Another look at indirect negative evidence
Indirect negative evidence is clearly an important way for learners to constrain overgeneralisation, and yet a good learning theoretic analysis has yet to be provided for this, whether in a PAC or a probabilistic identification in the limit framework. In this paper we suggest a theoretical analysis of indirect negative evidence that allows the presence of ungrammatical strings in the input and also accounts for the relationship between grammaticality/acceptability and probability. Given independently justified assumptions about lower bounds on the probabilities of grammatical strings, we establish that a limited number of membership queries of some strings can be probabilistically simulated
|Keywords||No keywords specified (fix it)|
|Categories||categorize this paper)|
References found in this work BETA
No references found.
Citations of this work BETA
No citations found.
Similar books and articles
Scrambling, Indirect Passives, and Wanna Contraction.Yukio Otsu - 2000 - Behavioral and Brain Sciences 23 (1):45-46.
Coherence and Confirmation Through Causation.Gregory Wheeler & Richard Scheines - 2013 - Mind 122 (485):135-170.
Negative Features on Negative Indefinites: Evidence From Split Scope.D. Penka - 2012 - Journal of Semantics 29 (3):373-402.
Negative Probabilities and the Uses of Signed Probability Theory.Edward H. Allen - 1976 - Philosophy of Science 43 (1):53-70.
Reasons, Facts‐About‐Evidence, and Indirect Evidence.Stephen Kearns & Daniel Star - 2013 - Analytic Philosophy 54 (2):237-243.
Underdetermination and the Argument From Indirect Confirmation.Sorin Bangu - 2006 - Ratio 19 (3):269–277.
Quotation: Compositionality and Innocence Without Demonstration.Andrew Botterell & Robert J. Stainton - 2005 - Critica 37 (110):3-33.
Added to index2009-02-04
Total downloads30 ( #167,161 of 2,152,440 )
Recent downloads (6 months)1 ( #399,788 of 2,152,440 )
How can I increase my downloads?