E. Yoshimura, S. Tsuchiya, H. Watabe, and T. Kawaoka (Japan)
Greeting Sentence, Association Judgement System, Natural Language
Greeting conversation plays an important part in smoothing oral communications. In the present paper, we describe a method of increase the number of appropriate greeting sentences for conversation and selecting sentences based on the situation by machine. We herein propose an intelligent greeting processing by which a machine generates various reply sentences automatically by obtaining information about the surrounding state and then generating the best conversation response based on the situation. Using the method described herein, we show that the proposed method increased the accuracy of greeting sentences to 84% and increased the number of greeting sentences to 23,891 sentences from 803 model sentences. Moreover, the technique used to select an appropriate sentence based on the situation was able to achieve an accuracy of 80.6%. When the situation was not considered, the accuracy was 10%. Thus, the proposed method is shown to be effective.
Important Links:
Go Back
