Year: 2021
Type: conference-paper
Abstract: Current NLP datasets targeting ambiguity can be solved by a native speaker with relative ease.We present Cryptonite, a large-scale dataset based on cryptic crosswords, which is both linguistically complex and naturally sourced.Each example in Cryptonite is a cryptic clue, a short phrase or sentence with a misleading surface reading, whose solving requires disambiguating semantic, syntactic, and phonetic wordplays, as well as world knowledge.Cryptic clues pose a challenge even for experienced solvers, though top-tier experts can solve them with almost 100% accuracy.Cryptonite is a challenging task for current models; fine-tuning T5-Large on 470k cryptic clues achieves only 7.6% accuracy, on par with the accuracy of a rule-based clue solver (8.6%).
Authors: Avia Efrat, Uri Shaham, Dan Kilman, Omer Levy
Institution: Tel Aviv University
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
Funders: Intel Corporation, Tel Aviv University
OpenAlex ID: W3133728641
