Research of Information Extraction and Visualization from Ancient Documents

为了实现对古代文献信息的提取与可视化研究，我需要实现以下三个过程；1)古日语句子分词；2)古文献知识获取；3)知识可视化。在本研究中，我针对这三个过程提出了方法，并取得了一定的效果。虽然由于分词精度不够，本文使用的是手工提取古代文献中人物的结果，但本研究给出了一个从古代文献中提取信息和可视化的方法示例。因此我实现了利用计算机获取古籍知识的辅助系统。

I have to realize following three processes in order to achieve research of information extraction and visualization from ancient documents; 1) Word segmentation for archaic Japanese sentence, 2) Knowledge acquisition from ancient documents, and 3) Visualization of obtained knowledge.In this research, I proposed methods for these three processes, and achieved certain result. This research has given an example of the way of information extraction and visualization from ancient documents, although I used the result of manually extraction for peoples in ancient documents because of insufficient precision of word segmentation. Therefore I realized the supporting system for obtaining knowledge from ancient documents using computers.