Ontology-Based Interactive Information Extraction

Abstract

Interactive Information Extraction brings together search and 
information extraction to provide fast, interactive text mining over 
large volumes of text such as Medline abstracts, full text scientific 
articles, patents etc. As well as covering the two ends of the spectrum: 
keyword search over documents, and detailed linguistic patterns within 
sentences, the Interactive Information Extraction System, I2E, also 
covers the points in between such as keywords within the same sentence, 
or co-occurrence of biological entities within sentences or documents. 
This talk briefly introduces the idea of Interactive Information 
Extraction, and describes how terminologies/ontologies are incorporated. 
We also show how I2E can be used to augment ontologies by finding 
potential synonyms or members of classes from the literature using 
linguistic patterns. Finally we discuss issues concerning how best to 
use ontologies for text mining.