ACAT-G: An Interactive Learning Framework for Assisted Response Generation

Xueyuan Lu, Saurav Sahay, Zhou Yu, Lama Nachman

AAAI 2021 pp. 16084-16086

doi:10.1609/AAAI.V35I18.18019 /aaai/2021/lu2021aaai-acat/

Abstract

In this paper, we introduce ACAT-G, an interactive dialogue learning framework that incorporates constant human feedback into fine-tuning language models in order to assist conditioned dialog generation. The system takes in a limited amount of input from a human and generates personalized response corresponding to the context of the conversation within natural dialog time-frame. By combining inspirations from online learning, reinforcement learning, and large scale language models, we expect this project to provide a foundation for human-in-the-loop conditional dialog generation tasks.

PDF AAAI Semantic Scholar

Cite

Text

Lu et al. "ACAT-G: An Interactive Learning Framework for Assisted Response Generation." AAAI Conference on Artificial Intelligence, 2021. doi:10.1609/AAAI.V35I18.18019

Markdown

[Lu et al. "ACAT-G: An Interactive Learning Framework for Assisted Response Generation." AAAI Conference on Artificial Intelligence, 2021.](https://mlanthology.org/aaai/2021/lu2021aaai-acat/) doi:10.1609/AAAI.V35I18.18019

BibTeX

@inproceedings{lu2021aaai-acat,
  title     = {{ACAT-G: An Interactive Learning Framework for Assisted Response Generation}},
  author    = {Lu, Xueyuan and Sahay, Saurav and Yu, Zhou and Nachman, Lama},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2021},
  pages     = {16084-16086},
  doi       = {10.1609/AAAI.V35I18.18019},
  url       = {https://mlanthology.org/aaai/2021/lu2021aaai-acat/}
}