{"url":"/dataset/chinese-classifier","name":"Chinese Classifier","full_name":null,"description_markdown":"Classifiers are function words that are used to express quantities in Chinese and are especially difficult for language learners. This dataset of **Chinese Classifiers** can be used to predict Chinese classifiers from context.\nThe dataset contains a large collection of example sentences for Chinese classifier usage derived from three language corpora (Lancaster Corpus of Mandarin Chinese, UCLA Corpus of Written Chinese and Leiden Weibo Corpus). The data was cleaned and processed for a context-based classifier prediction task.\n\nSource: [https://github.com/wuningxi/ChineseClassifierDataset](https://github.com/wuningxi/ChineseClassifierDataset)","description_withheld":null,"homepage":"https://github.com/wuningxi/ChineseClassifierDataset","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/classifierguesser-a-context-based-classifier","title":"ClassifierGuesser: A Context-based Classifier Prediction System for Chinese Language Learners","first_author":"Nicole Peinelt","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[],"languages":[{"name":"Chinese","url":"/datasets/language/chinese"}],"variants":["Chinese Classifier"],"data_loaders":[{"repo":"https://github.com/wuningxi/ChineseClassifierDataset","url":"https://github.com/wuningxi/ChineseClassifierDataset","frameworks":[]}],"num_papers_in_archive":2,"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."}