Have you ever read Isaac Asimov’s science fiction novel, I, Robot?
Our goal is to create an artificial brain that is similar to what Asimov introduced in his book. To create this brain, an enormous volume of knowledge and information must be transformed into a format that is readable by a machine. Today, the format called “ontology” is the method that is used the most to transform knowledge and information into a form that can be recognized by a machine.
An ontology used in an artificial brain must not only be huge, but also must change continuously in order to adapt to the changes in the external environment. Therefore, the technology that extracts information from common sentences and expands the ontology becomes crucial.
To extract Information from common sentences, a machine learning method is commonly used. Put simply, the technology extracts information from different sentences by analyzing patterns based on the existing data, which is composed of key information already annotated by humans within the common sentences. This data of key information annotated is called a “corpus” or a “language resource”.