Paper: A Bootstrapping Approach To Unsupervised Detection Of Cue Phrase Variants

ACL ID P06-1116
Title A Bootstrapping Approach To Unsupervised Detection Of Cue Phrase Variants
Venue Annual Meeting of the Association of Computational Linguistics
Session Main Conference
Year 2006
Authors

We investigate the unsupervised detection of semi- xed cue phrases such as This paper proposes a novel approach. .. 1 from unseen text, on the basis of only a handful of seed cue phrases with the de- sired semantics. The problem, in contrast to bootstrapping approaches for Question Answering and Information Extraction, is that it is hard to nd a constraining context for occurrences of semi- xed cue phrases. Our method uses components of the cue phrase itself, rather than external con- text, to bootstrap. It successfully excludes phrases which are different from the tar- get semantics, but which look super cially similar. The method achieves 88% ac- curacy, outperforming standard bootstrap- ping approaches.