Experiments for CoNLL 2016 Supplementary Task (shallow discourse sense classification) involving deep intermediate/layer-wise multi-task learning using shared representations and bidirectional GRU layers in Keras.

Note: Unfortunately this does NOT work yet, but development will continue!

• http://www.cs.brandeis.edu/~clp/conll16st/
• http://github.com/attapol/conll16st/
• http://github.com/gw0/conll16st-v20-multi-classifier/

If you find anything useful, consider citing a related conference paper:

• http://gw.tnode.com/deep-learning/acl2015-learning-representations-for-text-level-discourse-parsing/

Copyright © 2016 gw0 [http://gw.tnode.com/] <gw.2016@tnode.com>

This code is licensed under the GNU Affero General Public License 3.0+ (AGPL-3.0+). Note that it is mandatory to make all modifications and complete source code publicly available to any user.