Domain-specific embeddings for question-answering systems. FAQs for health coaching
Loading...
Author (Corporation)
Publication date
2024
Typ of student thesis
Course of study
Collections
Type
04B - Conference paper
Editors
Editor (Corporation)
Supervisor
Parent work
Proceedings of the AAAI 2024 Spring Symposium Series
Special issue
DOI of the original publication
Link
Series
Series number
Volume
3
Issue / Number
Pages / Duration
175-179
Patent number
Publisher / Publishing institution
Stanford University
Place of publication / Event location
Stanford
Edition
Version
Programming language
Assignee
Practice partner / Client
Abstract
FAQs are widely used to respond to users’ knowledge needs within knowledge domains. While LLM might be a promising way to address user questions, they are still prone to hallucinations i.e., inaccurate or wrong responses, which, can, inter alia, lead to massive problems, including, but not limited to, ethical issues. As a part of the healthcare coach chatbot for young Nigerian HIV clients, the need to meet their information needs through FAQs is one of the main coaching requirements. In this paper, we explore if domain knowledge in HIV FAQs can be represented as text embeddings to retrieve similar questions matching user queries, thus improving the understanding of the chatbot and the satisfaction of the users. Specifically, we describe our approach to developing an FAQ chatbot for the domain of HIV. We used a predefined FAQ question-answer knowledge base in English and Pidgin co-created by HIV clients and experts from Nigeria and Switzerland. The results of the post-engagement survey show that the chatbot mostly understood the user’s questions and could identify relevant matching questions and retrieve an appropriate response.
Keywords
Event
AAAI 2024 Spring Symposium Series
Exhibition start date
Exhibition end date
Conference start date
25.03.2024
Conference end date
27.03.2024
Date of the last check
ISBN
978-1-57735-888-6
ISSN
Language
English
Created during FHNW affiliation
Yes
Strategic action fields FHNW
Publication status
Published
Review
Peer review of the complete publication
Open access category
Closed
License
Citation
Martin, A., Pande, C., Schwander, S., Ajuwon, A. J., & Pimmer, C. (2024). Domain-specific embeddings for question-answering systems. FAQs for health coaching. In R. Petrick & C. Geib (Eds.), Proceedings of the AAAI 2024 Spring Symposium Series (Vol. 3, pp. 175–179). Stanford University. https://doi.org/10.1609/aaaiss.v3i1.31197