{"url":"/dataset/mave-attribute-black-tea-variety","name":"MAVE - Attribute: Black Tea Variety","full_name":"MAVE - Attribute: Black Tea Variety:  A Product Dataset for Multi-source Attribute Value Extraction","description_markdown":"The dataset contains 3 million attribute-value annotations across 1257 unique categories created from 2.2 million cleaned Amazon product profiles. It is a large, multi-sourced, diverse dataset for product attribute extraction study.","description_withheld":null,"homepage":"https://github.com/google-research-datasets/MAVE","introduced_date":"2021-12-16","introduced_date_note":null,"introduced_by":{"paper":"/paper/mave-a-product-dataset-for-multi-source","title":"MAVE: A Product Dataset for Multi-source Attribute Value Extraction","first_author":"Li Yang","url":null},"license":{"name":"Attribution-NonCommercial 4.0 International","url":"https://creativecommons.org/licenses/by/4.0/"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Attribute Value Extraction","url":"/task/attribute-value-extraction","datasets_with_task":"/datasets/task/attribute-value-extraction"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["MAVE - Attribute: Black Tea Variety"],"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."}