An Open Architecture for Multi-Domain Information Extraction

This paper presents a multi-domain information extraction system. The overall architecture of the system is detailed. A set of machine learning tools helps the expert to explore the corpus and automatically derive knowledge from this corpus. Thus, the system allows the end-user to rapidly develop a local ontology giving an accurate image of the content of the text, so that the expert can elaborate new extraction templates. The system is finally evaluated using classical indicators.1

• Type: Conference
• Year: 2001
• Where: IAAI
• Authors: Thierry Poibeau
• Keywords: Artificial Intelligence, IAAI 2001, Machine Learning Tools, Multi-domain Information Extraction, Overall Architecture