Attaching Multiple Prepositional Phrases: Generalized Backed-off Estimation

dc.creatorMerlo, Paola
dc.creatorCrocker, Matthew
dc.creatorBerthouzoz, Cathy
dc.date1997-10-16
dc.date.accessioned2026-07-07T02:36:06Z
dc.date.available2026-07-07T02:36:06Z
dc.descriptionThere has recently been considerable interest in the use of lexically-based statistical techniques to resolve prepositional phrase attachments. To our knowledge, however, these investigations have only considered the problem of attaching the first PP, i.e., in a [V NP PP] configuration. In this paper, we consider one technique which has been successfully applied to this problem, backed-off estimation, and demonstrate how it can be extended to deal with the problem of multiple PP attachment. The multiple PP attachment introduces two related problems: sparser data (since multiple PPs are naturally rarer), and greater syntactic ambiguity (more attachment configurations which must be distinguished). We present and algorithm which solves this problem through re-use of the relatively rich data obtained from first PP training, in resolving subsequent PP attachments.
dc.description7 pages, appeared in the EMNLP-2 proceedings
dc.identifierhttps://arxiv.org/abs/cmp-lg/9710005
dc.identifierhttp://arxiv.org/abs/cmp-lg/9710005
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/15795
dc.subjectComputation and Language
dc.titleAttaching Multiple Prepositional Phrases: Generalized Backed-off Estimation
dc.typetext

Files

Collections