Abstract | ||
---|---|---|
One challenge for dialogue agents is to recognize feelings of the conversation partner and respond accordingly. In this work, RoBERTa-GPT2 is proposed for empathetic dialogue generation, where the pre-trained auto-encoding RoBERTa is utilised as encoder and the pre-trained auto-regressive GPT-2 as decoder. With the combination of the pre-trained RoBERTa and GPT-2, our model realizes a new state-of-the-art emotion accuracy. To enable the empathetic ability of RoBERTa-GPT2 model, we propose a commonsense knowledge and emotional concepts extractor, in which the commonsensible and emotional concepts of dialogue context are extracted for the GPT-2 decoder. The experiment results demonstrate that the empathetic dialogue generation benefits from both pre-trained encoder-decoder architecture and external knowledge. |
Year | DOI | Venue |
---|---|---|
2021 | 10.1007/978-981-19-5538-9_5 | International Workshop on Spoken Dialogue Systems Technology (IWSDS) |
DocType | Citations | PageRank |
Conference | 0 | 0.34 |
References | Authors | |
0 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Ye Liu | 1 | 9 | 10.07 |
Wolfgang Maier | 2 | 2 | 2.41 |
Wolfgang Minker | 3 | 619 | 108.61 |
Stefan Ultes | 4 | 175 | 28.36 |