Computer Science – Computation and Language
Scientific paper
1995-04-13
Computer Science
Computation and Language
12 pages, ps, gzip, uuencoded
Scientific paper
Using the Thermodynamic Formalism, we introduce a Gibbsian model for the identification of regular grammars based only on positive evidence. This model mimics the natural language acquisition procedure driven by prosody which is here represented by the thermodynamical potential. The statistical question we face is how to estimate the incidenc e matrix of a subshift of finite type from a sample produced by a Gibbs state whose potential is known. The model acquaints for both the robustness of t he language acquisition procedure and language changes. The probabilistic appr oach we use avoids invoking ad-hoc restrictions as Berwick's Subset Principle.
Collet Pierre
Galves Antonio
Lopes A. A.
No associations
LandOfFree
MAXIMUM LIKELIHOOD AND MINIMUM ENTROPY IDENTIFICATION OF GRAMMARS does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.
If you have personal experience with MAXIMUM LIKELIHOOD AND MINIMUM ENTROPY IDENTIFICATION OF GRAMMARS, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and MAXIMUM LIKELIHOOD AND MINIMUM ENTROPY IDENTIFICATION OF GRAMMARS will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-542774