BAILANDO Projects: Lindi
Lindi Text Data Mining ProjectNote: This project has been superceded by the BioText project.
We are developing a text data mining system, Lindi, for Linking Information for Novel Discoveries and Insight. The main goal is to help automated discovery of new information from large text collections. As a step towards the goal of text mining, we are developing empirical algorithms for semantic analysis of natural language text.
An article on text data mining ideas at Mappa Mundi Magazine.
For an introduction to the the ideas behind LINDI, see:
Untangling Text Data Mining , Marti Hearst in the Proceedings of ACL'99: the 37th Annual Meeting of the Association for Computational Linguistics, University of Maryland, June 20-26, 1999 (invited paper). html
The Descent of Hierarchy, and Selection in Relational Semantics ACL-02, July, 2002. ppt
Interfaces for Intense Information Analysis, IBM Workshop on The User Experience of Business Intelligence and Knowledge Management, March 2002. (ppt)
Classifying the Semantic Relations in Noun Compounds via a Domain-Specific Lexical Hierarchy EMNLP '01 (ppt)
Text Data Mining: Issues, Techniques, and the Relation to Information Access (html) for the UW/MS workshop on data mining, July 1997.
See also the Text Data Mining Seminar from Fall 1999.