{"url":"/dataset/terra","name":"TERRa","full_name":"Textual Entailment Recognition for Russian","description_markdown":"Textual Entailment Recognition has been proposed recently as a generic task that captures major semantic inference needs across many NLP applications, such as Question Answering, Information Retrieval, Information Extraction, and Text Summarization. This task requires to recognize, given two text fragments, whether the meaning of one text is entailed (can be inferred) from the other text.\r\n\r\n### Task Type\r\nRTE (Recognizing Textual Entailment) Sentence Pair Classification - Entailment - Not Entailment\r\n\r\n### Example\r\n```\r\n{\r\n  \"premise\": \"Автор поста написал в комментарии, что прорвалась канализация.\",\r\n  \"hypothesis\": \"Автор поста написал про канализацию.\",\r\n  \"label\": \"entailment\",\r\n  \"idx\": \"6062\"\r\n}\r\n```\r\n\r\n### How did we collect data? \r\nAll text examples were collected from open news sources and literary magazines, then manually reviewed and supplemented by a human assessment on Yandex.Toloka","description_withheld":null,"homepage":"https://github.com/RussianNLP/RussianSuperGLUE","introduced_date":"2020-10-29","introduced_date_note":null,"introduced_by":{"paper":"/paper/russiansuperglue-a-russian-language","title":"RussianSuperGLUE: A Russian Language Understanding Evaluation Benchmark","first_author":"Tatiana Shavrina","url":null},"license":{"name":"MIT License","url":"https://github.com/RussianNLP/RussianSuperGLUE/blob/master/LICENSE"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Natural Language Inference","url":"/task/natural-language-inference","datasets_with_task":"/datasets/task/natural-language-inference"},{"name":"Lexical Entailment","url":"/task/lexical-entailment","datasets_with_task":"/datasets/task/lexical-entailment"}],"languages":[{"name":"Russian","url":"/datasets/language/russian"}],"variants":["TERRa"],"data_loaders":[],"num_papers_in_archive":7,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/natural-language-inference-on-terra","task":"Natural Language Inference","dataset_variant":"TERRa","rows":22,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"Human Benchmark","paper":"/paper/russiansuperglue-a-russian-language","metrics":{"Accuracy":"0.92"},"code_links":[{"title":"RussianNLP/RussianSuperGLUE","url":"https://github.com/RussianNLP/RussianSuperGLUE"},{"title":"RussianNLP/MOROCCO","url":"https://github.com/RussianNLP/MOROCCO"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/unreasonable-effectiveness-of-rule-based","title":"Unreasonable Effectiveness of Rule-Based Heuristics in Solving Russian SuperGLUE Tasks","date":"2021-05-03","rows_on_this_dataset":3,"code_links":0,"syntology":null},{"paper":"/paper/russiansuperglue-a-russian-language","title":"RussianSuperGLUE: A Russian Language Understanding Evaluation Benchmark","date":"2020-10-29","rows_on_this_dataset":2,"code_links":2,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":1,"samples_ran":1,"samples_unverified":0,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/mt5-a-massively-multilingual-pre-trained-text","title":"mT5: A massively multilingual pre-trained text-to-text transformer","date":"2020-10-22","rows_on_this_dataset":1,"code_links":8,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":13,"samples_ran":5,"samples_unverified":8,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}}],"syntology_totals":{"read_at":"2026-09-25T09:33:49+00:00","papers_with_samples":2,"samples_harvested":14,"samples_ran":6,"samples_unverified":8,"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."}