Google Code-in

1. Update the program URL: https://svn.code.sf.net/p/apertium/svn/trunk/apertium-tools/detectAnaphoraNPs.py

To use streamparser https://github.com/goavki/streamparser to process the input.

1. Make it parse -biltrans output instead of -tagger output

2. Test it on a large corpus (~ 100k tokens)

3. Get it to print out the stream following the instructions here: http://wiki.apertium.org/wiki/Anaphora_resolution