Predicting Human Metaphor Paraphrase Judgments with Deep Neural Networks

Yuri Bizzoni, Shalom Lappin
2018 Proceedings of the Workshop on Figurative Language Processing  
We propose a new annotated corpus for metaphor interpretation by paraphrase, and a novel DNN model for performing this task. Our corpus consists of 200 sets of 5 sentences, with each set containing one reference metaphorical sentence, and four ranked candidate paraphrases. Our model is trained for a binary classification of paraphrase candidates, and then used to predict graded paraphrase acceptability. It reaches an encouraging 75% accuracy on the binary classification task, and high Pearson
more » ... 75) and Spearman (.68) correlations on the gradient judgment prediction task.
doi:10.18653/v1/w18-0906 dblp:conf/acl-figlang/BizzoniL18 fatcat:umv2x4owpvf65ngqi4jtroyqru