The Univ. of Tokyo > The Center for Knowledge Structuring > Kotaro Nakayama
English / Japanese

Projects

Wikipedia Mining

Wikipedia, a collaborative wiki-based encyclopedia, has become a huge phenomenon on the WWW. As a corpus for knowledge extraction, it has various impressive characteristics such as a huge amount of articles, live updates, a dense link structure, brief link texts and URL identification for concepts. We unveiled these characteristics in detail, then we proposed an efficient link mining method lfibf (Link Frequency - Inversed Backward link Frequency) and the extension method "forward / backward link weighting (FB weighting)." The thesaurus, named Wikipedia thesaurus, is available on the WWW. Further information can be found in Wikipedia-lab.org, the Web site of the special interest group of Wikipedia Mining.


Docterra

According to a study in Colorado and Utah, at least 44,000 Americans die each year as a result of medical errors (1997). In addition, the results of a New York Study assume the number is estimated as high as 98,000. Our goal was to develop a solution that enables information exchange between doctors and patients and which is cost-effective as well as easy-to-use and provides high-mobility. Our system gDocterrah consists of 4 modules: Docterra Web, Docterra Mobile, Docterra Next and Docterra AR. See docterra project page for more detail.


3D-Raven

high-quality 3D graphics still remain beyond the computational capability of mobile device because of limitations of CPU, memory, battery life, and so on. Our innovative technology, named "3D-Raven" - a 3D framework for Pocket PC - enables a mobile device to render high-quality 3D graphics: showing textures, radiosity rendering, and other special effects. This framework has realized powerful performance with the greal-time server-side renderingh approach. See 3D-Raven project page for more detail.


GeoNote.net

GeoNote is a semantic web enabled social network system (Currently it's for geographical information). GeoNote enables users to share geographic information such as good restaurants and hospitals. It allows users to import the social network from existing friends network like MSN Messenger. See GeoNote project page for more detail.


Smart Explorer

Under construction

MSN Chatbot

Under construction