{"url":"/dataset/cs","name":"CS","full_name":"Chinese Simile","description_markdown":"This dataset is constructed and based on the online free-access fictions that are tagged with sci-fi, urban novel, love story, youth, etc. It is used for Writing Polishment with Smile (WPS) a task that aims to polish plain text with similes.\nAll similes are extracted by rich regular expression, and the extraction precision is estimated as 92% by labelling 500 random extracted samples.\nIt contains 5M samples for training and 2.5k for validation and test respectively.\n\nSource: [https://github.com/mrzjy/writing-polishment-with-simile](https://github.com/mrzjy/writing-polishment-with-simile)","description_withheld":null,"homepage":"https://github.com/mrzjy/writing-polishment-with-simile","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/writing-polishment-with-simile-task-dataset","title":"Writing Polishment with Simile: Task, Dataset and A Neural Approach","first_author":"Jiayi Zhang","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Reading Comprehension","url":"/task/reading-comprehension","datasets_with_task":"/datasets/task/reading-comprehension"},{"name":"Multi-Task Learning","url":"/task/multi-task-learning","datasets_with_task":"/datasets/task/multi-task-learning"}],"languages":[{"name":"Chinese","url":"/datasets/language/chinese"}],"variants":["CS"],"data_loaders":[{"repo":"https://github.com/mrzjy/writing-polishment-with-simile","url":"https://github.com/mrzjy/writing-polishment-with-simile","frameworks":["tf"]}],"num_papers_in_archive":3,"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."}