Predicting Human Metaphor Paraphrase Judgments with Deep Neural Networks

Yuri Bizzoni, Shalom Lappin


Abstract
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 (.75) and Spearman (.68) correlations on the gradient judgment prediction task.
Anthology ID:
W18-0906
Volume:
Proceedings of the Workshop on Figurative Language Processing
Month:
June
Year:
2018
Address:
New Orleans, Louisiana
Editors:
Beata Beigman Klebanov, Ekaterina Shutova, Patricia Lichtenstein, Smaranda Muresan, Chee Wee
Venue:
Fig-Lang
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
45–55
Language:
URL:
https://aclanthology.org/W18-0906
DOI:
10.18653/v1/W18-0906
Bibkey:
Cite (ACL):
Yuri Bizzoni and Shalom Lappin. 2018. Predicting Human Metaphor Paraphrase Judgments with Deep Neural Networks. In Proceedings of the Workshop on Figurative Language Processing, pages 45–55, New Orleans, Louisiana. Association for Computational Linguistics.
Cite (Informal):
Predicting Human Metaphor Paraphrase Judgments with Deep Neural Networks (Bizzoni & Lappin, Fig-Lang 2018)
Copy Citation:
PDF:
https://aclanthology.org/W18-0906.pdf