Choosing the word most typical in context using a lexical co-occurrence network

Authors:
Philip Edmonds
Affiliations:
University of Toronto, Toronto, Canada
Venue:
ACL '98 Proceedings of the 35th Annual Meeting of the Association for Computational Linguistics and Eighth Conference of the European Chapter of the Association for Computational Linguistics
Year:
1997

Citing 6
Cited 23

Using argumentation to control lexical choice: a functional unification implementation

Using argumentation to control lexical choice: a functional unification implementation
Similarity-based Word Sense Disambiguation

Similarity-based Word Sense Disambiguation
Lexical semantics and knowledge representation in multilingual sentence generation

Lexical semantics and knowledge representation in multilingual sentence generation
Integrating multiple knowledge sources to disambiguate word sense: an exemplar-based approach

ACL '96 Proceedings of the 34th annual meeting on Association for Computational Linguistics
Combining Trigram-based and feature-based methods for context-sensitive spelling correction

ACL '96 Proceedings of the 34th annual meeting on Association for Computational Linguistics
Word-sense disambiguation using statistical models of Roget's categories trained on large corpora

COLING '92 Proceedings of the 14th conference on Computational linguistics - Volume 2

Near-synonymy and lexical choice

Computational Linguistics
Target word selection as proximity in semantic space

ACL '98 Proceedings of the 36th Annual Meeting of the Association for Computational Linguistics and 17th International Conference on Computational Linguistics - Volume 2
Suregen-2: a shell system for the generation of clinical documents

EACL '03 Proceedings of the tenth conference on European chapter of the Association for Computational Linguistics - Volume 2
A framework for understanding latent semantic indexing (LSI) performance

Information Processing and Management: an International Journal - Special issue: Formal methods for information retrieval
A statistical model for near-synonym choice

ACM Transactions on Speech and Language Processing (TSLP)
Acquiring Word Similarities with Higher Order Association Mining

ICCBR '07 Proceedings of the 7th international conference on Case-Based Reasoning: Case-Based Reasoning Research and Development
Co-dispersion: a windowless approach to lexical association

EACL '09 Proceedings of the 12th Conference of the European Chapter of the Association for Computational Linguistics
A graph-theoretic model of lexical syntactic acquisition

EMNLP '08 Proceedings of the Conference on Empirical Methods in Natural Language Processing
Leveraging Higher Order Dependencies between Features for Text Classification

ECML PKDD '09 Proceedings of the European Conference on Machine Learning and Knowledge Discovery in Databases: Part I
HIT: web based scoring method for English lexical substitution

SemEval '07 Proceedings of the 4th International Workshop on Semantic Evaluations
Combining syntactic co-occurrences and nearest neighbours in distributional methods to remedy data sparseness

UMSLLS '09 Proceedings of the Workshop on Unsupervised and Minimally Supervised Learning of Lexical Semantics
Unified linear subspace approach to semantic analysis

Journal of the American Society for Information Science and Technology
A higher order collective classifier for detecting andclassifying network events

ISI'09 Proceedings of the 2009 IEEE international conference on Intelligence and security informatics
A framework for understanding Latent Semantic Indexing (LSI) performance

Information Processing and Management: an International Journal - Special issue: Formal methods for information retrieval
Understanding latent semantic indexing: A topological structure analysis using Q-analysis

Journal of the American Society for Information Science and Technology
Aspect presence verification conditional on other aspects

Proceedings of the 33rd international ACM SIGIR conference on Research and development in information retrieval
Corpus-based semantic class mining: distributional vs. pattern-based approaches

COLING '10 Proceedings of the 23rd International Conference on Computational Linguistics
Near-synonym lexical choice in latent semantic space

COLING '10 Proceedings of the 23rd International Conference on Computational Linguistics
Discriminative training for near-synonym substitution

COLING '10 Proceedings of the 23rd International Conference on Computational Linguistics
Exploiting syntactic and distributional information for spelling correction with web-scale n-gram models

EMNLP '11 Proceedings of the Conference on Empirical Methods in Natural Language Processing
Exploring extensive linguistic feature sets in near-synonym lexical choice

CICLing'12 Proceedings of the 13th international conference on Computational Linguistics and Intelligent Text Processing - Volume Part II
Creating a system for lexical substitutions from scratch using crowdsourcing

Language Resources and Evaluation
Independent component analysis for near-synonym choice

Decision Support Systems

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper presents a partial solution to a component of the problem of lexical choice: choosing the synonym most typical, or expected, in context. We apply a new statistical approach to representing the context of a word through lexical co-occurrence networks. The implementation was trained and evaluated on a large corpus, and results show that the inclusion of second-order co-occurrence relations improves the performance of our implemented lexical choice program.