Synonymy and semantic classification
Synonymy and semantic classification
Semantic interpretation and the resolution of ambiguity
Semantic interpretation and the resolution of ambiguity
Proceedings of the 1992 ACM/IEEE conference on Supercomputing
Computational Linguistics
Building a large-scale knowledge base for machine translation
AAAI '94 Proceedings of the twelfth national conference on Artificial intelligence (vol. 1)
The grammar of sense: Using part-of-speech tags as a first step in semantic disambiguation
Natural Language Engineering
Error driven word sense disambiguation
COLING '98 Proceedings of the 17th international conference on Computational linguistics - Volume 1
Unsupervised word sense disambiguation rivaling supervised methods
ACL '95 Proceedings of the 33rd annual meeting on Association for Computational Linguistics
Word-sense disambiguation using decomposable models
ACL '94 Proceedings of the 32nd annual meeting on Association for Computational Linguistics
Knowledge sources for word sense disambiguation of biomedical text
BioNLP '08 Proceedings of the Workshop on Current Trends in Biomedical Natural Language Processing
Hi-index | 0.00 |
The paper contrasts three approaches to the extension of lexical sense: what we shall call, respectively, lexical tuning; another based on lexical closeness and relaxation; and a third known as underspecification, or the use of lexical rules. These approaches have quite different origins in artificial intelligence(AI) and linguistics, and involve corpus input, lexicons and knowledge bases in quite different ways. Moreover, the types of sense extension they claim to deal with in their principal examples are actually quite different. The purpose of these contrasts in the paper is the possibility of evaluating their differing claims by means of the current markup and test paradigm that has been recently successful in the closely related task of word sense discrimination (WSD). The key question in the paper is what the relationship of sense extension to WSD is, and its conclusion is that, at the moment, not all types of sense extension heuristic can be evaluated within the current paradigm requiring markup and test.