A Conversational Agent Framework using Semantic Analysis

This paper focuses on the implementation of a novel semantic-based Conversational Agent (CA) framework. Traditional CAs interpret scripts consisting of structural patterns of sentences. User input is matched against such patterns and an associated response is sent as output. This traditional CA approach, which solely takes into account the structural form of a sentence, requires the scripter to anticipate the inordinate ways that a user may send input. This is a tiresome and timeconsuming process. As such, a semantic-based CA that interprets scripts consisting of natural language sentences alleviates this burden by removing the process of pattern generation. The CA was evaluated by participants using a domain of a specific nature, that is, student debt management, which indicated promising results.