Reliable Discourse Markers for Contrast Relations

Using the RST annotated corpus (Carlson et al., 2003), we use simple statistics on the distribution of discourse markers or cue phrases as evidence of the three-way distinction of Contrast relations, Contrast, Antithesis and Concession, recognized in standard Rhetorical Structure Theory (RST, Mann & Thompson 1987). We also show that however, an intuitive marker of Contrast, is not actually used statistically signi cantly more often in Contrast relations than in CauseE ect relations. These results highlight the need for empirically based discourse marker identi cation rather than the intuitive method that is the current norm.