{"url":"/dataset/cpp","name":"CPP","full_name":"Chinese Polyphones with Pinyin","description_markdown":"A benchmark dataset that consists of 99,000+ sentences for Chinese polyphone disambiguation. \r\n\r\nSource: [g2pM: A Neural Grapheme-to-Phoneme Conversion Package for Mandarin Chinese Based on a New Open Benchmark Dataset](/paper/g2pm-a-neural-grapheme-to-phoneme-conversion)","description_withheld":null,"homepage":"https://github.com/kakaobrain/g2pM","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/g2pm-a-neural-grapheme-to-phoneme-conversion","title":"g2pM: A Neural Grapheme-to-Phoneme Conversion Package for Mandarin Chinese Based on a New Open Benchmark Dataset","first_author":"Kyubyong Park","url":null},"license":null,"modalities":[],"tasks":[{"name":"Polyphone disambiguation","url":"/task/polyphone-disambiguation","datasets_with_task":"/datasets/task/polyphone-disambiguation"}],"languages":[{"name":"Chinese","url":"/datasets/language/chinese"}],"variants":["CPP"],"data_loaders":[{"repo":"https://github.com/kakaobrain/g2pM","url":"https://github.com/kakaobrain/g2pM","frameworks":[]}],"num_papers_in_archive":3,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/polyphone-disambiguation-on-cpp","task":"Polyphone disambiguation","dataset_variant":"CPP","rows":3,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"g2pW","paper":"/paper/g2pw-a-conditional-weighted-softmax-bert-for","metrics":{"Accuracy":"99.08"},"code_links":[{"title":"GitYCC/g2pW","url":"https://github.com/GitYCC/g2pW"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/g2pw-a-conditional-weighted-softmax-bert-for","title":"g2pW: A Conditional Weighted Softmax BERT for Polyphone Disambiguation in Mandarin","date":"2022-03-20","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/g2pm-a-neural-grapheme-to-phoneme-conversion","title":"g2pM: A Neural Grapheme-to-Phoneme Conversion Package for Mandarin Chinese Based on a New Open Benchmark Dataset","date":"2020-04-07","rows_on_this_dataset":2,"code_links":1,"syntology":null}],"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."}