{"url":"/task/table-extraction","name":"Table Extraction","slug":"table-extraction","description_markdown":"Table extraction involves detecting and recognizing a table's logical structure and content from its unstructured presentation within a document","categories":[{"name":"Miscellaneous","url":"/area/miscellaneous"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"derived"},"counts":{"papers_tagged":32,"papers_with_code":15,"benchmarks":0,"benchmark_tables_in_archive":0,"benchmark_tables_shown":0,"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":0,"subtasks":1,"parent_tasks":0},"benchmarks":[],"datasets":[],"subtasks":[{"url":"/task/table-functional-analysis","name":"Table Functional Analysis"}],"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":15,"of":15,"tagged_in_all":32,"items":[{"url":"/paper/tablenet-deep-learning-model-for-end-to-end","title":"TableNet: Deep Learning model for end-to-end Table detection and Tabular data extraction from Scanned Document Images","date":"2020-01-06","arxiv_id":"2001.01469","repositories_listed":5,"syntology":{"n":2,"n_ran":0,"n_unverified":2,"n_pointer_only":0}},{"url":"/paper/deep-learning-for-table-detection-and","title":"Deep learning for table detection and structure recognition: A survey","date":"2022-11-15","arxiv_id":"2211.08469","repositories_listed":3,"syntology":null},{"url":"/paper/scientific-evidence-extraction","title":"PubTables-1M: Towards comprehensive table extraction from unstructured documents","date":"2021-09-30","arxiv_id":"2110.00061","repositories_listed":2,"syntology":{"n":13,"n_ran":5,"n_unverified":8,"n_pointer_only":10}},{"url":"/paper/quest-quality-aware-semi-supervised-table","title":"QUEST: Quality-aware Semi-supervised Table Extraction for Business Documents","date":"2025-06-17","arxiv_id":"2506.14568","repositories_listed":1,"syntology":null},{"url":"/paper/synfintabs-a-dataset-of-synthetic-financial","title":"SynFinTabs: A Dataset of Synthetic Financial Tables for Information and Table Extraction","date":"2024-12-05","arxiv_id":"2412.04262","repositories_listed":1,"syntology":null},{"url":"/paper/pdftable-a-unified-toolkit-for-deep-learning","title":"PdfTable: A Unified Toolkit for Deep Learning-Based Table Extraction","date":"2024-09-08","arxiv_id":"2409.05125","repositories_listed":1,"syntology":null},{"url":"/paper/h-star-llm-driven-hybrid-sql-text-adaptive","title":"H-STAR: LLM-driven Hybrid SQL-Text Adaptive Reasoning on Tables","date":"2024-06-29","arxiv_id":"2407.05952","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_unverified":1,"n_pointer_only":4}},{"url":"/paper/simplot-enhancing-chart-question-answering-by","title":"SIMPLOT: Enhancing Chart Question Answering by Distilling Essentials","date":"2024-02-22","arxiv_id":"2405.00021","repositories_listed":1,"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/cte-a-dataset-for-contextualized-table","title":"CTE: A Dataset for Contextualized Table Extraction","date":"2023-02-02","arxiv_id":"2302.01451","repositories_listed":1,"syntology":null},{"url":"/paper/graph-neural-networks-and-representation","title":"Graph Neural Networks and Representation Embedding for Table Extraction in PDF Documents","date":"2022-08-23","arxiv_id":"2208.11203","repositories_listed":1,"syntology":null},{"url":"/paper/discomat-distantly-supervised-composition","title":"DiSCoMaT: Distantly Supervised Composition Extraction from Tables in Materials Science Articles","date":"2022-07-03","arxiv_id":"2207.01079","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}},{"url":"/paper/scanbank-a-benchmark-dataset-for-figure","title":"ScanBank: A Benchmark Dataset for Figure Extraction from Scanned Electronic Theses and Dissertations","date":"2021-06-23","arxiv_id":"2106.15320","repositories_listed":1,"syntology":null},{"url":"/paper/tab-iais-flexible-table-recognition-and","title":"Flexible Table Recognition and Semantic Interpretation System","date":"2021-05-25","arxiv_id":"2105.11879","repositories_listed":1,"syntology":null},{"url":"/paper/gfte-graph-based-financial-table-extraction","title":"GFTE: Graph-based Financial Table Extraction","date":"2020-03-17","arxiv_id":"2003.07560","repositories_listed":1,"syntology":null}],"syntology_records":4,"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"}}