About
ESpotter was a domain and user-adaptive named entity recognition (NER) system designed to improve the accuracy of NER on web pages by customising lexicons and patterns to fit specific domains and user preferences. Developed by Dr. Jianhan Zhu, Dr. Victoria Uren, and Prof. Enrico Motta, it functioned as a browser plug-in aimed at mitigating information overload by identifying relevant entities. ESpotter was integrated with tools like Magpie and could be customised and extended using a .NET framework for further development
Team
Dr. Jianhan Zhu
Dr. Victoria Uren
Prof. Enrico Motta
Talks
KMi Internal Talk: (June 14th 2005)
ESpotter: A Domain and User Adaptation Approach for Named Entity Recognition on the Web
Abstract: 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 ESpotter 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.
Keywords: Named entity recognition, information extraction, hierarchies.
Papers
Jianhan Zhu, Victoria Uren, and Enrico Motta. ESpotter: Adaptive Named Entity Recognition for Web Browsing. To appear in Proc. of Workshop on IT Tools for Knowledge Management Systems at WM2005 Conference, Kaiserslautern, Germany, April 11-13, 2005.
Demos:
Jianhan Zhu, Victoria Uren, and Enrico Motta. ESpotter: A Prototype System for Adaptive Named Entity Recognition Supporting Web Browsing. The Fifteenth ACM Conference on Hypertext and Hypermedia (Hypertext’04), Santa Cruz, USA, August 9-13, 2004.
Jianhan Zhu, Victoria Uren, and Enrico Motta. ESpotter: A Prototype System for Adaptive Named Entity Recognition Supporting Web Browsing. The Fourteenth International Conference on Knowledge Engineering and Knowledge Management (EKAW’2004), Whittlebury Hall, Northamptonshire, UK, October 5-8, 2004.
