Following the work of Chakrabarty et al. [2021], we performed human evaluation of the newly constructed metaphorical sentences, by comparing them against human-generated ones.

For each sentence, then, four different dimensions were evaluated, vis. **fluency**, **meaning**, **creativity**, and **metaphoricity**.

University of Michigan - Ann Arbor

The proposed algorithm required two training steps. First, a text classifier learns to classify metaphorical from literal sentences. 

Second, metaphorical sentences, which were correctly classified by our classifier as metaphorical, were passed to a reconstruction step, where metaphorical tokens were masked and then recovered through extraction (T5, BART) and masked language modeling (BERT, XLM-R).

Learn Before

Related