Prepositional phrase attachment ambiguity resolution using semantic hierarchies

Nadh, Kailash and Huyck, Christian R. ORCID logoORCID: https://orcid.org/0000-0003-4015-3549 (2009) Prepositional phrase attachment ambiguity resolution using semantic hierarchies. Hamza, M. H., ed. Artificial Intelligence and Applications (AIA 2009). In: 9th IASTED International Conference on Artificial Intelligence and Applications, 17-18 Feb 2009, Innsbruck, Austria. ISBN 9780889867796, e-ISBN 9780889867802. [Conference or Workshop Item]

[img]
Preview
PDF - Published version (with publisher's formatting)
Available under License Creative Commons Attribution-NonCommercial 4.0.

Download (458kB) | Preview

Abstract

This paper describes a system that resolves prepositional phrase attachment ambiguity in English sentence process-ing. This attachment problem is ubiquitous in English text, and is widely known as a place where semantics determines syntactic form. The decision is made based on a four-tuple composed of the head verb of the verb phrase, the head noun of the noun phrase, and the preposition and head noun in the prepositional phrase. A corpus with known results, the Penn Treebank, is used for training and testing purposes. During training, known results are used to build a lattice of hierarchical categories taken from WordNet. These lattices are then compared to the novel lattices derived from the test four-tuples. The results of the system are 90.53% correct attachment decisions.

Item Type: Conference or Workshop Item (Paper)
Keywords (uncontrolled): Prepositional Phrase Attachment, Syntactic and Semantic ambiguity, Semantic Nets, Hierarchies, Parsing, Ambiguity Resolution
Research Areas: A. > School of Science and Technology > Computer and Communications Engineering
Item ID: 2471
Useful Links:
Depositing User: Mr Kailash Nadh
Date Deposited: 30 Jun 2009 10:43
Last Modified: 30 Nov 2022 01:14
URI: https://eprints.mdx.ac.uk/id/eprint/2471

Actions (login required)

View Item View Item

Statistics

Activity Overview
6 month trend
807Downloads
6 month trend
775Hits

Additional statistics are available via IRStats2.