Extraction of Information From Public Health Emergency Web Documents

DOI

10.2991/amcce-15.2015.136How to use a DOI?

Keywords

information extraction; named entity recognition; public health; hidden Markov model; web document

Abstract

Globalization and economic growth have brought more and more uncertain factors that would lead to the occurrence of public health emergencies, which greatly threaten people’s lives and properties. The occurrence of a public health emergency is often accompanied by the appearance of a huge amount of related documents on the Internet, and these documents carry a lot of important information. To extract such information, which are usually stored in the form of plain texts (unstructured documents) and cannot be reused directly, it is crucial to automate the extraction process. This work proposed a method for the recognition of named entities with H7N9 public health emergency-related web documents as the research subject, using Hidden Markov Models. The experimental results showed that the proposed method could effectively extract time, location and symptom information.

Copyright

© 2015, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Li Wang
AU  - Yuanpeng Zhang
AU  - Danmin Qian
AU  - Min Yao
PY  - 2015/04
DA  - 2015/04
TI  - Extraction of Information From Public Health Emergency Web Documents
BT  - Proceedings of the 2015 International Conference on Automation, Mechanical Control and Computational Engineering
PB  - Atlantis Press
SP  - 1215
EP  - 1220
SN  - 1951-6851
UR  - https://doi.org/10.2991/amcce-15.2015.136
DO  - 10.2991/amcce-15.2015.136
ID  - Wang2015/04
ER  -