GNOME: Generating Nominal Expressions




Overview

This project focussed on the specific task of generating nominal expressions within a text. This is an area where achievements in NLG appear to lag behind those in parsing and interpretation; for instance there are well-known algorithms in the literature for resolving pronouns as part of the interpretation of texts, but these results have not been systematically applied to the generation task. Additionally, work on the generation of nominals has not profited much from theoretical research in formal semantics and psycholinguistics on the meaning, interpretation and production of nominal expressions.

In the GNOME project, we developed general algorithms which were informed by corpus analysis and results of psycholinguistic studies on how people produce and understand nominal expressions.

The resulting algorithms were implemented in the ICONOCLAST project and HCRC's ILEX system.

Duration The project started in January 1998 and ran for two years.

Financial Support This project was funded by the UK Engineering and Physical Sciences Research Council in a joint project to Donia Scott and Massimo Poesio.

Participants People involved in the project were:

Hua Cheng Kees van Deemter Renate Henschel Rodger Kibble
Jamie Pearson Massimo Poesio Donia Scott Rosemary Stevenson

Publications Conference/workshop papers
Technical reports and other documents
GNOME corpus information and annotation manual

Events Workshop on Generating Nominal Expressions at ESSLLI'99 in Utrecht, August 9-13 1999, organised by Kees van Deemter and Rodger Kibble.