Changes for the tagger


Version 0.3.1 (2012-10-23)

* Fixed crashing and hanging issues


Version 0.3 (2012-09-21)

* 40 times faster: completely new implementation

* More accurate: improvements to many features, including much better
  unsupervised word clusters

* Trained on more data: new annotated data released as well, with linguistic
  fixes too


Pseudo-0.2.1

This was never formally released, but the 'master' branch on
github.com/brendano/ark-tweetnlp, at some point after the 0.2 release, had a
performance (speedup) improvement (but no change to the actual model).


Version 0.2

* The tokenizer has been improved and integrated with the tagger in a single
  Java program.

* The new tokenizer was run on the 1,827 tweets used for the annotation effort

* and the  annotations were adapted for tweets with differing tokenizations.

* The revised annotations are contained in a companion v0.2 release of the

* data (twpos-data-v0.2).

* The tagging model is trained on ALL of the available annotated data in
  twpos-data-v0.2.  The model in v0.1 was only trained on the training set. 

* The tokenizer/tagger is integrated with Twitter's text commons annotations API.


Version 0.1

* First release
