Evaluation Results of Concept-based Translator with Partial Parsing

In this paper, we describe an evaluation of the output of the translator using conceptbased grammars. This translator translates the Korean sentence generated by a speech recognizer into an English sentence through a concept analysis approach. A partial parsing function added to the translator and obtained better improvement because the performance of the parser (whole parser) is low in the stage before applying partial parser to the translator. We obtained 76.5% and 55.2% for the transcribed text data and the recognized data as the translation rate of meaning based on intention before applying partial parser to the translator, and obtained 78.5% and 79.1% for both data after applying partial parser, respectively.