C
Chris Mellish
Researcher at University of Aberdeen
Publications - 162
Citations - 6859
Chris Mellish is an academic researcher from University of Aberdeen. The author has contributed to research in topics: Natural language generation & Natural language. The author has an hindex of 38, co-authored 162 publications receiving 6660 citations. Previous affiliations of Chris Mellish include University of Sussex & University of Edinburgh.
Papers
More filters
Journal ArticleDOI
Modelling human tutors' feedback to inform natural language interfaces for learning
TL;DR: A computational model of tutorial feedback selection based on the context of the immediate situation for which the feedback is selected as well as on politeness considerations shown to be of importance to increasing pedagogical efficacy of computer assisted learning is presented.
Proceedings ArticleDOI
A Representation for Complex and Evolving Data Dependencies in Generation
Chris Mellish,Roger Evans,Lynne Cahill,Christine Doran,Daniel Paiva,Mike Reape,Donia Scott,N Tipper +7 more
TL;DR: This paper introduces an approach to representing the kinds of information that components in a natural language generation (NLG) system will need to communicate to one another and makes a proposal for organising intermodule communication in an NLG system by having a central server for this information.
Proceedings Article
Content Selection From Semantic Web Data
TL;DR: This paper outlines the idea and plan for the execution of an initial challenge on content selection from Semantic Web data, and proposes a general model for this task.
Proceedings Article
Using a Corpus of Sentence Orderings Defined by Many Experts to Evaluate Metrics of Coherence for Text Structuring
TL;DR: This paper addresses two previously unresolved issues in the automatic evaluation of Text Structuring in Natural Language Generation by describing how to verify the generality of an existing collection of sentence orderings defined by one domain expert using data provided by additional experts.
Journal ArticleDOI
Exploring Mixed-Initiative Dialogue Using Computer Dialogue Simulation
TL;DR: It is shown that with easy problems, the efficiency of mixed-initiative dialogue is a little better than or equal to that of non-mixed initiative dialogue, while with difficult problems mixed-Initiative Dialogue is less efficient than non-Mixed- initiative dialogue.