Grammar Transfer in a Second Order Recurrent Neural Network
Michiro Negishi, Stephen José Hanson · The MIT Press eBooks · 2002
It has been known that people, after being exposed to sentences generated by an arti cial grammar, acquire implicit grammatical knowledge and are able to transfer the knowledge to inputs that are generated by a modi ed grammar. We show that a second order recurrent neural network is able to transfer grammatical knowledge from one language (generated by a Finite State Machine) to another language which dier both in vocabularies and syntax. Representation of the grammatical knowledge in the network is analyzed using linear discriminant analysis.