摘要 |
PURPOSE:To provide the speech pair recognizing device which recognizes a pair of speeches consisting of an interrogative speech and an answering speech without general speaker's plan recognition. CONSTITUTION:A speech semantic contents extracting means 1 extracts semantic contents of speeches consisting of the declaration object, the sentence pattern, the function of speeches, etc., from inputted speeches. A speech premise extracting means 2 extracts the premise of speeches from semantic contents of speeches. A speech pair recognizing means 5 refers to vocabulary knowledge derived from the concept structure of events stored in a vocabulary knowledge storage means 3, the structure where relations between the interrogative speech and the answering speech stored in an interrogation-answer relation structure storage means 4 are described, and semantic contents and the premise of input speeches to recognize the relations between interrogation and answer, thus recognizing the pair of speeches. |