Dr Dayne Freitag

Biography and Interests

• Machine learning for information extraction, including named entity recognition and relation/event extraction from free text, and Web extraction (unsupervised discovery of structure, semi-structured extraction, automated navigation).
• Advanced information retrieval through information extraction and enhanced query languages.
• Supervised and unsupervised learning for NLP, including induction of syntax, word sense discovery, automated lexicon construction.
• Natural language semantics and controlled languages, particularly with application to information retrieval.

Publications

The following are in reverse chronological order of publication.
Showing most recent 5 out of 24 [View All]

• Farber B., Freitag D., Habash N., Rambow O. Improving NER in Arabic using a morphological tagger, in Proceedings of LREC 08, 2008.  [Details]

• Freitag D., Khadivi S. A sequence alignment model based on the averaged perceptron, in Proceedings of EMNLP 07, 2007.  [Details]

• Freitag D., Blume M., Byrnes J., Chow E., Kapadia S., Rohwer R., Wang Z. New experiments in distributional representations of synonymy, in Proceedings of CoNLL 05, 2005.  [Details]

• Freitag D. Morphology induction from term clusters, in Proceedings of CoNLL 05, 2005.  [Details]

• Freitag D. Toward Unsupervised Whole-Corpus Tagging, in Proceedings of Coling 2004, 2004.  [Details]