CRF++ 0.53

CRF++ is a simple and customizable implementation of Conditional Random Fields (CRFs) for segmenting/labeling sequential data.

CRF++ is designed for generic purpose and will be applied to a variety of NLP tasks, such as Named Entity Recognition, Information Extraction and Text Chunking.

Here are some key features of "CRF++":

· Can redefine feature sets
· Written in C++ with STL
· Fast training based on LBFGS, a quasi-newton algorithm for large scale numerical optimization problem
· Less memory usage both in training and testing
· encoding/decoding in practical time
· Can perform n-best outputs
· Can perform single-best MIRA training
· Can output marginal probabilities for all candidates
· Available as an open source software

What`s New in This Release: [ read full changelog ]

· fixed build failure on libtool