Using the web to obtain frequencies for unseen bigrams
Computational Linguistics - Special issue on web as corpus
Evaluating sense disambiguation across diverse parameter spaces
Natural Language Engineering
Choosing the word most typical in context using a lexical co-occurrence network
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
Word association norms, mutual information, and lexicography
ACL '89 Proceedings of the 27th annual meeting on Association for Computational Linguistics
The computation of word associations: comparing syntagmatic and paradigmatic approaches
COLING '02 Proceedings of the 19th international conference on Computational linguistics - Volume 1
Fast computation of lexical affinity models
COLING '04 Proceedings of the 20th international conference on Computational Linguistics
Robust utilization of context in word sense disambiguation
CONTEXT'05 Proceedings of the 5th international conference on Modeling and Using Context
EMNLP '09 Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing: Volume 2 - Volume 2
Expectation vectors: a semiotics inspired approach to geometric lexical-semantic representation
GEMS '10 Proceedings of the 2010 Workshop on GEometrical Models of Natural Language Semantics
Compositional expectation: a purely distributional model of compositional semantics
IWCS '11 Proceedings of the Ninth International Conference on Computational Semantics
Hi-index | 0.00 |
We introduce an alternative approach to extracting word pair associations from corpora, based purely on surface distances in the text. We contrast it with the prevailing window-based co-occurrence model and show it to be more statistically robust and to disclose a broader selection of significant associative relationships - owing largely to the property of scale-independence. In the process we provide insights into the limiting characteristics of window-based methods which complement the sometimes conflicting application-oriented literature in this area.