The Notion of Argument in Prepositional Phrase Attachment
نویسندگان
چکیده
منابع مشابه
The Notion of Argument in Prepositional Phrase Attachment
In this article we refine the formulation of the problem of prepositional phrase (PP) attachment as a four-way disambiguation problem. We argue that, in interpreting PPs, both knowledge about the site of the attachment (the traditional noun–verb attachment distinction) and the nature of the attachment (the distinction of arguments from adjuncts) are needed. We introduce a method to learn argume...
متن کاملPrepositional Phrase Attachment without Oracles
Work on PP attachment resolution generally assumes that there is an oracle that provides the two hypothesized structures that we want to choose between. The information that there are two possible attachment sites and the information about the lexical heads of those phrases is usually extracted from gold standard parse trees. We show that the performance of reattachment methods is higher with s...
متن کاملPrepositional Phrase Attachment and Interlingua
In this paper, we present our work on the classical problem of prepositional phrase attachment. This forms part of an interlingua based machine translation system, in which the semantics of the source language sentences is captured in the form of Universal Networking Language (UNL) expressions. We begin with a thorough linguistic analysis of six common prepositions in English, namely, for, from...
متن کاملThesauruses for Prepositional Phrase Attachment
Probabilistic models have been effective in resolving prepositional phrase attachment ambiguity, but sparse data remains a significant problem. We propose a solution based on similarity-based smoothing, where the probability of new PPs is estimated with information from similar examples generated using a thesaurus. Three thesauruses are compared on this task: two existing generic thesauruses an...
متن کاملPostnominal Prepositional Phrase Attachment in Proteomics
We present a small set of attachment heuristics for postnominal PPs occurring in full-text articles related to enzymes. A detailed analysis of the results suggests their utility for extraction of relations expressed by nominalizations (often with several attached PPs). The system achieves 82% accuracy on a manually annotated test corpus of over 3000 PPs from varied biomedical texts.
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Computational Linguistics
سال: 2006
ISSN: 0891-2017,1530-9312
DOI: 10.1162/coli.2006.32.3.341