The Adapter-Bot: All-In-One Controllable Conversational Model

Authors

  • Zhaojiang Lin The Hong Kong University of Science and Technology
  • Andrea Madotto The Hong Kong University of Science and Technology
  • Yejin Bang The Hong Kong University of Science and Technology
  • Pascale Fung The Hong Kong University of Science and Technology

Keywords:

Chatbot, Conversational AI, Language Model

Abstract

In this paper, we present the Adapter-Bot, a generative chat-bot that uses a fixed backbone conversational model such as DialGPT (Zhang et al. 2019) and triggers on-demand dialogue skills via different adapters (Houlsby et al. 2019). Each adapter can be trained independently, thus allowing a continual integration of skills without retraining the entire model. Depending on the skills, the model is able to process multiple knowledge types, such as text, tables, and graphs, in a seamless manner. The dialogue skills can be triggered automatically via a dialogue manager, or manually, thus allowing high-level control of the generated responses. At the current stage, we have implemented 12 response styles (e.g., positive, negative etc.), 6 goal-oriented skills (e.g. weather information, movie recommendation, etc.), and personalized and emphatic responses.

Downloads

Published

2021-05-18

How to Cite

Lin, Z., Madotto, A., Bang, Y., & Fung, P. (2021). The Adapter-Bot: All-In-One Controllable Conversational Model. Proceedings of the AAAI Conference on Artificial Intelligence, 35(18), 16081-16083. Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/18018