{"url":"/dataset/chinese-gigaword","name":"Chinese Gigaword","full_name":"Chinese Gigaword","description_markdown":"**Chinese Gigaword** corpus consists of 2.2M of headline-document pairs of news stories covering over 284 months from two Chinese newspapers, namely the Xinhua News Agency of China (XIN) and the Central News Agency of Taiwan (CNA).\r\n\r\nSource: [Order-Preserving Abstractive Summarization for Spoken Content Based on Connectionist Temporal Classification](https://arxiv.org/abs/1709.05475)\r\nImage Source: [https://catalog.ldc.upenn.edu/desc/addenda/LDC2011T13.jpg](https://catalog.ldc.upenn.edu/desc/addenda/LDC2011T13.jpg)","description_withheld":null,"homepage":"https://catalog.ldc.upenn.edu/LDC2011T13","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":null,"title":"LDC Catalog No.: LDC2003T09, ISBN","first_author":null,"url":"https://catalog.ldc.upenn.edu/LDC2011T13"},"license":{"name":"Custom","url":"https://catalog.ldc.upenn.edu/LDC2011T13"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Named Entity Recognition (NER)","url":"/task/named-entity-recognition-ner","datasets_with_task":"/datasets/task/named-entity-recognition-ner"},{"name":"Word Embeddings","url":"/task/word-embeddings","datasets_with_task":"/datasets/task/word-embeddings"},{"name":"Decipherment","url":"/task/decipherment","datasets_with_task":"/datasets/task/decipherment"}],"languages":[{"name":"Chinese","url":"/datasets/language/chinese"}],"variants":["Chinese Gigaword"],"data_loaders":[],"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":"2026-09-25T09:33:49+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."}