Learning to Order Facts for Discourse Planning in Natural Language Generation

Simple item page
dc.creatorDimitromanolaki, Aggeliki
dc.creatorAndroutsopoulos, Ion
dc.date2003-06-13
dc.date.accessioned2026-07-07T03:19:51Z
dc.date.available2026-07-07T03:19:51Z
dc.descriptionThis paper presents a machine learning approach to discourse planning in natural language generation. More specifically, we address the problem of learning the most natural ordering of facts in discourse plans for a specific domain. We discuss our methodology and how it was instantiated using two different machine learning algorithms. A quantitative evaluation performed in the domain of museum exhibit descriptions indicates that our approach performs significantly better than manually constructed ordering rules. Being retrainable, the resulting planners can be ported easily to other similar domains, without requiring language technology expertise.
dc.description8 pages, 4 figures, 1 table
dc.identifierhttps://arxiv.org/abs/cs/0306062
dc.identifierhttp://arxiv.org/abs/cs/0306062
dc.identifierProceedings of EACL 2003 Workshop on Natural Language Generation
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/31626
dc.subjectComputation and Language
dc.subjectH.5.2
dc.titleLearning to Order Facts for Discourse Planning in Natural Language Generation
dc.typetext

Files

Collections

arXiv