burr settles. Ph.D. Candidate, Computer Sciences Armadillo Enthusiast 6775 Medical Sciences Center 1300 University Avenue Madison, Wisconsin 53706 bsettles@cs.wisc.edu 608-265-6868 | vox 608-265-7916 | fax

research interests.

Machine learning, natural language processing, and bioinformatics. In particular, efficient active learning and multiple-instance learning approaches to facilitate real-world applications in information extraction, information retrieval, and data mining from social and biological networks.

I expect to defend my Ph.D. in December 2008. My advisor is Mark Craven

software & data.

AMIL: Active Multiple-Instance Library. An open-source framework for multiple-instance (MI) learning, and MI active learning in particular.

ABNER: A Biomedical Named Entity Recognizer. An open-source information extraction tool which identifies proteins and other entities of biomedical significance from free text using a linear-chain conditional random field (CRF). ABNER works stand-alone or as a Java API.

publications.

• An Analysis of Active Learning Strategies for Sequence Labeling Tasks.
  B. Settles & M. Craven.
  Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP), to appear. ACL Press, 2008.
• A Software Tool for Biomedical Information Extraction (and Beyond).
  B. Settles.
  V. Prince & M. Roche (Eds.), Information Retrieval in Biomedicine: Natural Language Processing for Knowledge Integration, to appear. IGI Global Press, 2008.
• Multiple-Instance Active Learning.
  B. Settles, M. Craven, & S. Ray.
  Advances in Neural Information Processing Systems (NIPS), 20, 1289-1296. MIT Press, 2008.
• Ranking Biomedical Passages for Relevance and Diversity.
  A. Goldberg, D. Andrzejewski, J. Van Gael, B. Settles, X. Zhu & M. Craven.
  Proceedings of the Fifteenth Text Retrieval Conference (TREC). 2007.
• Classifying Biomedical Articles by Making Localized Decisions.
  T. Brow, B. Settles & M. Craven (2006).
  Proceedings of the Fourteenth Text Retrieval Conference (TREC). 2006.
• ABNER: An Open Source Tool for Automatically Tagging Genes, Proteins, and Other Entity Names in Text.
  B. Settles.
  Bioinformatics, 21(14):3191-3192. 2005.
• Exploiting Zone Information, Syntactic Features, and Informative Terms in Gene Ontology Annotation from Biomedical Documents.
  B. Settles & M. Craven.
  Proceedings of the Thirteenth Text Retrieval Conference (TREC). 2005.
• Biomedical Named Entity Recognition Using Conditional Random Fields and Rich Feature Sets.
  B. Settles.
  Proceedings of the International Joint Workshop on Natural Language Processing in Biomedicine and Its Applications (NLPBA), 104-107. 2004.

Click here for related work and citations...

teaching.

In Summer 2008, I am teaching the Computational Biology & Biostatistics course for UW-Madison's ISB Summer Research Program.

In Summer 2003, I taught CS 540: Artificial Intelligence.

From 2000-2002, I served as teaching assistant for several courses including Compilers, Computer Architecture, Java Programming, and Computer Graphics & Web Design.

miscellany.

I have a separate, personal website at burrsettles.com.

I am a co-founder of FAWM.ORG, an online community for musicians of all stripes, and annual songwriting challenge (to write 14 new songs each February). I am an avid musician myself, proficient at several instruments and known to tour and perform internationally when time allows.

Misellaneous "webtoys" that use simple statistical NLP in fun ways:

• Shakespearian Insult Generator
• Babblefisch
• Polyglot

I am also a big fan of wordplay, especially anagrams.
(Alas, adorable clownery is iffy. A gag's appal, mon ami!)