{"url":"/dataset/oa-mine-annotations","name":"OA-Mine - annotations","full_name":null,"description_markdown":"The dataset contains Amazon products from 10 product categories with full human annotations.\r\nThe dataset was collected in 2021. The products may have been taken down from Amazon since the collection of the dataset.","description_withheld":null,"homepage":"https://github.com/xinyangz/OAMine","introduced_date":"2022-04-29","introduced_date_note":null,"introduced_by":{"paper":"/paper/oa-mine-open-world-attribute-mining-for-e","title":"OA-Mine: Open-World Attribute Mining for E-Commerce Products with Weak Supervision","first_author":"Xinyang Zhang","url":null},"license":null,"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":["OA-Mine - annotations"],"data_loaders":[],"num_papers_in_archive":3,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/attribute-value-extraction-on-oa-mine","task":"Attribute Value Extraction","dataset_variant":"OA-Mine - annotations","rows":2,"metrics":["F1-score"],"first_row_in_archive_order":{"model":"ft-GPT-3.5-json-val","paper":"/paper/product-attribute-value-extraction-using","metrics":{"F1-score":"84.5"},"code_links":[{"title":"wbsg-uni-mannheim/extractgpt","url":"https://github.com/wbsg-uni-mannheim/extractgpt"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/attribute-mining-on-oa-mine-annotations","task":"Attribute Mining","dataset_variant":"OA-Mine - annotations","rows":1,"metrics":["F1-score"],"first_row_in_archive_order":{"model":"T5 Large - End2End","paper":"/paper/an-empirical-comparison-of-generative","metrics":{"F1-score":"86.28"},"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/product-attribute-value-extraction-using","title":"ExtractGPT: Exploring the Potential of Large Language Models for Product Attribute Value Extraction","date":"2023-10-19","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."}