no code implementations • 11 Jul 2020 • Hung-Yi Lee, Cheng-Hao Ho, Chien-Fu Lin, Chiung-Chih Chang, Chih-Wei Lee, Yau-Shian Wang, Tsung-Yuan Hsu, Kuan-Yu Chen
Conventional seq2seq chatbot models attempt only to find sentences with the highest probabilities conditioned on the input sequences, without considering the sentiment of the output sentences.
no code implementations • 25 Sep 2019 • Chun-Hsing Lin, Alvin Chiang, Chi-Liang Liu, Chien-Fu Lin, Po-Hsien Chu, Siang-Ruei Wu, Yi-En Tsai, Chung-Yang (Ric) Huang
Score-function-based text generation approaches such as REINFORCE, in general, suffer from high computational complexity and training instability problems.