The Penn Discourse Treebank (PDTB) was released to the public in 2008 and remains the largest corpus of manually annotated discourse relations — both relations that are signaled explicitly (e.g., by a coordinating or subordinating conjunction, or by a discourse adverbial or other construction) and ones that otherwise appear implicit. The Penn Discourse TreeBank also diverges from other discours...

Computational approaches to discourse understanding have a two-part goal: (1) to identify those aspects of discourse understanding that require process-based accounts, and (2)to characterize the processes and data structures they involve. To date, in the area of reference, process-based accounts have been developed for subsequent reference via anaphoric pronouns and reference via definite descr...

The explicit consideration of an addressee’s inferences during discourse planning affects the content and coherence of the generated discourse. The content of the discourse is affected because the consideration of an addressee’s inferences may require the addition of information that addresses erroneous inferences or suggest the omission of easily inferred information. The coherence of the disc...

The identification of discourse units is an essential step in discourse parsing, the automatic construction of a discourse structure from a text. We present a rule-based algorithm to identify elementary discourse units (EDUs) in Dutch written text. Contrary to approaches that focus on the determination of segment boundaries, we identify complete discourse units, which is especially helpful for ...

Discourse relations bind smaller linguistic units into coherent texts. Automatically identifying discourse relations is difficult, because it requires understanding the semantics of the linked arguments. A more subtle challenge is that it is not enough to represent the meaning of each argument of a discourse relation, because the relation may depend on links between lowerlevel components, such ...

Litman and Allen are concerned with the relationship between plan recognition in discourse and the underlying commonsense structures that are necessary to support the discourse. Building around a train-trip scenario, they demonstrate the importance of commonsense understanding of plans to the ability to analyze a discourse revolving around this plan. In this capacity they make the distinction b...

In the world of linguistics, term “discourse” is often used in many scientific works devoted to study text problems. As V. Hegay rightly points out, although widely linguistics as well fields literature, sociology, political science, philosophy, logic, psychology, itself has a unique, accepted interpretation, meaningless, express variety different concepts.

RASTA (Rhetorical Structure Theory Analyzer), a discourse analysis component within the Microsoft English Grammar, efficiently computes representations of the structure of written discourse using information available in syntactic and logical form analyses. RASTA heuristically scores the rhetorical relations that it hypothesizes, using those scores to guide it in producing more plausible discou...

Text-level discourse parsing is notoriously difficult, as distinctions between discourse relations require subtle semantic judgments that are not easily captured using standard features. In this paper, we present a representation learning approach, in which we transform surface features into a latent space that facilitates RST discourse parsing. By combining the machinery of large-margin transi...

The CoNLL-2015 shared task focuses on shallow discourse parsing, which takes a piece of newswire text as input and returns the discourse relations in a PDTB style. In this paper, we describe our discourse parser that participated in the shared task. We use 9 components to construct the whole parser to identify discourse connectives, label arguments and classify the sense of Explicit or Non-Expl...