Nigel COLLIER

# Doctoral Degrees:1996, Ph.D. (UMIST, UK)
# Research Fields:Natural Language Processing, Machine Learning, Information Extraction


Web surveillance for public health risk management:
Suppose a serious public health crisis occurs in Japan, or somewhere else in the world. What's the most effective way to minimize the risk (risk management) of problems caused by the crisis? The first course of action is to identify the crisis and take all possible response measures. To do this successfully, it's important to obtain accurate information on the crisis as quickly as possible.

Developing a system to prevent the spread of communicable diseases:
If an infectious disease outbreak occurs somewhere in the world, one of the most important things to do at the initial stage of risk management is finding a way to allow national governments and medical specialists to get accurate and correct information as quickly as possible. In the past, information was acquired by manual efforts including monitoring local news broadcasts in the region where the disease broke out. But due to several factors, including language differences and the massive volume of news, this isn't an especially efficient way to collect information. A project called BioCaster was initiated in 2006 to reduce this problem.

BioCaster aims to automatically scan news in the regions or countries where the outbreak of a disease is reported and produces a brief summary of the incident in various languages. This allows public health workers around the world to find out about the outbreaks of dangerous diseases in real-time. To start, the system is scheduled to provide information in four languages, English, Japanese, Vietnamese, and Thai.

Creating a medical information infrastructure based on BioCaster:
Several current systems scan public health information on the Web, but they all have drawbacks-limited language compatibility or lack of ease of use. The basic technologies for solving these problems are being developed in BioCaster. Some of the benefits of the research can be seen on our website (http://biocaster.nii.ac.jp) including the global health monitor for mapping disease and a searchable ontology.

In addition to obtaining information on disease outbreaks, we also aim to provide intelligent links to biomedical journals into the system to give medical specialists easy access to the latest in research information.

My field of expertise is natural language processing, but I've been studying text mining (text data analysis methods) since participating in the University of Tokyo's GENIA project in 1998. The goal of the GENIA project was to develop a system that automatically analyzes and retrieves research results from the Web to reduce the significant delays in getting biomedical research results into databases. Text mining technologies can be applied to various fields and offer great potential for helping professional workers find specific information more efficiently. Implementing these technologies will require the mutual efforts of experts from various fields.