Metaphorical Paraphrase Generation: Feeding Metaphorical Language Models with Literal Texts
This addresses the problem of generating creative metaphors for natural language processing applications, though it is incremental in scope.
The paper tackles metaphorical paraphrase generation by masking literal tokens in sentences and unmasking them with metaphorical language models, achieving a 3% F1 improvement in metaphorical sentence classification through data augmentation.
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.