We describe our experience in developing a discourse-annotated corpus for community-wide use. Working in the framework of Rhetorical Structure Theory, we were able to create a large annotated resource with very high consistency, using a well-defined methodology and protocol. This resource is made publicly available through the Linguistic Data Consortium to enable researchers to develop empirica...

In this paper, we describe novel methods for topic segmentation based on patterns of discourse organization. Using a corpus of news texts, our results show that it is possible to use discourse features (based on Rhetorical Structure Theory) for topic segmentation and that we outperform some well-known methods.

In the last decade, members of the computational linguistics community have adopted a perspective on discourse based primarily on either Rhetorical Structure Theory or Grosz and Sidner’s Theory. However, only recently, researchers have started to investigate the relationship between the two perspectives. In this paper, we use Moser and Moore’s (1996) work as a departure point for extending Marc...

In the last decade, members of the computational linguistics community have adopted a perspective on discourse based primarily on either Rhetorical Structure Theory or Grosz and Sidner’s Theory. However, only recently, researchers have started to investigate the relationship between the two perspectives. In this paper, we use Moser and Moore’s [1996] work as a departure point for extending our ...

This paper explores the use of a simple and computational optimality theoretic pragmatics (OT pragmatics, OTP) to the analysis of the rhetorical structure of texts. It introduces this variant of OTP briefly and then shows that it can be applied to explain coherence, rhetorical relations, discourse trees and context dependence using the occasional extra premiss. It thereby improves on existing a...

This paper presents a message planner, TraumaGEN, that draws on rhetorical structure and discourse theory to address the problem of producing integrated messages from individual critiques, each of which is designed to achieve its own communicative goal. TraumaGEN takes into account the purpose of the messages, the situation in which the messages will be received, and the social role of the system.

Observation of writers producingg non-trivial texts suggests t hat most spendd time generating andd organisingg content prior to draftingg full text. Resear chsuggests a linkk between time spent inn these activities andd the quality of the resulting docume nt. Very little is known, however, about either the nature of the representation that is c reatedd during this planningg phase (the writer's...

Logic-based controlled natural languages usually provide some facility for compositional representation, minimally including sentence level coordination and sometimes subordination. Although these compositional forms suffice for representing short passages, they can become unwieldy for expressing entire paragraphs and documents. This paper describes an approach to representing larger composite ...

This paper offers a semantic theory of uses of now in which now refers to a time introduced in discourse. I argue that the interpretation of an anaphoric use of now is determined by the rhetorical structure of the discourse in which the token of now figures.