PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Prepositional Phrase Attachment in Shallow Parsing
Vincent Van Asch and Walter Daelemans
In: 7th International Conference on Recent Advances in Natural Language Processing, 14-16 Sep 2009, Borovets, Bulgaria.

Abstract

In this paper we extend a shallow parser with prepositional phrase attachment. Although the PP attachment task is a well-studied task in a discriminative learning context, it is mostly ad- dressed in the context of articial situations like the quadruple classication task in which only two possible attachment sites, each time a noun or a verb, are possible. In this pa- per we provide a method to evaluate the task in a more natural situation, making it possible to compare the approach to full statistical pars- ing approaches. First, we show how to extract anchor-pp pairs from parse trees in the GENIA and WSJ treebanks. Next, we discuss the exten- sion of the shallow parser with a PP-attacher. We compare the PP attachment module with a statistical full parsing approach and ana- lyze the results. More specically, we investi- gate the domain adaptation properties of both approaches (in this case domain shifts between journalistic and medical language).

PDF - Requires Adobe Acrobat Reader or other PDF viewer.
EPrint Type:Conference or Workshop Item (Paper)
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Natural Language Processing
ID Code:5691
Deposited By:Vincent Van Asch
Deposited On:08 March 2010