This paper describes a word-clustering scheme for POS-tagging, which is based on
the behaviour of a baseline parser instead of distributional similarity.

It was rejected from ACL-2012 (short papers), with relatively high scores.

I believe the technique is useful.  I believe it would have been accepted eventually.  I do not care.  I am not 
going to submit it again.  I decided to publish it on my webpage + arXiv instead (along with the reviews).

If you found it to be useful also, I'd be nice if you drop me a line and/or cite it as a tech-report.