fundamental flaws in a commonly-used
feature selection algorithm and develop a statistics-based framework for text feature
selection. Greater understanding of Naive Bayes and the properties of text allows us
to make better use of it in text classification.},
	biburl = {http://www.bibsonomy.org/bibtex/22896eb9538a6ee34f8e6c6757bdcf99e/jil},
	keywords = {herleitung multinomial estimation bayes exhaustive likelihood thesis prior naive komplett maximum map deduction mle}
}