In closed-domain (or restricted-domain) question answering systems, the first step that a system must perform is to transform an input question into an intermediate representation. Most published works so far use rule-based approaches to realize this transformation in question answering systems. Nevertheless, in existing rule-based approaches, manually creating the rules is error-prone and expensive in time and effort. Therefore, we propose a FrameScript language-based approach that offers an intuitive way to create compact rules for extracting intermediate representation of input questions. Our approach achieves reasonable performance and it is straightforward to adapt to new domains.
More importantly, we introduce a Vietnamese text-based conversational agent architecture using FrameScript language on specific knowledge domain. In order to deal with an user input that our question answering system fails to provide an answer, our conversational agent can communicate with users to provide more additional information. Experimental results are promising where our Vietnamese text-based conversational agent achieves positive feedback in an investigation about the university academic regulation domain.