Gary Underwood's starred repositories
etude-engine
ETUDE (Evaluation Tool for Unstructured Data and Extractions) is a Python-based tool that provides consistent evaluation options across a range of annotation schemata and corpus formats
etude-viewer
A visual representation of some reference document vs. a target document
brown-cluster
Java implementation of the brown clustering algorithm that clusters words based on their contexts in a text corpus.
tan-clustering
Hierarchical word clustering, following "Brown clustering" (Brown et al., 1992)