Previous researches on Text-level discourse parsing mainly made use of constituency structure to parse the whole document into one discourse tree. In this paper, we present the limitations of constituency based discourse parsing and first propose to use dependency structure to directly represent the relations between elementary discourse units (EDUs). The state-of-the-art dependency parsing tec...

Despite showing an overtly simple structure, the semantic process in classic literary-narrative discourse conforms to complicated semiotic systems. As a result, semio-semantics is deemed as one of the most scientific, reliable tools since it helps intradiscursive semio-textual propositions be phenomenologically, and even epistemologically, analyzed. Consequently, the narrative discourse in “The...

This paper is about the flow of inference between communicative intentions, discourse structure and the domain during discourse processing. We augment a theory of discourse interpretation with a theory of distinct mental attitudes and reasoning about them, in order to provide an account of how the attitudes interact with reasoning about discourse structure.

It is much harder to say how meaning depends on context to pinpoint the various contextual factors that affect the meanings of different expressions and to spell out in detail how those expressions are affected by them. For one thing such analyses require explicit characterisations of ''context''. In many discussions of the context-dependence of language such a characterisation has been lacking...

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...

We are compiling a corpus of Dutch texts annotated with discourse structure and lexical cohesion, containing initially 80 texts from expository and persuasive genres. We are using this resource for corpus-based studies of discourse relations, discourse markers, cohesion, and genre differences. We are also exploring the possibilities of automatic text segmentation and semi-automatic discourse an...

Discourse markers are complex discontinuous linguistic expressions which are used to explicitly signal the discourse structure of a text. This paper describes efforts to improve an automatic tagging system which identifies and classifies discourse markers in Chinese texts by applying machine learning (ML) to the disambiguation of discourse markers, as an integral part of automatic text summariz...

Identifying the regularity of middle level discourse is useful for annotating discourse structure in long monologues. A convincing way to find segments is described on the middle level of discourse structure (sub-story), based on a committee-based decision of discourse purposes and a detection of transitive expressions.

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...

We present analyses aimed at eliciting which specific aspects of discourse provide the strongest indication for text importance. In the context of content selection for single document summarization of news, we examine the benefits of both the graph structure of text provided by discourse relations and the semantic sense of these relations. We find that structure information is the most robust ...