Attaching Multiple Prepositional Phrases: Generalized Backed-off Estimation
| dc.creator | Merlo, Paola | |
| dc.creator | Crocker, Matthew | |
| dc.creator | Berthouzoz, Cathy | |
| dc.date | 1997-10-16 | |
| dc.date.accessioned | 2026-07-07T02:36:06Z | |
| dc.date.available | 2026-07-07T02:36:06Z | |
| dc.description | There 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.description | 7 pages, appeared in the EMNLP-2 proceedings | |
| dc.identifier | https://arxiv.org/abs/cmp-lg/9710005 | |
| dc.identifier | http://arxiv.org/abs/cmp-lg/9710005 | |
| dc.identifier.uri | http://salesiana.dossiersoluciones.com/handle/123456789/15795 | |
| dc.subject | Computation and Language | |
| dc.title | Attaching Multiple Prepositional Phrases: Generalized Backed-off Estimation | |
| dc.type | text |