Selection restrictions acquisition for parsing improvement

Authors:
Alexandre Agustini;Pablo Gamallo;Gabriel P. Lopes
Affiliations:
CENTRIA, Departamento de Informática Universidade Nova de Lisboa, Portgual;CENTRIA, Departamento de Informática Universidade Nova de Lisboa, Portgual;CENTRIA, Departamento de Informática Universidade Nova de Lisboa, Portgual
Venue:
INAP'01 Proceedings of the Applications of prolog 14th international conference on Web knowledge management and decision support
Year:
2001

Citing 12
Cited 1

Evaluation techniques for automatic semantic extraction: comparing syntactic and window based approaches

Corpus processing for lexical acquisition
Similarity-Based Models of Word Cooccurrence Probabilities

Machine Learning - Special issue on natural language learning
Explorations in Automatic Thesaurus Discovery

Explorations in Automatic Thesaurus Discovery
Tagging with Small Training Corpora

IDA '01 Proceedings of the 4th International Conference on Advances in Intelligent Data Analysis
Structural ambiguity and lexical relations

Computational Linguistics - Special issue on using large corpora: I
From grammar to lexicon: unsupervised learning of lexical syntax

Computational Linguistics - Special issue on using large corpora: II
Automatic extraction of subcategorization from corpora

ANLC '97 Proceedings of the fifth conference on Applied natural language processing
On learning more appropriate Selectional Restrictions

EACL '95 Proceedings of the seventh conference on European chapter of the Association for Computational Linguistics
Automatic retrieval and clustering of similar words

COLING '98 Proceedings of the 17th international conference on Computational linguistics - Volume 2
Distributional clustering of English words

ACL '93 Proceedings of the 31st annual meeting on Association for Computational Linguistics
Generalizing automatically generated selectional patterns

COLING '94 Proceedings of the 15th conference on Computational linguistics - Volume 2
A rule-based approach to prepositional phrase attachment disambiguation

COLING '94 Proceedings of the 15th conference on Computational linguistics - Volume 2

Ontology learning from text: A look back and into the future

ACM Computing Surveys (CSUR)

Quantified Score

Hi-index	0.00

Visualization

Abstract

Partially parsed corpora is used for automatically extracting semantic and syntactic subcategorization information for words, helping to cluster them according to their sense which is highly restricted by the syntactic contexts where words do occur. In this paper we propose the use of a parsing platform, based on chart parsing and tabling, in order to check if the syntactic and semantic information extracted automatically leads to better parses than assuming that words do not subcategorize anything.