{"url":"/task/attribute-value-extraction","name":"Attribute Value Extraction","slug":"attribute-value-extraction","description_markdown":"**Attribute Value Extraction** is the task of extracting values for a given set of attributes of interest from free text input. Attribute value extraction is for example applied in the context of e-commerce where product attribute values are extracted from product offers.\r\n\r\nThe related task [Attribute Mining](https://paperswithcode.com/task/attribute-mining) assume that the target attribute set is unknown, while attribute value extraction assumes that the attribute set is given.\r\n[Multimodal Attribute Extraction](https://paperswithcode.com/task/multimodal-attribute-value-extraction) aims at extracting attribute values from multi-modal input such as text plus images.","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":35,"papers_with_code":16,"benchmarks":4,"benchmark_tables_in_archive":4,"benchmark_tables_shown":4,"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":6,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/attribute-value-extraction-on-wdc-pave","slug":"attribute-value-extraction-on-wdc-pave","dataset":"WDC-PAVE","dataset_url":"/dataset/wdc-pave","rows_in_archive":5,"metrics":["F1-Score"],"first_row_in_archive_order":{"model":"GPT-4_10_example_values_&_10_demonstrations","paper_title":"Using LLMs for the Extraction and Normalization of Product Attribute Values","paper_url":"/paper/using-llms-for-the-extraction-and","paper_date":"2024-03-04","arxiv_id":"2403.02130","code_links":[{"title":"wbsg-uni-mannheim/wdc-pave","url":"https://github.com/wbsg-uni-mannheim/wdc-pave"}],"syntology":null}},{"leaderboard":"/sota/attribute-value-extraction-on-mave","slug":"attribute-value-extraction-on-mave","dataset":"MAVE","dataset_url":"/dataset/mave","rows_in_archive":3,"metrics":["F1-score"],"first_row_in_archive_order":{"model":"MAVEQA","paper_title":"MAVE: A Product Dataset for Multi-source Attribute Value Extraction","paper_url":"/paper/mave-a-product-dataset-for-multi-source","paper_date":"2021-12-16","arxiv_id":"2112.08663","code_links":[{"title":"google-research-datasets/mave","url":"https://github.com/google-research-datasets/mave"}],"syntology":null}},{"leaderboard":"/sota/attribute-value-extraction-on-ae-110k","slug":"attribute-value-extraction-on-ae-110k","dataset":"AE-110k","dataset_url":"/dataset/ae-110k","rows_in_archive":2,"metrics":["F1-score"],"first_row_in_archive_order":{"model":"GPT-4-json-val-10-dem","paper_title":"ExtractGPT: Exploring the Potential of Large Language Models for Product Attribute Value Extraction","paper_url":"/paper/product-attribute-value-extraction-using","paper_date":"2023-10-19","arxiv_id":"2310.12537","code_links":[{"title":"wbsg-uni-mannheim/extractgpt","url":"https://github.com/wbsg-uni-mannheim/extractgpt"}],"syntology":null}},{"leaderboard":"/sota/attribute-value-extraction-on-oa-mine","slug":"attribute-value-extraction-on-oa-mine","dataset":"OA-Mine - annotations","dataset_url":"/dataset/oa-mine-annotations","rows_in_archive":2,"metrics":["F1-score"],"first_row_in_archive_order":{"model":"ft-GPT-3.5-json-val","paper_title":"ExtractGPT: Exploring the Potential of Large Language Models for Product Attribute Value Extraction","paper_url":"/paper/product-attribute-value-extraction-using","paper_date":"2023-10-19","arxiv_id":"2310.12537","code_links":[{"title":"wbsg-uni-mannheim/extractgpt","url":"https://github.com/wbsg-uni-mannheim/extractgpt"}],"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},{"url":"/dataset/wdc-pave","name":"WDC-PAVE","full_name":"Web Data Commones - Product Attribute Value Extraction","num_papers_in_archive":2},{"url":"/dataset/caselaw4","name":"Caselaw4","full_name":"","num_papers_in_archive":1},{"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","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[{"url":"/task/information-extraction","name":"Information Extraction"}],"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":16,"of":16,"tagged_in_all":35,"items":[{"url":"/paper/multimodal-joint-attribute-prediction-and","title":"Multimodal Joint Attribute Prediction and Value Extraction for E-commerce Product","date":"2020-09-15","arxiv_id":"2009.07162","repositories_listed":2,"syntology":null},{"url":"/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","date":"2019-07-01","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/opentag-open-attribute-value-extraction-from","title":"OpenTag: Open Attribute Value Extraction from Product Profiles [Deep Learning, Active Learning, Named Entity Recognition]","date":"2018-06-01","arxiv_id":"1806.01264","repositories_listed":2,"syntology":{"n":3,"n_ran":1,"n_unverified":2,"n_pointer_only":3}},{"url":"/paper/automated-self-refinement-and-self-correction","title":"Automated Self-Refinement and Self-Correction for LLM-based Product Attribute Value Extraction","date":"2025-01-02","arxiv_id":"2501.01237","repositories_listed":1,"syntology":null},{"url":"/paper/implicitave-an-open-source-dataset-and","title":"ImplicitAVE: An Open-Source Dataset and Multimodal LLMs Benchmark for Implicit Attribute Value Extraction","date":"2024-04-24","arxiv_id":"2404.15592","repositories_listed":1,"syntology":null},{"url":"/paper/using-llms-for-the-extraction-and","title":"Using LLMs for the Extraction and Normalization of Product Attribute Values","date":"2024-03-04","arxiv_id":"2403.02130","repositories_listed":1,"syntology":null},{"url":"/paper/multi-label-zero-shot-product-attribute-value","title":"Multi-Label Zero-Shot Product Attribute-Value Extraction","date":"2024-02-13","arxiv_id":"2402.08802","repositories_listed":1,"syntology":null},{"url":"/paper/jpave-a-generation-and-classification-based","title":"JPAVE: A Generation and Classification-based Model for Joint Product Attribute Prediction and Value Extraction","date":"2023-11-07","arxiv_id":"2311.04196","repositories_listed":1,"syntology":null},{"url":"/paper/product-attribute-value-extraction-using","title":"ExtractGPT: Exploring the Potential of Large Language Models for Product Attribute Value Extraction","date":"2023-10-19","arxiv_id":"2310.12537","repositories_listed":1,"syntology":null},{"url":"/paper/ae-smnsmlc-multi-label-classification-with","title":"AE-smnsMLC: Multi-Label Classification with Semantic Matching and Negative Label Sampling for Product Attribute Value Extraction","date":"2023-10-11","arxiv_id":"2310.07137","repositories_listed":1,"syntology":null},{"url":"/paper/knowledge-enhanced-multi-label-few-shot","title":"Knowledge-Enhanced Multi-Label Few-Shot Product Attribute-Value Extraction","date":"2023-08-16","arxiv_id":"2308.08413","repositories_listed":1,"syntology":null},{"url":"/paper/cave-correcting-attribute-values-in-e","title":"CAVE: Correcting Attribute Values in E-commerce Profiles","date":"2022-10-17","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/openbrand-open-brand-value-extraction-from","title":"OpenBrand: Open Brand Value Extraction from Product Descriptions","date":"2022-05-01","arxiv_id":null,"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/mave-a-product-dataset-for-multi-source","title":"MAVE: A Product Dataset for Multi-source Attribute Value Extraction","date":"2021-12-16","arxiv_id":"2112.08663","repositories_listed":1,"syntology":null},{"url":"/paper/knowledge-guided-open-attribute-value","title":"Knowledge-guided Open Attribute Value Extraction with Reinforcement Learning","date":"2020-10-19","arxiv_id":"2010.09189","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_unverified":1,"n_pointer_only":2}}],"syntology_records":2,"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":2,"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"}}