Conversation Learner - A Machine Teaching Tool for Building Dialog Managers for Task-Oriented Dialog Systems

Swadheen Shukla, Lars Liden, Shahin Shayandeh, Eslam Kamal, Jinchao Li, Matt Mazzola, Thomas Park, Baolin Peng, Jianfeng Gao


Abstract
Traditionally, industry solutions for building a task-oriented dialog system have relied on helping dialog authors define rule-based dialog managers, represented as dialog flows. While dialog flows are intuitively interpretable and good for simple scenarios, they fall short of performance in terms of the flexibility needed to handle complex dialogs. On the other hand, purely machine-learned models can handle complex dialogs, but they are considered to be black boxes and require large amounts of training data. In this demonstration, we showcase Conversation Learner, a machine teaching tool for building dialog managers. It combines the best of both approaches by enabling dialog authors to create a dialog flow using familiar tools, converting the dialog flow into a parametric model (e.g., neural networks), and allowing dialog authors to improve the dialog manager (i.e., the parametric model) over time by leveraging user-system dialog logs as training data through a machine teaching interface.
Anthology ID:
2020.acl-demos.39
Volume:
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: System Demonstrations
Month:
July
Year:
2020
Address:
Online
Editors:
Asli Celikyilmaz, Tsung-Hsien Wen
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
343–349
Language:
URL:
https://aclanthology.org/2020.acl-demos.39
DOI:
10.18653/v1/2020.acl-demos.39
Bibkey:
Cite (ACL):
Swadheen Shukla, Lars Liden, Shahin Shayandeh, Eslam Kamal, Jinchao Li, Matt Mazzola, Thomas Park, Baolin Peng, and Jianfeng Gao. 2020. Conversation Learner - A Machine Teaching Tool for Building Dialog Managers for Task-Oriented Dialog Systems. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: System Demonstrations, pages 343–349, Online. Association for Computational Linguistics.
Cite (Informal):
Conversation Learner - A Machine Teaching Tool for Building Dialog Managers for Task-Oriented Dialog Systems (Shukla et al., ACL 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.acl-demos.39.pdf
Video:
 http://slideslive.com/38928605