JINSECT 1.0

george giannakopoulos — Thu, 25 Feb 2010 19:03:06 -0000

The JINSECT toolkit is a Java-based toolkit and library that supports and demonstrates the use of n-gram graphs within Natural Language Processing applications, ranging from summarization and summary evaluation to text classi?cation and indexing.

It provides: - implementation of the AutoSummENG method for summary evaluation - implementation of a language neutral multi-document summarizer - an efficient set of representations and algorithms based on the n-gram graphs for documents - a set of storage abstractions for storage - several utility classes implementing statistical functions (e.g., entropy, moments) and structures (e.g., distribution) - a set of (more than) proof-of-concept applications for the use of n-gram graphs including text classification, text clustering, string normality detection, and others

For support, do not hesitate to contact me at ggiannaATiitDOTdemokritosDOTgr.

mloss.org JINSECT

JINSECT 1.0