{"url":"/dataset/cc-riddle","name":"CC-Riddle","full_name":"Chinese Character Riddle","description_markdown":"**CC-Riddle** is a Chinese character riddle dataset covering the majority of common simplified Chinese characters by crawling riddles from the Web and generating brand new ones. In the generation stage, the authors provide the Chinese phonetic alphabet, decomposition and explanation of the solution character for the generation model and get multiple riddle descriptions for each tested character. Then the generated riddles are manually filtered and the final dataset, CCRiddle is composed of both human-written riddles and filtered generated riddle.\r\n\r\nSource: [CC-Riddle: A Question Answering Dataset of Chinese Character Riddles](https://arxiv.org/pdf/2206.13778v1.pdf)\r\n\r\nImage Source: [https://arxiv.org/pdf/2206.13778v1.pdf](https://arxiv.org/pdf/2206.13778v1.pdf)","description_withheld":null,"homepage":"https://github.com/sailxuOvO/CC-Riddle","introduced_date":"2022-06-28","introduced_date_note":null,"introduced_by":{"paper":"/paper/cc-riddle-a-question-answering-dataset-of","title":"CC-Riddle: A Question Answering Dataset of Chinese Character Riddles","first_author":"Fan Xu","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Question Answering","url":"/task/question-answering","datasets_with_task":"/datasets/task/question-answering"}],"languages":[{"name":"Chinese","url":"/datasets/language/chinese"}],"variants":["CC-Riddle"],"data_loaders":[],"num_papers_in_archive":1,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[],"papers_with_a_benchmark_row":[],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":0,"samples_harvested":0,"samples_ran":0,"samples_unverified":0,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}