Predictable and Adaptive Goal-oriented Dialog Policy Generation

Nhat Le, A. B. Siddique, Fuad Jamour, Samet Oymak, Vagelis Hristidis

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

3 Scopus citations

Abstract

Most existing commercial goal-oriented chatbots are diagram-based; i.e., they follow a rigid dialog flow to fill the slot values needed to achieve a user's goal. Diagram-based chatbots are predictable, thus their adoption in commercial settings; however, their lack of flexibility may cause many users to leave the conversation before achieving their goal. On the other hand, state-of-the-art research chatbots use Reinforcement Learning (RL) to generate flexible dialog policies. However, such chatbots can be unpredictable, may violate the intended business constraints, and require large training datasets to produce a mature policy. We propose a framework that achieves a middle ground between the diagram-based and RL-based chatbots: we constrain the space of possible chatbot responses using a novel structure, the chatbot dependency graph, and use RL to dynamically select the best valid responses. Dependency graphs are directed graphs that conveniently express a chatbot's logic by defining the dependencies among slots: all valid dialog flows are encapsulated in one dependency graph. Our experiments in several domains show that our framework quickly adapts to user characteristics and achieves up to 23.77% improved success rate compared to a state-of-the-art RL model.

Original languageEnglish
Title of host publicationProceedings - 2021 IEEE 15th International Conference on Semantic Computing, ICSC 2021
Pages40-47
Number of pages8
ISBN (Electronic)9781728188997
DOIs
StatePublished - Jan 2021
Event15th IEEE International Conference on Semantic Computing, ICSC 2021 - Virtual, Laguna Hills, United States
Duration: Jan 27 2021Jan 29 2021

Publication series

NameProceedings - 2021 IEEE 15th International Conference on Semantic Computing, ICSC 2021

Conference

Conference15th IEEE International Conference on Semantic Computing, ICSC 2021
Country/TerritoryUnited States
CityVirtual, Laguna Hills
Period1/27/211/29/21

Bibliographical note

Funding Information:
ACKNOWLEDGMENT This work was supported by NSF grants IIS-1619463, IIS-1838222, and IIS-1901379.

Publisher Copyright:
© 2021 IEEE.

Keywords

  • Dialog policy
  • Dialog systems
  • Goal oriented chatbots

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Science Applications
  • Decision Sciences (miscellaneous)

Fingerprint

Dive into the research topics of 'Predictable and Adaptive Goal-oriented Dialog Policy Generation'. Together they form a unique fingerprint.

Cite this