Full text discourse parsing relies on texts comprehensively annotated with discourse relations. To this end, we address a significant gap in the inter-sentential discourse relations annotated in the Penn Discourse Treebank (PDTB), namely the class of cross-paragraph implicit relations, which account for 30% of inter-sentential relations in the corpus. We present our annotation study to explore the incidence rate of adjacent vs. non-adjacent implicit relations in cross-paragraph contexts, and the relative degree of difficulty in annotating them. Our experiments show a high incidence of non-adjacent relations that are difficult to annotate reliably, suggesting the practicality of backing off from their annotation to reduce noise for corpus-based studies. Our resulting guidelines follow the PDTB adjacency constraint for implicits while employing an underspecified representation of non-adjacent implicits, and yield 62% inter-annotator agreement on this task.

Penn Discourse Treebank (PDTB)-style annotation focuses on labeling local discourse relations between text spans and typically ignores larger discourse contexts. In this paper we propose two approaches to infer discourse relations in a paragraph-level context from annotated PDTB labels. We investigate the utility of inferring such discourse information using the task of revision classification. Experimental results demonstrate that the inferred information can significantly improve classification performance compared to baselines, not only when PDTB annotation comes from humans but also from automatic parsers.

We present a corpus of spoken dialogues between students and an adaptive Wizard-of-Oz tutoring system, in which student uncertainty was manually annotated in real-time. We detail the corpus contents, including speech files, transcripts, annotations, and log files, and we discuss possible future uses by the computational linguistics community as a novel resource for studying naturally occurring user affect and adaptation in complex spoken dialogue systems.