An implementation of a partial parser in the spoken language translator

We describe the characteristics of the partial parser and evaluations of the output of the spoken language translator with concept-based grammars. This translator translates the Korean utterance generated by a speech recognizer which recognizes spontaneous speech into an English/Japanese utterances through a concept analysis approach. The parsing fails to parse input utterance when the parser reaches medium level tokens because the successful parsing results only accomplish when all the concepts, except for the highest top level tokens, are reduced into the ones of the highest top level tokens. At this time, the partial parser is run to analyze those medium level tokens without parsing failure. We obtained 55.2% for the recognized data based on the translation rate before applying the partial parser to the spoken translator, and 79.1% after applying the partial parser