ESpotter: A Domain and User Adaptation Approach for Named Entity Recognition on the Web
Jianhan Zhu

This event took place on 14th June 2004 at 12:30pm (11:30 GMT)
Knowledge Media Institute, Berrill Building, The Open University, Milton Keynes, United Kingdom, MK7 6AA

Named entity recognition (NER) systems are commonly designed with a "one-size-fits-all" philosophy. Lexicons and patterns manually crafted or learned from a training set of documents are applied to any other document without taking into account its background and user needs. However, when applying NER to Web pages, due to the diversity of these Web pages and user needs, one size frequently does not fit all. In this talk, I present a system called ESpotter, which improves NER on the Web by adapting lexicons and patterns to domains on the Web and user preferences. My results show that ESpotteqr provides more accurate and efficient NER on Web pages from various domains than current NER systems. ESpotter is implemented as a browser plug-in to help solve the information overload problem on the Web by discovering relevant information on user's behalf. Further work of integrating ESpotter with ontology based semantic browsing tool, Magpie, and the KMi semantic Web site are explored.

Download PowerPoint Presentation (755 KB ZIP file)

The webcast was open to 50 users

Click below to play the event (50 minutes)

Creative Commons Licence KMi logo