met*: a method for discriminating metonymy and metaphor by computer
Computational Linguistics
Understanding metonymies in discourse
Artificial Intelligence
A statistical approach to the processing of metonymy
COLING '00 Proceedings of the 18th conference on Computational linguistics - Volume 2
Syntactic features and word similarity for supervised metonymy resolution
ACL '03 Proceedings of the 41st Annual Meeting on Association for Computational Linguistics - Volume 1
Metonymy resolution as a classification task
EMNLP '02 Proceedings of the ACL-02 conference on Empirical methods in natural language processing - Volume 10
Metonymy as a cross-lingual phenomenon
LexFig '03 Proceedings of the ACL 2003 workshop on Lexicon and figurative language - Volume 14
SemEval-2007 task 08: metonymy resolution at SemEval-2007
SemEval '07 Proceedings of the 4th International Workshop on Semantic Evaluations
Combining collocations, lexical and encyclopedic knowledge for metonymy resolution
EMNLP '09 Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing: Volume 2 - Volume 2
Resolution of modifier-head relation gaps using automatically extracted metonymic expressions
IJCNLP'04 Proceedings of the First international joint conference on Natural Language Processing
| Hi-index | 0.00 |
In this article we outline a basic approach to treating metonymy properly in a multilingual machine translation system. This is the first attempt at treating metonymy in an machine translation environment. The approach is guided by the differences of acceptability of metonymy which were obtained by our comparative survey among three languages, English, Chinese, and Japanese. The characteristics of the approach are as follows:(1)Influences of the context, individuals, and familiality with metonymy are not used.(2) An actual acceptability of each metonymic expression is not realized directly.(3) Grouping metonymic examples into patterns is determined by the acceptability judgement of the speakers surveyed as well as the analysts' intuition.(4) The analysis and generation components treat metonymy differently using the patterns.(5) The analysis component accepts a wider range of metonymy than the actual results of the survey, and the generation component treats metonymy more strictly than the actual results.We think that the approach is a starting point for more sophisticated approaches to translation in a multilingual machine translation environment.