Ordering among premodifiers
James Shaw, Vasileios Hatzivassiloglou · 1999
We present a corpus-based study of the sequential ordering among premodifiers in noun phrases. This information is important for the fluency of generated text in practical applications. We propose and evaluate three approaches to identify sequential order among premodifiers: direct evidence, transitive closure, and clustering. Our implemented system can make over 94% of such ordering decisions correctly, as evaluated on a large, previously unseen test corpus.