{"url":"/task/attribute-mining","name":"Attribute Mining","slug":"attribute-mining","description_markdown":"The attribute mining task assumes an open-world setting in which novel attributes and their values are extracted from free text.\r\nThe task is mainly studied in the e-commerce context, where new attribute are mined from product titles and product descriptions.","categories":[{"name":"Natural Language Processing","url":"/area/natural-language-processing"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":4,"papers_with_code":3,"benchmarks":3,"benchmark_tables_in_archive":3,"benchmark_tables_shown":3,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":3,"subtasks":0,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/attribute-mining-on-ae-110k","slug":"attribute-mining-on-ae-110k","dataset":"AE-110k","dataset_url":"/dataset/ae-110k","rows_in_archive":1,"metrics":["F1-score"],"first_row_in_archive_order":{"model":"T5 Large - End2End","paper_title":"An Empirical Comparison of Generative Approaches for Product Attribute-Value Identification","paper_url":"/paper/an-empirical-comparison-of-generative","paper_date":"2024-07-01","arxiv_id":"2407.01137","code_links":[],"syntology":null}},{"leaderboard":"/sota/attribute-mining-on-mave","slug":"attribute-mining-on-mave","dataset":"MAVE","dataset_url":"/dataset/mave","rows_in_archive":1,"metrics":["F1-score"],"first_row_in_archive_order":{"model":"T5 Large - End2End","paper_title":"An Empirical Comparison of Generative Approaches for Product Attribute-Value Identification","paper_url":"/paper/an-empirical-comparison-of-generative","paper_date":"2024-07-01","arxiv_id":"2407.01137","code_links":[],"syntology":null}},{"leaderboard":"/sota/attribute-mining-on-oa-mine-annotations","slug":"attribute-mining-on-oa-mine-annotations","dataset":"OA-Mine - annotations","dataset_url":"/dataset/oa-mine-annotations","rows_in_archive":1,"metrics":["F1-score"],"first_row_in_archive_order":{"model":"T5 Large - End2End","paper_title":"An Empirical Comparison of Generative Approaches for Product Attribute-Value Identification","paper_url":"/paper/an-empirical-comparison-of-generative","paper_date":"2024-07-01","arxiv_id":"2407.01137","code_links":[],"syntology":null}}],"datasets":[{"url":"/dataset/mave","name":"MAVE","full_name":"MAVE: : A Product Dataset for Multi-source Attribute Value Extraction","num_papers_in_archive":14},{"url":"/dataset/ae-110k","name":"AE-110k","full_name":"AliExpress - 110k","num_papers_in_archive":12},{"url":"/dataset/oa-mine-annotations","name":"OA-Mine - annotations","full_name":"","num_papers_in_archive":3}],"subtasks":[],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":3,"of":3,"tagged_in_all":4,"items":[{"url":"/paper/towards-open-world-product-attribute-mining-a","title":"Towards Open-World Product Attribute Mining: A Lightly-Supervised Approach","date":"2023-05-26","arxiv_id":"2305.18350","repositories_listed":1,"syntology":null},{"url":"/paper/oa-mine-open-world-attribute-mining-for-e","title":"OA-Mine: Open-World Attribute Mining for E-Commerce Products with Weak Supervision","date":"2022-04-29","arxiv_id":"2204.13874","repositories_listed":1,"syntology":null},{"url":"/paper/attribute-mix-semantic-data-augmentation-for","title":"Attribute Mix: Semantic Data Augmentation for Fine Grained Recognition","date":"2020-04-06","arxiv_id":"2004.02684","repositories_listed":1,"syntology":null}],"syntology_records":0,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}