A Generation Framework for Grammar Development

Shashi Narayan, Claire Gardent

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

We developed a general framework for the development of a symbolic (hand-written) feature-based lexicalised tree-adjoining grammar (FB-LTAG). We choose natural language generation, surface realisation in particular, to question the capabilities of the grammar in terms of both accuracy and robustness. Our framework combines an optimised surface realiser with efficient error mining techniques. While generating from a large data set provided by the Generation Challenge Surface Realisation task, we improve both accuracy and robustness of our grammar significantly.
Original languageEnglish
Title of host publication1st International Data-to-Text Workshop
Number of pages4
Publication statusPublished - 6 Mar 2015
Event1st International Data-to-Text Workshop - Edinburgh, United Kingdom
Duration: 6 Mar 2015 → …

Workshop

Workshop1st International Data-to-Text Workshop
CountryUnited Kingdom
CityEdinburgh
Period6/03/15 → …

Cite this