Contextual Modulation for Relation-Level Metaphor Identification

Omnia Zayed, John P. McCrae, Paul Buitelaar


Abstract
Identifying metaphors in text is very challenging and requires comprehending the underlying comparison. The automation of this cognitive process has gained wide attention lately. However, the majority of existing approaches concentrate on word-level identification by treating the task as either single-word classification or sequential labelling without explicitly modelling the interaction between the metaphor components. On the other hand, while existing relation-level approaches implicitly model this interaction, they ignore the context where the metaphor occurs. In this work, we address these limitations by introducing a novel architecture for identifying relation-level metaphoric expressions of certain grammatical relations based on contextual modulation. In a methodology inspired by works in visual reasoning, our approach is based on conditioning the neural network computation on the deep contextualised features of the candidate expressions using feature-wise linear modulation. We demonstrate that the proposed architecture achieves state-of-the-art results on benchmark datasets. The proposed methodology is generic and could be applied to other textual classification problems that benefit from contextual interaction.
Anthology ID:
2020.findings-emnlp.36
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2020
Month:
November
Year:
2020
Address:
Online
Editors:
Trevor Cohn, Yulan He, Yang Liu
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
388–406
Language:
URL:
https://aclanthology.org/2020.findings-emnlp.36
DOI:
10.18653/v1/2020.findings-emnlp.36
Bibkey:
Cite (ACL):
Omnia Zayed, John P. McCrae, and Paul Buitelaar. 2020. Contextual Modulation for Relation-Level Metaphor Identification. In Findings of the Association for Computational Linguistics: EMNLP 2020, pages 388–406, Online. Association for Computational Linguistics.
Cite (Informal):
Contextual Modulation for Relation-Level Metaphor Identification (Zayed et al., Findings 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.findings-emnlp.36.pdf
Code
 OmniaZayed/affineTrans_metaphor_identification