{"url":"/dataset/paralex","name":"Paralex","full_name":null,"description_markdown":"Paralex learns from a collection of 18 million question-paraphrase pairs scraped from WikiAnswers.","description_withheld":null,"homepage":"http://knowitall.cs.washington.edu/paralex/","introduced_date":"2013-06-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/paraphrase-driven-learning-for-open-question","title":"Paraphrase-Driven Learning for Open Question Answering","first_author":"Anthony Fader","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Paraphrase Identification","url":"/task/paraphrase-identification","datasets_with_task":"/datasets/task/paraphrase-identification"},{"name":"Paraphrase Generation","url":"/task/paraphrase-generation","datasets_with_task":"/datasets/task/paraphrase-generation"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["Paralex"],"data_loaders":[],"num_papers_in_archive":20,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/paraphrase-generation-on-paralex","task":"Paraphrase Generation","dataset_variant":"Paralex","rows":2,"metrics":["iBLEU","BLEU"],"first_row_in_archive_order":{"model":"HRQ-VAE","paper":"/paper/hierarchical-sketch-induction-for-paraphrase","metrics":{"BLEU":"39.49","iBLEU":"24.93"},"code_links":[{"title":"tomhosking/hrq-vae","url":"https://github.com/tomhosking/hrq-vae"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/hierarchical-sketch-induction-for-paraphrase","title":"Hierarchical Sketch Induction for Paraphrase Generation","date":"2022-03-07","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":3,"samples_ran":3,"samples_unverified":0,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/factorising-meaning-and-form-for-intent","title":"Factorising Meaning and Form for Intent-Preserving Paraphrasing","date":"2021-05-31","rows_on_this_dataset":1,"code_links":1,"syntology":null}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":1,"samples_harvested":3,"samples_ran":3,"samples_unverified":0,"pointer_only_for_licence":0,"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."}