Optimal Language Learning

Gold’s original paper on inductive inference introduced a notion of an optimal learner. Intuitively, a learner identifies a class of objects optimally iff there is no other learner that: requires as little of each presentation of each object in the class in order to identify that object, and, for some presentation of some object in the class, requires less of that presentation in order to identify that object. Wiehagen considered this notion in the context of function learning, and characterized an optimal function learner as one that is class-preserving, consistent, and (in a very strong sense) non-U-shaped, with respect to the class of functions learned. Herein, Gold’s notion is considered in the context of language learning. Intuitively, a language learner identifies a class of languages optimally iff there is no other learner that: requires as little of each text for each language in the class in order to identify that language, and, for some text for some language in the c...

• Type: Conference
• Year: 2008
• Where: ALT
• Authors: John Case, Samuel E. Moelius
• Keywords: ALT 2008, Arbitrary Optimal Learner, Language Learner, Machine Learning, Optimal Function Learner