{"url":"/dataset/oie2016","name":"OIE2016","full_name":null,"description_markdown":"OIE2016 is the first large-scale OpenIE benchmark. It is created by automatic conversion from QA-SRL [He et al., 2015], a semantic role labeling dataset. The sentences are from news (e.g., WSJ) and encyclopedia (e.g., WIKI) domains. Since there are no restrictions on the elements of OpenIE extractions, partial-matching criteria instead of exact-matching is typically used. Hence, the evaluation script can tolerate the extractions that are slightly different from the gold annotation. \r\n\r\nSource: https://arxiv.org/pdf/2205.11725.pdf (section 3.1)","description_withheld":null,"homepage":"","introduced_date":"2016-11-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/creating-a-large-benchmark-for-open","title":"Creating a Large Benchmark for Open Information Extraction","first_author":"Gabriel Stanovsky","url":null},"license":null,"modalities":[],"tasks":[{"name":"Open Information Extraction","url":"/task/open-information-extraction","datasets_with_task":"/datasets/task/open-information-extraction"}],"languages":[],"variants":["OIE2016"],"data_loaders":[],"num_papers_in_archive":31,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/open-information-extraction-on-oie2016","task":"Open Information Extraction","dataset_variant":"OIE2016","rows":12,"metrics":["F1","AUC"],"first_row_in_archive_order":{"model":"DeepEx (zero-shot)","paper":"/paper/zero-shot-information-extraction-as-a-unified","metrics":{"AUC":"58.6","F1":"72.6"},"code_links":[{"title":"cgraywang/deepex","url":"https://github.com/cgraywang/deepex"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/improving-open-information-extraction-with","title":"Improving Open Information Extraction with Large Language Models: A Study on Demonstration Uncertainty","date":"2023-09-07","rows_on_this_dataset":3,"code_links":0,"syntology":null},{"paper":"/paper/a-survey-on-neural-open-information","title":"A Survey on Neural Open Information Extraction: Current Status and Future Directions","date":"2022-05-24","rows_on_this_dataset":4,"code_links":0,"syntology":null},{"paper":"/paper/deepstruct-pretraining-of-language-models-for-1","title":"DeepStruct: Pretraining of Language Models for Structure Prediction","date":"2022-05-21","rows_on_this_dataset":3,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":13,"samples_ran":7,"samples_unverified":6,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/zero-shot-information-extraction-as-a-unified","title":"Zero-Shot Information Extraction as a Unified Text-to-Triple Translation","date":"2021-09-23","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/span-based-open-information-extraction","title":"Span Model for Open Information Extraction on Accurate Corpus","date":"2019-01-30","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":4,"samples_ran":4,"samples_unverified":0,"pointer_only_for_licence":4,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":2,"samples_harvested":17,"samples_ran":11,"samples_unverified":6,"pointer_only_for_licence":4,"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."}