Multi-lingual Sentence Generation from the PIVOT Interlingua

This paper proposes a strategy for French and Spanish sentence generation systems, based on the English generation system. The English generation mode! consists of four procedures, conceptual wording (sentence-structure planning), syntactic selection, ordering and morphological generation. The analysis of linguistic similarities and differences between English, French and Spanish reveals that a single model is applicable for Spanish and French generation by modifying the contents of the dictionary and the knowledge base. The differences can naturally be represented in the knowledge base and dictionary, which is difficult in the transfer approach. So, it is possible to develop Spanish and French generation systems from the English generation system, merely by modifying the contents of the dictionary and knowledge base. Using this strategy, the authors have succeeded in developing English, Spanish, French, Korean and Japanese sentence generation systems. The input for each system is a languageindependent conceptual representation, which is an interlingua of the machine translation system PIVOT. The sizes for each dictionary are 70,000 English words, 5,000 Spanish words, 3,000 French words, 110,000 Japanese words and 10,000 Korean words. The systems are implemented on NEC’s work station.