A Korean morphological analyzer for speech translation system

Describes a Korean morphological analyzer which can be used as a part of language processor for a speech translation system. We have modified the CYK algorithm so that we are able to analyze many phenomena occurring in spontaneous speech such as ellipsis, shorter words, poor and mispronounced words, and so on, and we have also constructed a rule set with 112 connection rules and seven kinds of dictionaries, in which there are a total of about 81,000 keywords. Currently, we have achieved a success rate of 93.0% with a text corpus of dialogue for the hotel reservation domain.