In this paper we study the utility of discourse structure for spoken dialogue performance modeling. We experiment with various ways of exploiting the discourse structure: in isolation, as context information for other factors (correctness and certainty) and through trajectories in the discourse structure hierarchy. Our correlation and PARADISE results show that, while the discourse structure is...

A central but still unsettled question in formal theories about discourse interpretation is: What are the key theoretical structures on which discourse interpretation should depend? If we take our cue from theories that analyze the meanings of individual sentences, the meaning of the discourse's parts should determine the meaning of the whole; some sort principle of compositionality of meaning ...

Previous work on discourse parsing has mostly relied on surface syntactic and lexical features; the use of semantics is limited to shallow semantics. The goal of this thesis is to exploit event semantics in order to build discourse parse trees (DPT) based on informational rhetorical relations. Our work employs an Inductive Logic Programming (ILP) based rhetorical relation classifier, a Neural N...

This paper proposes a computational system of narrative discourse generation and its implementation. In the system, Genette’s discourse theory is reconstructed as discourse techniques which transform the tree structure for a story into discourse structures. Also, we introduce Jauss’s reception theory to construct the control mechanism, which continues discourse generation through generation cyc...

This paper argues for a novel data structure for the representation of discourse referents. A so-called hashing list is employed to store discourse referents according to their grammatical features. The account proposed combines insights from several theories of discourse comprehension. Segmented Discourse Representation Theory (Asher, 1993) is enriched by the ranking system developed in center...

In this paper we investigate how discourse structure a ects the meanings of words and how the meanings of words a ect discourse structure We integrate three ingredients a theory of discourse structure called sdrt which represents discourse in terms of rhetorical relations that glue together the propositions introduced by the text segments an accom panying theory of discourse attachment called d...

OBJECTIVE Relation extraction in biomedical text mining systems has largely focused on identifying clause-level relations, but increasing sophistication demands the recognition of relations at discourse level. A first step in identifying discourse relations involves the detection of discourse connectives: words or phrases used in text to express discourse relations. In this study supervised mac...

In example (1), a sentence from a Wall Street Journal article taken from the Penn TreeBank corpus is further segmented into four EDUs, (1a), (1b), (1c) and (1d) (RST, 2002). Discourse segmentation, clearly, is not as easy as sentence boundary detection. The lack of consensus with regards to what constitutes an elementary discourse unit adds to the difficulty. Building a rule based discourse seg...

The paper addresses the relation between several dimensions along which discourse has been assumed to be structured – topical structure, hierarchical structure, QUD-structure and thematic structure – and points at previously undescribed mismatches between those. BACKGROUND ASSUMPTIONS: As discourse progresses, the aboutness topic of a sentence (Reinhart, 1981; Roberts, 2011; Krifka, 2007) may r...