A shallow discourse parsing system based on maximum entropy model

Abstract

This paper describes our system for Shallow Discourse Parsing - the CoNLL 2015 Shared Task. We regard this as a classification task and build a cascaded system based on Maximum Entropy to identify the discourse connective, the spans of two arguments and the sense of the discourse connective. We trained the cascaded models with a variety of features such as lexical and syntactic features. We also report the results achieved by our team.