Greedy Grammar Induction with Indirect Negative Evidence (2312.15321v2)
Abstract: This paper offers a fresh look at the pumping lemma constant as an upper bound on the information required for learning Context Free Grammars. An objective function based on indirect negative evidence considers the occurrences, and non-occurrences, of a finite number of strings, encountered after a sufficiently long presentation. This function has optimal substructure in the hypotheses space, giving rise to a greedy search learner in a branch and bound method. A hierarchy of learnable classes is defined in terms of the number of production rules that must be added to interim solutions in order to incrementally fit the input. Efficiency strongly depends on the position of the target grammar in the hierarchy and on the richness of the input.
- Dana Angluin. 1980. Inductive inference of formal languages from positive data. Information and control, 45(2):117–135.
- On formai properties oî simple phreise structure grammars. STUF-Language Typology and Universals, 14(1-4):143–172.
- Concentration inequalities in the infinite urn scheme for occupancy counts and the missing mass, with applications. Bernoulli, 23(1):249 – 287.
- Noam Chomsky. 1981. Lectures on government and binding, foris, dordrecht. ChomskyLectures on Government and Binding1981.
- Alexander Clark and Rémi Eyraud. 2007. Polynomial identification in the limit of substitutable context-free languages. Journal of Machine Learning Research, 8(8).
- Alexander Clark and Shalom Lappin. 2010. Linguistic Nativism and the Poverty of the Stimulus. John Wiley & Sons.
- Jay Earley. 1970. An efficient context-free parsing algorithm. Communications of the ACM, 13(2):94–102.
- E Mark Gold. 1967. Language identification in the limit. Information and control, 10(5):447–474.
- Irving J Good. 1953. The population frequencies of species and the estimation of population parameters. Biometrika, 40(3-4):237–264.
- Aravind K Joshi. 1987. An introduction to tree adjoining grammars. Mathematics of language, 1:87–115.
- Bill Keller and Rudi Lutz. 1997. Evolving stochastic context-free grammars from examples using a minimum description length principle. In Workshop on Automatic Induction, Grammatical Inference and Language Acquisition.
- John R Koza. 1994. Genetic programming as a means for programming computers by natural selection. Statistics and computing, 4:87–112.
- David McAllester and Luis Ortiz. 2003. Concentration inequalities for the missing mass and for histogram rule error. Journal of Machine Learning Research, 4(Oct):895–911.
- Elizabeth Scott. 2008. Sppf-style parsing from earley recognisers. Electronic Notes in Theoretical Computer Science, 203(2):53–67.
- Stuart M Shieber. 1985. Evidence against the context-freeness of natural language. In The Formal complexity of natural language, pages 320–334. Springer.
- Ray J Solomonoff. 1964. A formal theory of inductive inference. part i. Information and control, 7(1):1–22.
- Andreas Stolcke. 1995. An efficient probabilistic context-free parsing algorithm that computes prefix probabilities. Computational Linguistics, 21(2):165–201.
- Masaru Tomita. 2013. Efficient parsing for natural language: a fast algorithm for practical systems, volume 8. Springer Science & Business Media.
- Peter Wyard. 1994. Representational issues for context free grammar induction using genetic algorithms. In Grammatical Inference and Applications: Second International Colloquium, ICGI-94 Alicante, Spain, September 21–23, 1994 Proceedings 2, pages 222–235. Springer.
Collections
Sign up for free to add this paper to one or more collections.