{"url":"/dataset/pit","name":"PIT","full_name":"Paraphrase and Semantic Similarity in Twitter","description_markdown":"Paraphrase and Semantic Similarity in Twitter (PIT) presents a constructed Twitter Paraphrase Corpus that contains 18,762 sentence pairs. \r\n\r\nSource: [SemEval-2015 Task 1: Paraphrase and Semantic Similarity in Twitter (PIT)](https://www.aclweb.org/anthology/S15-2001.pdf)","description_withheld":null,"homepage":"https://github.com/cocoxu/SemEval-PIT2015","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/semeval-2015-task-1-paraphrase-and-semantic","title":"SemEval-2015 Task 1: Paraphrase and Semantic Similarity in Twitter (PIT)","first_author":"Wei Xu","url":null},"license":{"name":"Unknown","url":null},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Semantic Textual Similarity","url":"/task/semantic-textual-similarity","datasets_with_task":"/datasets/task/semantic-textual-similarity"},{"name":"Paraphrase Identification","url":"/task/paraphrase-identification","datasets_with_task":"/datasets/task/paraphrase-identification"},{"name":"Sentence Embeddings","url":"/task/sentence-embeddings","datasets_with_task":"/datasets/task/sentence-embeddings"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["PIT"],"data_loaders":[{"repo":"https://github.com/cocoxu/SemEval-PIT2015","url":"https://github.com/cocoxu/SemEval-PIT2015","frameworks":[]}],"num_papers_in_archive":22,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/paraphrase-identification-on-pit","task":"Paraphrase Identification","dataset_variant":"PIT","rows":1,"metrics":["AP"],"first_row_in_archive_order":{"model":"TSDAE","paper":"/paper/tsdae-using-transformer-based-sequential","metrics":{"AP":"69.2"},"code_links":[{"title":"kwang2049/pytorch-bertflow","url":"https://github.com/kwang2049/pytorch-bertflow"},{"title":"ukplab/pytorch-bertflow","url":"https://github.com/ukplab/pytorch-bertflow"},{"title":"kwang2049/useb","url":"https://github.com/kwang2049/useb"},{"title":"UKPLab/useb","url":"https://github.com/UKPLab/useb"},{"title":"climsocana/tecb-de","url":"https://github.com/climsocana/tecb-de"},{"title":"exploration-lab/iitk-semeval-2024-task-1","url":"https://github.com/exploration-lab/iitk-semeval-2024-task-1"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/tsdae-using-transformer-based-sequential","title":"TSDAE: Using Transformer-based Sequential Denoising Auto-Encoder for Unsupervised Sentence Embedding Learning","date":"2021-04-14","rows_on_this_dataset":1,"code_links":6,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":4,"samples_ran":0,"samples_unverified":4,"pointer_only_for_licence":0,"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":1,"samples_harvested":4,"samples_ran":0,"samples_unverified":4,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":1,"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."}