Title: A Question Answering System being able to Infer based on Definition and Acquire of Knowledge in English Text of the Written Language

Year of Publication: Dec - 2015
Page Numbers: 93-99
Authors: Kenta Hiratsuka, Hiroki Imamura
Conference Name: The Second International Conference on Digital Information Processing, Data Mining, and Wireless Communications (DIPDMWC2015)
- United Arab Emirates

Abstract:


In recent years, question answering systems attract attention as one of the new information search technologies. In contrast, we have proposed the new question answering system that can produce new knowledge by the logical inference. The proposed system needs two characteristics that are“The logical inference using the knowledge. ”and“ Dealing with the diversity of the natural language. ”. For the realization of it, in this paper, we construct the question answering processing section that can perform the logical inference in the proposed system. Our system performs inference based on ”knowledge sentence” and ”definition sentence”. Our system can perform a more complicated logical inference by using definition sentences, and performing the inference repeatedly. Thereby, the new knowledge not acquired by only human beings may be produced by logical combination of knowledge. In the future, our system can be expected high usefulness as a system supporting human intellectual activity.