Template-Driven Information Extraction for Populating Ontologies

We address the integration of information extraction (IE) and ontologies. In particular, using an ontology to aid the IE process, and using the IE results to help populate the ontology. We perform IE by means of domain specific templates and the lightweight use of Natural Languages Processing techniques (NLP).

Our main goal is to learn information from text by the use of templates and in this way to alleviate the main bottleneck in creating knowledge-base systems that is ``the extraction of knowledge''.

Our domain of study is ``KMi Planet'', a Web-based news server that helps to communicate relevant information between members in our institute [Domingue and Scott, 1999]. The raw input consists of e-mailed stories written by members of the laboratory. The main goals of our system are to classify the story, obtain the relevant objects within the story, deduce the

relationships between them, and to populate the ontology. Furthermore, we aim to do this with minimal help from the user.

Publication(s)

Submitted to the IJCAI'01 Workshop on Ontology Learning (OL-2001), Seattle, USA, August 4, 2001.