The DCU Discourse Parser for Connective, Argument Identification and Explicit Sense Classification

This paper describes our submission to the CoNLL-2015 shared task on discourse parsing. We factor the pipeline into subcomponents which are then used to form the final sequential architecture. Focusing on achieving good performance when inferring explicit discourse relations, we apply maximum entropy and recurrent neural networks to different sub-tasks such as connective identification, argument extraction, and sense classification. The our final system achieves 16.51%, 12.73% and 11.15% overall F1 scores on the dev, WSJ and blind test sets, respectively.