{"url":"/task/attribute-extraction","name":"Attribute Extraction","slug":"attribute-extraction","description_markdown":null,"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":59,"papers_with_code":11,"benchmarks":1,"benchmark_tables_in_archive":1,"benchmark_tables_shown":1,"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":1,"subtasks":1,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/attribute-extraction-on-swde","slug":"attribute-extraction-on-swde","dataset":"SWDE","dataset_url":"/dataset/swde","rows_in_archive":2,"metrics":["Avg F1"],"first_row_in_archive_order":{"model":"InstrucTE (zero-shot)","paper_title":"Schema-Driven Information Extraction from Heterogeneous Tables","paper_url":"/paper/schema-driven-information-extraction-from","paper_date":"2023-05-23","arxiv_id":"2305.14336","code_links":[{"title":"bflashcp3f/schema-to-json","url":"https://github.com/bflashcp3f/schema-to-json"}],"syntology":null}}],"datasets":[{"url":"/dataset/swde","name":"SWDE","full_name":"Structured Web Data Extraction","num_papers_in_archive":5}],"subtasks":[{"url":"/task/legal-outcome-extraction","name":"legal outcome extraction"}],"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":11,"of":11,"tagged_in_all":59,"items":[{"url":"/paper/moon-a-mixed-objective-optimization-network","title":"MOON: A Mixed Objective Optimization Network for the Recognition of Facial Attributes","date":"2016-03-22","arxiv_id":"1603.07027","repositories_listed":3,"syntology":{"n":4,"n_ran":0,"n_unverified":4,"n_pointer_only":0}},{"url":"/paper/simplified-dom-trees-for-transferable","title":"Simplified DOM Trees for Transferable Attribute Extraction from the Web","date":"2021-01-07","arxiv_id":"2101.02415","repositories_listed":2,"syntology":null},{"url":"/paper/schema-driven-information-extraction-from","title":"Schema-Driven Information Extraction from Heterogeneous Tables","date":"2023-05-23","arxiv_id":"2305.14336","repositories_listed":1,"syntology":null},{"url":"/paper/dissecting-recall-of-factual-associations-in","title":"Dissecting Recall of Factual Associations in Auto-Regressive Language Models","date":"2023-04-28","arxiv_id":"2304.14767","repositories_listed":1,"syntology":null},{"url":"/paper/a-unified-framework-of-medical-information","title":"A Unified Framework of Medical Information Annotation and Extraction for Chinese Clinical Text","date":"2022-03-08","arxiv_id":"2203.03823","repositories_listed":1,"syntology":null},{"url":"/paper/dom-lm-learning-generalizable-representations","title":"DOM-LM: Learning Generalizable Representations for HTML Documents","date":"2022-01-25","arxiv_id":"2201.10608","repositories_listed":1,"syntology":null},{"url":"/paper/deepke-a-deep-learning-based-knowledge","title":"DeepKE: A Deep Learning Based Knowledge Extraction Toolkit for Knowledge Base Population","date":"2022-01-10","arxiv_id":"2201.03335","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/extracting-outcomes-from-appellate-decisions","title":"Extracting Outcomes from Appellate Decisions in US State Courts","date":"2020-12-09","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/getting-to-know-you-user-attribute-extraction","title":"Getting To Know You: User Attribute Extraction from Dialogues","date":"2019-08-13","arxiv_id":"1908.04621","repositories_listed":1,"syntology":null},{"url":"/paper/multimodal-attribute-extraction","title":"Multimodal Attribute Extraction","date":"2017-11-29","arxiv_id":"1711.11118","repositories_listed":1,"syntology":null}],"syntology_records":1,"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"}}