We propose a novel utterance selection method for chat-oriented dialogue systems. Many chat-oriented dialogue systems have huge databases of candidate utterances for utterance generation. However, many of these systems have a critical issue in that they select utterances that are inappropriate to the past conversation due to a limitation in contextual understanding. We solve this problem with our proposed method, which uses a discourse relation to the last utterance when selecting an utterance from candidate utterances. We aim to improve the performance of system utterance selection by preferentially selecting an utterance that has a discourse relation to the last utterance. Experimental results with human subjects showed that our proposed method was more effective than previous utterance selection methods.
CITATION STYLE
Otsuka, A., Hirano, T., Miyazaki, C., Higashinaka, R., Makino, T., & Matsuo, Y. (2017). Utterance selection using discourse relation filter for chat-oriented dialogue systems. In Lecture Notes in Electrical Engineering (Vol. 427 427 LNEE, pp. 355–365). Springer Verlag. https://doi.org/10.1007/978-981-10-2585-3_29
Mendeley helps you to discover research relevant for your work.