Corpus-based Customization for an Ontology

Software · Tue Sep 14 00:00:00 EDT 2010

OSTI ID:1231400

CCAT scans a corpus of text for terms, and computes lexical similarity between corpus terms and taxonomy terms. Based on a set of metrics and a learning algorithm, the system inserts corpus terms into the taxonomy. Conversely, terms from the taxonomy are disambiguated based on the text in the corpus. Unused terms are discarded, and infrequently used senses of terms are collapsed to make the taxonomy more manageable.

• Short Name / Acronym: CCAT; 002596MLTPL00
• Site Accession Number: LLNL-CODE-462893
• Version: 00
• Programming Language(s): Medium: X; OS: Linux; windows (1.6JMV); Compatibility: Multiplatform
• Research Organization: Lawrence Livermore National Laboratory (LLNL), Livermore, CA (United States)
• Sponsoring Organization: USDOE
• Contributing Organization: K. Stevens, D. Buttler, T. Cottom
• DOE Contract Number: DE-AC52-07NA27344
• OSTI ID: 1231400
• Country of Origin: United States