{"url":"/task/information-extraction","name":"Information Extraction","slug":"information-extraction","description_markdown":"Information extraction is the task of automatically extracting structured information from unstructured and / or semi-structured machine-readable documents and other electronically represented sources (Source: Wikipedia).","categories":[{"name":"Medical","url":"/area/medical"},{"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":3,"papers_with_code":3,"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":16,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/information-extraction-on-semtabnet","slug":"information-extraction-on-semtabnet","dataset":"SemTabNet","dataset_url":"/dataset/semtabnet","rows_in_archive":1,"metrics":["average Tree Similarity Score"],"first_row_in_archive_order":{"model":"T5","paper_title":"Statements: Universal Information Extraction from Tables with Large Language Models for ESG KPIs","paper_url":"/paper/statements-universal-information-extraction","paper_date":"2024-06-27","arxiv_id":"2406.19102","code_links":[{"title":"ds4sd/semtabnet","url":"https://github.com/ds4sd/semtabnet"}],"syntology":null}}],"datasets":[{"url":"/dataset/semtabnet","name":"SemTabNet","full_name":"","num_papers_in_archive":1}],"subtasks":[{"url":"/task/attribute-value-extraction","name":"Attribute Value Extraction"},{"url":"/task/catalog-extraction","name":"Catalog Extraction"},{"url":"/task/definition-extraction","name":"Definition Extraction"},{"url":"/task/document-level-closed-information-extraction","name":"Document-level Closed Information Extraction"},{"url":"/task/document-level-event-extraction","name":"Document-level Event Extraction"},{"url":"/task/drug-drug-interaction-extraction","name":"Drug–drug Interaction Extraction"},{"url":"/task/event-extraction","name":"Event Extraction"},{"url":"/task/event-relation-extraction","name":"Event Relation Extraction"},{"url":"/task/extractive-summarization","name":"Extractive Summarization"},{"url":"/task/genetic-ie","name":"Genetic IE"},{"url":"/task/information-threading","name":"Information Threading"},{"url":"/task/joint-entity-and-relation-extraction","name":"Joint Entity and Relation Extraction"},{"url":"/task/low-resource-named-entity-recognition","name":"Low Resource Named Entity Recognition"},{"url":"/task/multimodal-attribute-value-extraction","name":"Multimodal Attribute Value Extraction"},{"url":"/task/participant-intervention-comparison-outcome","name":"Participant Intervention Comparison Outcome Extraction"},{"url":"/task/temporal-information-extraction","name":"Temporal Information 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":3,"of":3,"tagged_in_all":3,"items":[{"url":"/paper/statements-universal-information-extraction","title":"Statements: Universal Information Extraction from Tables with Large Language Models for ESG KPIs","date":"2024-06-27","arxiv_id":"2406.19102","repositories_listed":1,"syntology":null},{"url":"/paper/texttovec-deep-contextualized-neural","title":"textTOvec: Deep Contextualized Neural Autoregressive Topic Models of Language with Distributed Compositional Prior","date":"2018-10-09","arxiv_id":"1810.03947","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":3}},{"url":"/paper/closing-the-loop-fast-interactive-semi","title":"Closing the Loop: Fast, Interactive Semi-Supervised Annotation With Queries on Features and Instances","date":"2011-07-01","arxiv_id":null,"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"}}