DKPro TC An Open Source text classification Java framework based on the Apache UIMA Framework
Download

DKPro TC Ranking & Summary

DKPro TC Tags

DKPro TC Description

DKPro TC is an open source and completely free text classification framework written in the Java programming language, based on the Apache UIMA Framework, and built on top of Weka Machine Learning Toolkit, DKPro Core, and DKPro Lab. It is designed especially to mitigate supervised machine learning experiments that implicates any type of textual data. DKPro TC features a fetting-started example code that can be used for standard text collections, such as the Reuters-21578 Text Categorization corpus, in Groovy and Java; numerous generic feature extractors, such as POS-tags and n-grams; convenient parameter optimization functionality; extensive reporting, supporting lots of standard performance measures; support for pair-wise document classification; support for single-label and multi-label classification.

DKPro TC Related Software