Generation for Dialogue Translation Using Typed Feature Structure Unification

This a r t i c l e i n t r o d u c e s a b i d i r e c t i o n a l g r a m m a r genera t ion sys tem called fea ture s t ructure-directed generat ion, developed for a d ia logue t rans la t ion sys tem. The sys tem utilizes typed feature structures to control the top-down derivation in a declarative way. This generation system also uses disjunctive feature structures to reduce the number of copies of the derivat ion tree. The grammar for this generator is designed to properly generate the speaker 's intention in a telephone dialogue.