CAiRE: An End-to-End Empathetic Chatbot

Zhaojiang Lin, Peng Xu, Genta Indra Winata, Farhad Bin Siddique, Zihan Liu, Jamin Shin, Pascale Fung

AAAI 2020 pp. 13622-13623

doi:10.1609/AAAI.V34I09.7098 /aaai/2020/lin2020aaai-caire/

Abstract

In this paper, we present an end-to-end empathetic conversation agent CAiRE. Our system adapts TransferTransfo (Wolf et al., 2019) learning approach that fine-tunes a large-scale pre-trained language model with multi-task objectives: response language modeling, response prediction and dialogue emotion detection. We evaluate our model on the recently proposed empathetic-dialogues dataset (Rashkin et al., 2019), the experiment results show that CAiRE achieves state-of-the-art performance on dialogue emotion detection and empathetic response generation.

PDF AAAI Semantic Scholar

Cite

Text

Lin et al. "CAiRE: An End-to-End Empathetic Chatbot." AAAI Conference on Artificial Intelligence, 2020. doi:10.1609/AAAI.V34I09.7098

Markdown

[Lin et al. "CAiRE: An End-to-End Empathetic Chatbot." AAAI Conference on Artificial Intelligence, 2020.](https://mlanthology.org/aaai/2020/lin2020aaai-caire/) doi:10.1609/AAAI.V34I09.7098

BibTeX

@inproceedings{lin2020aaai-caire,
  title     = {{CAiRE: An End-to-End Empathetic Chatbot}},
  author    = {Lin, Zhaojiang and Xu, Peng and Winata, Genta Indra and Bin Siddique, Farhad and Liu, Zihan and Shin, Jamin and Fung, Pascale},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2020},
  pages     = {13622-13623},
  doi       = {10.1609/AAAI.V34I09.7098},
  url       = {https://mlanthology.org/aaai/2020/lin2020aaai-caire/}
}