An Analysis of the Dialogic Complexities in Designing a Question/Answering Based Conversational Agent for Preschoolers

摘要

Parents are well aware that pre-school children are incessantly inquisitive, and the high ratio of questions to statements suggests that questions are a primary method utilized by children for language acquisition, cognitive development, and formulating knowledge structures. Question-asking is furthermore a comfortable medium for a child to stay engaged in natural discourse and the activity at hand. To take advantage of the naturalness and learning benefits of question-answer exchanges, there could be intelligent agents that can engage a child in activities while setting children in the mood to ask meaningful, information-seeking questions. There are currently multiple intelligent agents that can interact with older children and adults to promote literacy or teach topics in specific domains. This paper thus focuses on the complexities of designing an intelligent agent for younger children, by collecting and analyzing data and categorizing children's questions, which are often ill-formed.