Associate Professor, School of Computing
Ph.D., University of
Massachusetts at Amherst, 1994
Professor Riloff
joined the faculty in 1994. Her research interests are in natural
language processing, machine learning, and artificial intelligence.
She is particularly interested in techniques for automatically
generating dictionaries and knowledge bases for natural language
processing. Most of her work revolves around the task of
information extraction, which involves extracting information from
text. The NLP research group at Utah has built its own NLP system
called Sundance, which is a partial parser that activates and
instantiates case frames for information extraction. Current research
projects include bootstrapping techniques for learning extraction
patterns, corpus-based techniques for learning semantic dictionaries,
and corpus-based methods for coreference resolution.
- Riloff, E. and Jones, R., ``Learning Dictionaries for
Information Extraction by Multi-Level Bootstrapping,'' in
Proceedings of the Sixteenth National Conference on Artificial
Intelligence (AAAI-99). 1999.
- Bean, D. and Riloff, E., ``Corpus-Based Identification of
Non-Referential Noun Phrases,'' in Proceedings of the 37th Annual
Meeting of the Association for Computational Linguistics
(ACL-99). 1999.
- Riloff, E. ``Information Extraction as a Stepping Stone toward Story
Understanding,'' in Computational Models of Reading and
Understanding. The MIT Press. 1999.
- Riloff, E. and Shepherd, J., ``A Corpus-Based Approach for
Building Semantic Lexicons,'' in Proceedings of the Second
Conference on Empirical Methods in Natural Language Processing. 1997.
- Riloff, E.,
``Automatically Generating Extraction Patterns from Untagged Text,''
in Proceedings of the Thirteenth National Conference on
Artificial Intelligence (AAAI-96). 1996.