Another look at indirect negative evidence
Alexander Clark and Shalom Lappin
In: Proceedings of the EACL Workshop on Cognitive Aspects of Computational Language Acquisition, 31 March 2009, Athens, Greece.
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