Modelling metaphor with attribute-based semantics
View / Open Files
Authors
Bulat, L
Clark, Stephen
Shutova, Ekaterina
Publication Date
2017-04-07Journal Title
Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics
Volume
2
Pages
523-528
Language
eng
Type
Article
This Version
VoR
Metadata
Show full item recordCitation
Bulat, L., Clark, S., & Shutova, E. (2017). Modelling metaphor with attribute-based semantics. Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics, 2 523-528. https://doi.org/10.18653/v1/E17-2084
Abstract
One of the key problems in computational metaphor modelling is finding the optimal level of abstraction of semantic representations, such that these are able to capture and generalise metaphorical mechanisms. In this paper we present the first metaphor identification method that uses representations constructed from property norms. Such norms have been previously shown to provide a cognitively plausible representation of concepts in terms of semantic properties. Our results demonstrate that such property-based semantic representations provide a suitable model of cross-domain knowledge projection in metaphors, outperforming standard distributional
models on a metaphor identification task.
Identifiers
External DOI: https://doi.org/10.18653/v1/E17-2084
This record's URL: https://www.repository.cam.ac.uk/handle/1810/266932
Rights
Licence:
http://www.rioxx.net/licenses/all-rights-reserved