• Publications
  • Influence
What You See Is What You Meant: direct knowledge editing with natural language feedback
TLDR
WYSIWYM editing is an alternative solution in which the texts em- ployed to view and edit the knowledge are generated not by the user but by the system; each choice directly updates the knowledge base, from which a new text is then generated. Expand
  • 133
  • 10
  • PDF
Document Structure
TLDR
Abstract document structure can be seen as an extension of Nunberg's text-grammar it is also closely related to logical markup in languages like HTML and LaTEX. Expand
  • 132
  • 9
  • PDF
An integrated framework for text planning and pronominalisation
TLDR
This paper describes an implemented system which uses centering theory for planning of coherent texts and choice of referring expressions. Expand
  • 55
  • 8
  • PDF
Composing Questions through Conceptual Authoring
TLDR
This article describes a method for composing fluent and complex natural language question-answering systems where reliability and transparency are critical, and where users cannot be expected to undergo extensive training in question composition. Expand
  • 92
  • 7
  • PDF
The organisation of purposeful dialogues
TLDR
This paper describes a computer program which models a conversation between two robots. Expand
  • 136
  • 6
Expressing OWL axioms by English sentences: dubious in theory, feasible in practice
With OWL (Web Ontology Language) established as a standard for encoding ontologies on the Semantic Web, interest has begun to focus on the task of verbalising OWL code in controlled English (or otherExpand
  • 45
  • 6
  • PDF
Multilingual Authoring Using Feedback Texts
TLDR
We introduce here a new technique which employs M-NLG during the phase of knowledge editing to produce texts in all of the supported languages, requiring from the author only expertise in the subject-matter, not expertise in knowledge engineering. Expand
  • 132
  • 5
  • PDF
Generation of Referring Expressions: Assessing the Incremental Algorithm
TLDR
A substantial amount of recent work in natural language generation has focused on the generation of ''one-shot'' referring expressions whose only aim is to identify a target referent. Expand
  • 80
  • 5
  • PDF
Implementing a Characterization of Genre for Automatic Genre Identification of Web Pages
TLDR
In this paper, we propose an implementable characterization of genre suitable for automatic genre identification of web pages. Expand
  • 31
  • 5
  • PDF
Planning texts by constraint satisfaction
  • R. Power
  • Computer Science
  • COLING
  • 31 July 2000
TLDR
A method is described by which a rhetorical-structure tree can be realized by a text structure made up of sections, paragraphs, sentences, vertical lists, and other textual patterns, with discourse connectives added (in the correct positions) to mark rhetorical relations. Expand
  • 36
  • 5
  • PDF
...
1
2
3
4
5
...