The CLaC discourse parser at CoNLL-2016

Abstract

This paper describes our submission (CLaC) to the CoNLL-2016 shared task on shallow discourse parsing. We used two complementary approaches for the task. A standard machine learning approach for the parsing of explicit relations, and a deep learning approach for non-explicit relations. Overall, our parser achieves an F1score of 0.2106 on the identification of discourse relations (0.3110 for explicit relations and 0.1219 for non-explicit relations) on the blind CoNLL-2016 test set.