PDTB Discourse Parsing as a Tagging Task: The Two Taggers Approach

Full discourse parsing in the PDTB framework is a task that has only recently been attempted. We present the Two Taggers approach, which reformulates the discourse parsing task as two simpler tagging tasks: identifying the relation within each sentence, and identifying the relation between each pair of adjacent sentences. We then describe a system that uses two CRFs to achieve an F1 score of 39.33, higher than the only previously existing system, at the full discourse parsing task. Our results show that sequential information is important for discourse relations, especially cross-sentence relations, and that a simple approach to argument span identification is enough to achieve state of the art results. We make our easy to use, easy to extend parser publicly available.