Typographic Error Identification and Correction in Chatbot Using N-gram Overlapping Approach

Citation

Muthu Anbananthen, Kalaiarasi Sonai and Kannan, Subarmaniam and Muhammad Azman Busst, Mikail and Muthaiyah, Saravanan and Lurudusamy, Saravanan Nathan (2022) Typographic Error Identification and Correction in Chatbot Using N-gram Overlapping Approach. Journal of System and Management Sciences, 12 (5). pp. 91-104. ISSN 1816-6075, 1818-0523

[img] Text
86.pdf - Published Version
Restricted to Repository staff only

Download (557kB)

Abstract

The high demand in the business sector and Artificial Intelligence (AI) capability have led to the development of chat robots, or in short, chatbots. A chatbot interacts through instant messaging, artificially replicating the patterns of human interaction. It is a computer program or virtual agent that allows humans and machines to freely converse using Natural Language Processing (NLP). People may input their queries with various typographical errors when interacting with a chatbot. The typographical errors include misspelt words or using abbreviated words. The primary drawback of most existing chatbots is that they can only handle questions with correct sentences. Natural language processing alone is insufficient for detecting typographical problems in input queries. Although the typographical error checker has become one of the most commonly used features in many applications and programs, including web applications, crawlers, and web browsers, in chatbots, especially in "Manglish", it still does not exist. Therefore, this research aims to enable chatbots to respond to queries correctly even with typographical errors using an embedding model of the N-gram overlapping with a rule-based algorithm.

Item Type: Article
Uncontrolled Keywords: Chatbots, n-gram overlapping, Manglish, typographical-error
Subjects: Q Science > QA Mathematics > QA71-90 Instruments and machines > QA75.5-76.95 Electronic computers. Computer science
Divisions: Faculty of Information Science and Technology (FIST)
Faculty of Management (FOM)
Depositing User: Ms Nurul Iqtiani Ahmad
Date Deposited: 30 Nov 2022 04:42
Last Modified: 30 Nov 2022 04:42
URII: http://shdl.mmu.edu.my/id/eprint/10871

Downloads

Downloads per month over past year

View ItemEdit (login required)