We introduce EUREKA, an ensemble-based approach for performing automatic euphemism detection. We (1) identify and correct potentially mislabelled rows in the dataset, (2) curate an expanded corpus called EuphAug, (3) leverage model representations of Potentially Euphemistic Terms (PETs), and (4) explore using representations of semantically close sentences to aid in classification. Using our augmented dataset and kNN-based methods, EUREKA was able to achieve state-of-the-art results on the public leaderboard of the Euphemism Detection Shared Task, ranking first with a macro F1 score of 0.881.
2022, Proceedings of the 3rd Workshop on Figurative Language Processing (FLP), Pages -
EUREKA: EUphemism Recognition Enhanced through Knn-based methods and Augmentation (04b Atto di convegno in volume)
Scott Keh Sedrick, Bharadwaj Rohit K., Liu Emmy, Tedeschi Simone, Gangal Varun, Navigli Roberto
Gruppo di ricerca: Natural Language Processing