Paper
27 March 2024 A question answer chatbot using term frequency-inverse document frequency and Markov chain
Shuang Li, Yu Che, Jing Yang, Qianyu Li, Tian Tian
Author Affiliations +
Proceedings Volume 13105, International Conference on Computer Graphics, Artificial Intelligence, and Data Processing (ICCAID 2023); 131053V (2024) https://doi.org/10.1117/12.3026489
Event: 3rd International Conference on Computer Graphics, Artificial Intelligence, and Data Processing (ICCAID 2023), 2023, Qingdao, China
Abstract
The Natural Language Processing has achieved great success theses years, especially in sentiment analysis, text generation, and Human-Machine Interaction. Since the chat generative pretrained transformer developed by OpenAI in November 2022, more chatbots based on Large Language Models have appeared in our life, bring us a more convenient service. This paper we developed a organization self-use chatbot, using the Markov Model and the Term Frequency-Inverse Document Frequency algorithm. We use Term Frequency-Inverse Document Frequency to vectorize user’s question and calculate the text similarity to match answer, use the Markov Model to predict user’s intentions when the question is too short. This kind of chatbot is suitable for some organizations, for it can be trained with less corpus and topics, and it also has a good performance on user guidance and user satisfaction.
(2024) Published by SPIE. Downloading of the abstract is permitted for personal use only.
Shuang Li, Yu Che, Jing Yang, Qianyu Li, and Tian Tian "A question answer chatbot using term frequency-inverse document frequency and Markov chain", Proc. SPIE 13105, International Conference on Computer Graphics, Artificial Intelligence, and Data Processing (ICCAID 2023), 131053V (27 March 2024); https://doi.org/10.1117/12.3026489
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Data modeling

Artificial intelligence

Mathematical modeling

Computer programming

Machine learning

Matrices

Reflection

Back to Top