Witte, R., "{An Integration Architecture for User-Centric Document Creation, Retrieval, and Analysis}", Proceedings of the VLDB Workshop on Information Integration on the Web (IIWeb'04), Toronto, Canada, pp. 141–144, August 30, 2004.

Baker, C. J. O., and R. Witte, "{Enriching Protein Structure Visualizations with Mutation Annotations Obtained by Text Mining Protein Engineering Literature}", The 3rd Canadian Working Conference on Computational Biology (CCCB'04), Markham, Ontario, Canada, October 4, 2004.

Baker, C. J. O., and R. Witte, "{Mutation Miner – Textual Annotation of Protein Structures}", 5th CERMM Annual Symposium, Concordia University, Montréal, Québec, Canada, Centre for Research in Molecular Modeling, pp. 29, February 11–13, 2005.

Witte, R., and C. J. O. Baker, "{Combining Biological Databases and Text Mining to support New Bioinformatics Applications}", Natural Language Processing and Information Systems: 10th International Conference on Applications of Natural Language to Information Systems (NLDB 2005), vol. 3513, Alicante, Spain, Springer-Verlag, pp. 310–321, June 15–17, 2005.

Witte, R., Q. Li, Y. Zhang, and J. Rilling, "{Ontological Text Mining of Software Documents}", NLDB, vol. 4592, CNAM, Paris, France, Springer, pp. 168–180, June 27–29, 2007.

Witte, R., and N. Papadakis, "{Semantic Assistants: SOA for Text Mining}", CASCON 2009 Technical Showcase, Markham, Ontario, Canada, November 2–9, 2009.

Naderi, N., and R. Witte, "{Ontology-Based Extraction and Summarization of Protein Mutation Impact Information}", Proceedings of the 2010 Workshop on Biomedical Natural Language Processing (BioNLP 2010), Uppsala, Sweden, Association for Computational Linguistics (ACL), pp. 128--129, July 15, 2010.

PAX is a GATE component for extracting predicate-argument structures (PAS) from the output of different parsers.

Semantic Assistants support users in content retrieval, analysis, and development, by offering context-sensitive NLP services directly integrated in standard desktop clients, like a word processor. They are implemented through an open service-oriented architecture, using Semantic Web ontologies and W3C Web Services.

The growing number of publicly available information sources makes it impossible for individuals to keep track of all the various opinions on one topic. The goal of our fuzzy believer system presented in this paper is to extract and analyze statements of opinion from newspaper articles.

Beliefs are modeled using a fuzzy-theoretic approach applied after NLP-based information extraction. A fuzzy believer models a human agent, deciding what statements to believe or reject based on different, configurable strategies.