Modelling metaphor with attribute-based semantics

Luana Bulat, Stephen Clark, Ekaterina Shutova


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.
Anthology ID:
E17-2084
Volume:
Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 2, Short Papers
Month:
April
Year:
2017
Address:
Valencia, Spain
Editors:
Mirella Lapata, Phil Blunsom, Alexander Koller
Venue:
EACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
523–528
Language:
URL:
https://aclanthology.org/E17-2084
DOI:
Bibkey:
Cite (ACL):
Luana Bulat, Stephen Clark, and Ekaterina Shutova. 2017. Modelling metaphor with attribute-based semantics. In Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 2, Short Papers, pages 523–528, Valencia, Spain. Association for Computational Linguistics.
Cite (Informal):
Modelling metaphor with attribute-based semantics (Bulat et al., EACL 2017)
Copy Citation:
PDF:
https://aclanthology.org/E17-2084.pdf