Discourse Relation Sense Classification with Two-Step Classifiers

Discourse Relation Sense Classification is the classification task of assigning a sense to discourse relations, and is a part of the series of tasks in discourse parsing. This paper analyzes the characteristics of the data we work with and describes the system we submitted to the CoNLL2016 Shared Task. Our system uses two sets of two-step classifiers for Explicit and AltLex relations and Implicit and EntRel relations, respectively. Regardless of the simplicity of the implementation, it achieves competitive performance using minimalistic features. The submitted version of our system ranked 8th with an overall F1 score of 0.5188. The evaluation on the test dataset achieved the best performance for Explicit relations with an F1 score of 0.9022.