Modeling Conceptual Attribute Likeness and Domain Inconsistency for Metaphor Detection

Yuan Tian, Nan Xu, Wenji Mao, Daniel Dajun Zeng

Submission Type: Regular Long Paper

Submission Track: Information Retrieval and Text Mining

Submission Track 2: Linguistic Theories, Cognitive Modeling, and Psycholinguistics

Keywords: Metaphor detection, Attribute likeness, Attribute siamese network, Conceptual metaphor theory

Abstract: Metaphor detection is an important and challenging task in natural language processing, which aims to distinguish between metaphorical and literal expressions in text. Previous studies mainly leverage the incongruity of source and target domains and contextual clues for detection, neglecting similar attributes shared between source and target concepts in metaphorical expressions. Based on conceptual metaphor theory, these similar attributes are essential to infer implicit meanings conveyed by the metaphor. Under the guidance of conceptual metaphor theory, in this paper, we model the likeness of attribute for the first time and propose a novel Attribute Likeness and Domain Inconsistency Learning framework (AIDIL) for word-pair metaphor detection. Specifically, we propose an attribute siamese network to mine similar attributes between source and target concepts. We then devise a domain contrastive learning strategy to learn the semantic inconsistency of concepts in source and target domains. Extensive experiments on four datasets verify that our method significantly outperforms the previous state-of-the-art methods, and demonstrate the generalization ability of our method.

Submission Number: 431