Optimising Text Quality in Generation From Relational Databases

Michael O'Donnell , Alistair Knott, Jon Oberlander, Christopher Mellish

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

Abstract

This paper outlines a text generation system suited to a large class of information sources, relational databases. We focus on one aspect of the problem: the additional information which needs to be specified to produce reasonable text quality when generating from relational databases. We outline how databases need to be prepared, and then describe various types of domain semantics which can be used to improve text quality.
Original languageEnglish
Title of host publicationProceedings of the First International Natural Language Generation Conference
Subtitle of host publicationINLG 2000
PublisherAssociation for Computational Linguistics
Pages133-140
Number of pages8
Publication statusPublished - 2000
EventFirst International Natural Language Generation Conference: INLG 2000 - Ramon Inn, Mitzpe Ramon, Israel
Duration: 12 Jun 200016 Jun 2000

Conference

ConferenceFirst International Natural Language Generation Conference: INLG 2000
CountryIsrael
CityMitzpe Ramon
Period12/06/0016/06/00

Fingerprint

Dive into the research topics of 'Optimising Text Quality in Generation From Relational Databases'. Together they form a unique fingerprint.

Cite this