To give reading which is widely different from normal Japanese grammar, like the reading especially in utterance of dialog.
A morphemic analyzing section 130 performs morphemic analysis processing on a text, and generates a word information string in which each word constituting the text is related to each attribute value and outputs the word information string. Then, a segment information generating section 140 generates a segment information string for relating a segment which is the word of the word information string or its divided unit, to a feature value extracted from the attribute value related to the word, and outputs the segment information string. A classification processing section 150 determines a content of re-read processing of each segment by using the feature value of the segment information string and classification regulation information, and outputs classification result information for indicating the content of re-read processing. Then, a conversion processing section 160 performs the re-read processing of each segment by using the classification result information and conversion regulation information.
COPYRIGHT: (C)2007,JPO&INPIT
JP2001343987A | ||||
JP2005235100A | ||||
JP2002311981A |
Taku Kusano
Yukio Nakamura