Incremental Generation of Plural Descriptions: Similarity and Partitioning
Albert Gatt, Kees van Deemter · OAR@UM (University of Malta) · 2007
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.