Metaphorical Paraphrase Generation: Feeding Metaphorical Language Models with Literal Texts

TL;DR

This paper introduces a novel metaphorical paraphrase generation method that masks literal words and uses metaphorical language models to unmask them, improving metaphorical sentence classification performance.

Contribution

It extends metaphorical paraphrasing to nouns and adjectives, not just verbs, and demonstrates improved classification accuracy through data augmentation.

Findings

Transfer rate for verbs is 56%.

Feasibility of transferring nouns and adjectives is 24% and 31%.

Data augmentation improves classification F1 by 3%.

Abstract

This study presents a new approach to metaphorical paraphrase generation by masking literal tokens of literal sentences and unmasking them with metaphorical language models. Unlike similar studies, the proposed algorithm does not only focus on verbs but also on nouns and adjectives. Despite the fact that the transfer rate for the former is the highest (56%), the transfer of the latter is feasible (24% and 31%). Human evaluation showed that our system-generated metaphors are considered more creative and metaphorical than human-generated ones while when using our transferred metaphors for data augmentation improves the state of the art in metaphorical sentence classification by 3% in F1.