Personalized responses are essential for having an informative and human-like conversation. Because it is difficult to collect a large amount of dialogues involved with specific speakers, it is desirable that chatbot can learn to generate personalized responses simply from monologues of individuals. In this paper, we propose a novel personalized dialogue generation method which reduces the training data requirement to dialogues without speaker information and monologues of every target speaker. In the proposed approach, a generative adversarial network ensures the responses containing recognizable personal characteristics of the target speaker, and a backward SEQ2SEQ model reconstructs the input message for keeping the coherence of the generated responses. The proposed model demonstrates its flexibility to respond to open-domain conversations, and the experimental results show that the proposed method performs favorably against prior work in coherence, personality classification, and human evaluation.
Cite as: Su, F.-G., Hsu, A.R., Tuan, Y.-L., Lee, H.-Y. (2019) Personalized Dialogue Response Generation Learned from Monologues. Proc. Interspeech 2019, 4160-4164, doi: 10.21437/Interspeech.2019-1696
@inproceedings{su19b_interspeech, author={Feng-Guang Su and Aliyah R. Hsu and Yi-Lin Tuan and Hung-Yi Lee}, title={{Personalized Dialogue Response Generation Learned from Monologues}}, year=2019, booktitle={Proc. Interspeech 2019}, pages={4160--4164}, doi={10.21437/Interspeech.2019-1696} }