Proceedings of the 2021 Conference on Empirical Methods in Natural Language ProcessingĪssociation for Computational Linguistics Cryptic clues pose a challenge even for experienced solvers, though top-tier experts can solve them with almost 100).",Ĭryptonite: A Cryptic Crossword Benchmark for Extreme Ambiguity in Language 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. We present Cryptonite, a large-scale dataset based on cryptic crosswords, which is both linguistically complex and naturally sourced. Publisher = "Association for Computational Linguistics",Ībstract = "Current NLP datasets targeting ambiguity can be solved by a native speaker with relative ease. Cite (Informal): Cryptonite: A Cryptic Crossword Benchmark for Extreme Ambiguity in Language (Efrat et al., EMNLP 2021) Copy Citation: BibTeX Markdown MODS XML Endnote More options… PDF: Video: Code = "Cryptonite: A Cryptic Crossword Benchmark for Extreme Ambiguity in Language",īooktitle = "Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing",Īddress = "Online and Punta Cana, Dominican Republic", Association for Computational Linguistics. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 4186–4192, Online and Punta Cana, Dominican Republic. Cryptonite: A Cryptic Crossword Benchmark for Extreme Ambiguity in Language. Anthology ID: 2021.emnlp-main.344 Volume: Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing Month: November Year: 2021 Address: Online and Punta Cana, Dominican Republic Venue: EMNLP SIG: Publisher: Association for Computational Linguistics Note: Pages: 4186–4192 Language: URL: DOI: 10.18653/v1/2021.emnlp-main.344 Bibkey: efrat-etal-2021-cryptonite Cite (ACL): Avia Efrat, Uri Shaham, Dan Kilman, and Omer Levy. 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%). Cryptic clues pose a challenge even for experienced solvers, though top-tier experts can solve them with almost 100% accuracy. ![]() Abstract Current NLP datasets targeting ambiguity can be solved by a native speaker with relative ease.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |