Year: 2014
Type: conference-paper
Abstract: This paper outlines the development of UMAIR an Urdu conversational agent developed as a customer service representative. UMAIRs architecture includes a novel engine, scripting language and WOW (Word Order Wizard) string similarity algorithm which are combined to tackle the language unique challenges of Urdu. Initial testing of the new architecture has yielded positive results towards UMAIR being able to cope with the inherent differences in the Urdu language such as word order.
Authors: Mohammed Kaleem, James O’Shea, Keeley Crockett
Language: English
Topic: Speech and dialogue systems
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W2184456630