Evaluating algorithms for the generation of referring expressions: going beyond toy domains

Ielka van der Sluis* (Corresponding Author), Albert Gatt, Kees van Deemter

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingPublished conference contribution

Abstract

We describe a corpus-based evaluation methodology, applied to a number of classic algorithms in the generation of referring expressions. Following up on earlier work involving very simple domains, this paper deals with the issues associated with domains that contain ‘real-life’ objects of some complexity. Results indicate that state of the art algorithms perform very differently when applied to a complex domain. Moreover, if a version of the Incremental Algorithm is used then it becomes of huge importance to select a good preference order. These results should contribute to a growing debate on the evaluation of nlg systems, arguing in favour of carefully constructed balanced and semantically transparent corpora.
Original languageEnglish
Title of host publicationProceedings of Recent Advances in Natural Language Processing International Conference 2007
EditorsGalia Angelova, Kalina Bontcheva, Ruslan Mitkov, Nicolas Nicolov, Nicolai Nikolov
Place of PublicationBorovets, Bulgaria
PublisherRANLP
Pages541-547
Number of pages7
ISBN (Electronic)978-954-91743-7-3
Publication statusPublished - 2007
Event Recent Advances in Language Processing International Conference 2007 - Borovets, Russian Federation
Duration: 27 Sep 200729 Sep 2007
https://lml.bas.bg/ranlp2007/

Conference

Conference Recent Advances in Language Processing International Conference 2007
Abbreviated titleRANLP 2007
Country/TerritoryRussian Federation
CityBorovets
Period27/09/0729/09/07
Internet address

Keywords

  • generation of referring expressions
  • corpus-based evaluation of algorithms
  • Natural Language Generation

Fingerprint

Dive into the research topics of 'Evaluating algorithms for the generation of referring expressions: going beyond toy domains'. Together they form a unique fingerprint.

Cite this