Heidelberg System Wins CoNLL 2016 Shared Task on Discourse Relation Sense Disambiguation

Todor Mihaylov and Anette Frank’s submission wins the CoNLL 2016 Shared Task on Discourse Relation Sense Disambiguation. Their approach using cross-argument semantic similarity based on word embeddings obtained best overall results for the English track.

The paper will be presented at the Conference for Natural Language Learning 11-12 August in Berlin, co-located with ACL 2016.

Todor Mihaylov and Anette Frank (2016):
Discourse Relation Sense Classification Using Cross-argument Semantic Similarity Based on Word Embeddings, to appear in: Proceedings of the Twentieth Conference on Computational Natural Language Learning, Berlin, Germany.