{"url":"/dataset/mave","name":"MAVE","full_name":"MAVE: : 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.\r\nIt 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"},{"name":"Attribute Mining","url":"/task/attribute-mining","datasets_with_task":"/datasets/task/attribute-mining"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["MAVE"],"data_loaders":[],"num_papers_in_archive":14,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/attribute-value-extraction-on-mave","task":"Attribute Value Extraction","dataset_variant":"MAVE","rows":3,"metrics":["F1-score"],"first_row_in_archive_order":{"model":"MAVEQA","paper":"/paper/mave-a-product-dataset-for-multi-source","metrics":{"F1-score":"98.32"},"code_links":[{"title":"google-research-datasets/mave","url":"https://github.com/google-research-datasets/mave"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/attribute-mining-on-mave","task":"Attribute Mining","dataset_variant":"MAVE","rows":1,"metrics":["F1-score"],"first_row_in_archive_order":{"model":"T5 Large - End2End","paper":"/paper/an-empirical-comparison-of-generative","metrics":{"F1-score":"95.19"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/an-empirical-comparison-of-generative","title":"An Empirical Comparison of Generative Approaches for Product Attribute-Value Identification","date":"2024-07-01","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/mave-a-product-dataset-for-multi-source","title":"MAVE: A Product Dataset for Multi-source Attribute Value Extraction","date":"2021-12-16","rows_on_this_dataset":3,"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."}