{"url":"/dataset/ae-110k","name":"AE-110k","full_name":"AliExpress - 110k","description_markdown":"The dataset contains product information from AliExpress Sports & Entertainment category. Each attribute value in \"Item Specific\" is matched against the product title using exact string match to generate positive triples <title, attribute, value>. Negative triples <title, attribute, NULL> are randomly generated. Each triple is stored in a line and separated by \\u0001.","description_withheld":null,"homepage":"https://github.com/cubenlp/ACL19_Scaling_Up_Open_Tagging/blob/master/publish_data.txt","introduced_date":"2019-07-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/scaling-up-open-tagging-from-tens-to","title":"Scaling up Open Tagging from Tens to Thousands: Comprehension Empowered Attribute Value Extraction from Product Title","first_author":"Huimin Xu","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":["AE-110k"],"data_loaders":[],"num_papers_in_archive":12,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/attribute-value-extraction-on-ae-110k","task":"Attribute Value Extraction","dataset_variant":"AE-110k","rows":2,"metrics":["F1-score"],"first_row_in_archive_order":{"model":"GPT-4-json-val-10-dem","paper":"/paper/product-attribute-value-extraction-using","metrics":{"F1-score":"87.5"},"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-ae-110k","task":"Attribute Mining","dataset_variant":"AE-110k","rows":1,"metrics":["F1-score"],"first_row_in_archive_order":{"model":"T5 Large - End2End","paper":"/paper/an-empirical-comparison-of-generative","metrics":{"F1-score":"84.29"},"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."}