Doc2Bot: Document grounded Bot Framework

Authors

  • Kshitij Fadnis IBM Research
  • Pankaj Dhoolia IBM Research
  • Li Zhu IBM Research
  • Q. Vera Liao IBM Research
  • Steven Ross IBM Research
  • Nathaniel Mills IBM Research
  • Sachindra Joshi IBM Research
  • Luis Lastras IBM Research

Keywords:

Chatbot Framework, Dialog Model Acquisition, Conversational Systems

Abstract

Conversational agents, or chatbots, are widely used to provide customer care and other informational support. Currently, the development of chatbots using standard frameworks requires a lot of manual crafting by subject matter experts (SMEs). On the other hand, while learning-based approaches to dialog have made significant advancements, they require training with a large volume of dialog data, which chatbot developers typically do not have access to. To tackle these challenges, we introduce DOC2BOT, a system that supports the automated construction of chatbots by digesting various forms of documents such as business manuals, HowTos, and customer support pages that organizations own. In addition to that, DOC2BOT provides a user-friendly experience to SMEs, and to minimize their effort by supporting intuitive interactions and streamlining their workflow.

Downloads

Published

2021-05-18

How to Cite

Fadnis, K., Dhoolia, P., Zhu, L., Liao, Q. V., Ross, S., Mills, N., Joshi, S., & Lastras, L. (2021). Doc2Bot: Document grounded Bot Framework. Proceedings of the AAAI Conference on Artificial Intelligence, 35(18), 16026-16028. Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/18001