Building Natural Language Understanding System from User Manual to Execute Office Application Functions

To improve the flexibility of using office applications, it takes a natural language interface that can execute the office application's functions. To achieve this, the office application must have an inference engine that can automatically detect the intents and the entities contained in an instruction, into an algorithm to execute the related functions in the application on the entities. Creating a natural language understanding system by manually listing various rules in a knowledge base, is very inefficient and makes the effort of using natural language to execute office application functions too expensive. The author proposes conducting research to build a natural language understanding system more efficient, by analyzing the text contained in the office application user manual, by means of natural language processing technology. We propose to build a variety of simple rules automatically, using the text in the user manual, which is specifically crafted to facilitate and support natural language processing technology. In future works, research will be conducted to automatically build various complicated rules, from analysis of the text from common and commercially available user manual. In this preliminary study, the necessary steps to execute the application functions, is executed on an office application prototype specifically built for this study.