Paper: Incremental Generation of Plural Descriptions: Similarity and Partitioning

ACL ID D07-1011
Title Incremental Generation of Plural Descriptions: Similarity and Partitioning
Venue Conference on Empirical Methods in Natural Language Processing
Session Main Conference
Year 2007
Authors

Approaches to plural reference generation emphasise descriptive brevity, but often lack empirical backing. This paper describes a corpus-based study of plural descrip- tions, and proposes a psycholinguistically- motivated algorithm for plural reference generation. The descriptive strategy is based on partitioning and incorporates corpus- derived heuristics. An exhaustive evaluation shows that the output closely matches hu- man data.