Word order variation and string similarity algorithm to reduce pattern scripting in pattern matching conversational agents

摘要: This paper presents a novel sentence similarity algorithm designed to mitigate the issue of free word order in Urdu language. Free language poses many challenges when implemented conversational agent, primarily due fact that it increases amount scripting time needed script domain knowledge. A with like means single phrase/utterance can be expressed different ways using same words and still grammatically correct. led research string which was utilized development an agent. The tested through black box testing methodology involved processing variations scripted patterns system gauge performance accuracy regards recognizing related patterns. Initial has highlighted is able recognize legal reduce knowledge base agents significantly. Thus saving great effort