Incremental generation of plural descriptions: Similarity and partitioning

Albert Gatt, Kees Van Deemter

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

7 Citations (Scopus)

Abstract

Approaches to plural reference generation emphasise descriptive brevity, but often lack empirical backing. This paper describes a corpus-based study of plural descriptions, and proposes a psycholinguisticallymotivated algorithm for plural reference generation. The descriptive strategy is based on partitioning and incorporates corpusderived heuristics. An exhaustive evaluation shows that the output closely matches human data.
Original languageEnglish
Title of host publicationProceedings of the Conference on Empirical Methods in Natural Language Processing, EMNLP-CoNLL
Number of pages10
Publication statusPublished - 2007
EventConference on Empirical Methods in Natural Language Processing (EMNLP-CoNLL 2007) - Prague, Czech Republic
Duration: 28 Jun 200730 Jun 2007

Conference

ConferenceConference on Empirical Methods in Natural Language Processing (EMNLP-CoNLL 2007)
CountryCzech Republic
CityPrague
Period28/06/0730/06/07

Keywords

  • natural language generation
  • generation of referring expressions
  • plurals
  • partitioning

Fingerprint Dive into the research topics of 'Incremental generation of plural descriptions: Similarity and partitioning'. Together they form a unique fingerprint.

  • Cite this

    Gatt, A., & Van Deemter, K. (2007). Incremental generation of plural descriptions: Similarity and partitioning. In Proceedings of the Conference on Empirical Methods in Natural Language Processing, EMNLP-CoNLL http://www.csd.abdn.ac.uk/~kvdeemte/emnlp2007.pdf