Identifying Justifications in Written Dialogs

Abstract

In written dialog, discourse participants need to justify claims they make, to convince the reader the claim is true and/or relevant to the discourse. This paper presents a new task (with an associated corpus), namely detecting such justifications. We investigate the nature of such justifications, and observe that the justifications themselves often contain discourse structure. We therefore develop a method to detect the existence of certain types of discourse relations, which helps us classify whether a segment is a justification or not. Our task is novel, and our work is novel in that it uses a large set of connectives (which we call indicators), and in that it uses a large set of discourse relations, without choosing among them.