A Hybrid Text Classification Approach for Chatbots

Chatbots are preferred in many fields due to their ability to provide fast and uninterrupted customer service at all hours. Most chatbots work by classifying input text and responding accordingly. In this work, a hybrid chatbot app-roach is presented by combining a commercial system and a deep learn...

Full description

Saved in:
Bibliographic Details
Published in2023 31st Signal Processing and Communications Applications Conference (SIU) pp. 1 - 4
Main Authors Karaahmetoglu, Atilla, Yigitoglu, Ugur, Vardarli, Elif, Unal, Erdem, Aydin, Ugur, Koras, Murat, Gonen, Mehmet, Akgun, Baris
Format Conference Proceeding
LanguageEnglish
Turkish
Published IEEE 05.07.2023
Subjects
Chatbots
Long short term memory
natural language processing
Robots
Signal processing
Text categorization
Transformers
Online AccessGet full text

Cover

More Information
Summary:Chatbots are preferred in many fields due to their ability to provide fast and uninterrupted customer service at all hours. Most chatbots work by classifying input text and responding accordingly. In this work, a hybrid chatbot app-roach is presented by combining a commercial system and a deep learning-based text classification model. Additionally, active learning-based label correction and data expansion approaches are used to increase chatbot performance and keep it up-to-date. In offline tests, the hybrid method made three times fewer errors than the methods it was composed of. Online evaluations performed after deployment show that the hybrid method was able to preserve its superiority and that keeping the dataset up-to-date had positive contributions.
DOI:10.1109/SIU59756.2023.10223933