The role of nominalizations in prepositional phrase attachment in GENIA

Authors:
Jonathan Schuman;Sabine Bergler
Affiliations:
Department of Computer Science and Software Engineering, Concordia University, Montreal, Quebec;Department of Computer Science and Software Engineering, Concordia University, Montreal, Quebec
Venue:
Canadian AI'08 Proceedings of the Canadian Society for computational studies of intelligence, 21st conference on Advances in artificial intelligence
Year:
2008

Citing 7
Cited 0

Class-Based Construction of a Verb Lexicon

Proceedings of the Seventeenth National Conference on Artificial Intelligence and Twelfth Conference on Innovative Applications of Artificial Intelligence
The Berkeley FrameNet Project

COLING '98 Proceedings of the 17th international conference on Computational linguistics - Volume 1
The Proposition Bank: An Annotated Corpus of Semantic Roles

Computational Linguistics
The Notion of Argument in Prepositional Phrase Attachment

Computational Linguistics
Evita: a robust event recognizer for QA systems

HLT '05 Proceedings of the conference on Human Language Technology and Empirical Methods in Natural Language Processing
Postnominal prepositional phrase attachment in proteomics

BioNLP '06 Proceedings of the Workshop on Linking Natural Language Processing and Biology: Towards Deeper Biological Literature Analysis
Coverage and inheritance in the preposition project

Prepositions '06 Proceedings of the Third ACL-SIGSEM Workshop on Prepositions

Quantified Score

Hi-index	0.00

Visualization

Abstract

We demonstrate the importance of nominalizations for prepositional phrase attachment for biomedical journal articles. We outline several significant features of the GENIA corpus data and compare them to Wall Street Journal Data. We evaluate a heuristics-based approach to PP attachment based on shallow chunking and domain dependent resources. We conclude that the heuristics based approach performs well, is appropriate for shallow levels of text analysis, and can easily be adapted to or used with other techniques, such as a filter after a statistical parse, or as features in a more complex machine learning environment.