Multi-Paradigm and Multi-Lingual Information Extraction as Support for Medical Web Labelling Authorities
Until recently, quality labelling of medical web content has been a pre-dominantly manual activity. However, the advances in automated text processing opened the way to computerised support of this activity. The core enabling technology is information extraction (IE). However, the heterogeneity of w...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Czech Society of Systems Integration
2010-10-01
|
| Series: | Journal of Systems Integration |
| Subjects: | |
| Online Access: | http://si-journal.org/index.php/JSI/article/viewFile/73/44 |
| Summary: | Until recently, quality labelling of medical web content has been a pre-dominantly manual activity. However, the advances in automated text processing opened the way to computerised support of this activity. The core enabling technology is information extraction (IE). However, the heterogeneity of websites offering medical content imposes particular requirements on the IE techniques to be applied. In the paper we discuss these requirements and describe a multi-paradigm approach to IE addressing them. Experiments on multi-lingual data are reported. The research has been carried out within the EU MedIEQ project. |
|---|---|
| ISSN: | 1804-2724 |