Learnings from Implementing a Pilot Hybrid Question Answering System for a Government Agency in Singapore

Date
2023-01-03
Authors
Lee, Alvina
Venky, Shankararaman
Eng Lieh, Ouh
Contributor
Advisor
Department
Instructor
Depositor
Speaker
Researcher
Consultant
Interviewer
Journal Title
Journal ISSN
Volume Title
Publisher
Volume
Number/Issue
Starting Page
1910
Ending Page
Alternative Title
Abstract
The Singapore Government first released its digital government blueprint in 2018 with the key message for all agencies to be "digital to the core and served with heart". With this push, agencies are moving towards human-centric digital services to handle the surge in inquiries from individual citizens. One solution that is widely adopted is the use of chatbot technology that directly interfaces with the customer. However, several organizations have faced backlash from the citizens when such chatbots are unable to answer or give inappropriate answers to the questions. Hence this research explores a different approach to address this challenge using a question answering (QA) system that supports the CSOs to help answer the citizen inquiries more efficiently. This paper shares our preliminary learnings from the implementation of the pilot QA system, the Citizen Question Answering System (CQAS), and proposes areas for future work to enhance QA systems. This research work contributes to the body of artificial intelligence (AI) applied research in a government setting.
Description
Keywords
Emerging Topics in Digital Government, applied ai, digital government, question answering
Citation
Extent
10
Format
Geographic Location
Time Period
Related To
Proceedings of the 56th Hawaii International Conference on System Sciences
Rights
Attribution-NonCommercial-NoDerivatives 4.0 International
Rights Holder
Email libraryada-l@lists.hawaii.edu if you need this content in ADA-compliant format.