{"url":"/dataset/biosses","name":"BIOSSES","full_name":"Biomedical Semantic Similarity Estimation System","description_markdown":"The BIOSSES data set comprises total 100 sentence pairs all of which were selected from the \"[TAC2 Biomedical Summarization Track Training Data Set](https://tac.nist.gov/2014/BiomedSumm/)\" .\r\n\r\nThe sentence pairs were evaluated by five different human experts that judged their similarity and gave scores in a range [0-4]. Our guideline was prepared based on SemEval 2012 Task 6 Guideline.\r\n\r\nImage source: [BIOSSES](https://tabilab.cmpe.boun.edu.tr/BIOSSES/DataSet.html)","description_withheld":null,"homepage":"https://tabilab.cmpe.boun.edu.tr/BIOSSES/DataSet.html","introduced_date":"2017-07-15","introduced_date_note":null,"introduced_by":{"paper":"/paper/biosses-a-semantic-sentence-similarity","title":"BIOSSES: A Semantic Sentence Similarity Estimation System for the Biomedical Domain","first_author":"Gizem Sogancioglu","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"},{"name":"Medical","url":"/datasets/modality/medical"}],"tasks":[{"name":"Semantic Similarity","url":"/task/semantic-similarity","datasets_with_task":"/datasets/task/semantic-similarity"},{"name":"Sentence Embeddings For Biomedical Texts","url":"/task/sentence-embeddings-for-biomedical-texts","datasets_with_task":"/datasets/task/sentence-embeddings-for-biomedical-texts"},{"name":"Sentence Similarity","url":"/task/sentence-similarity","datasets_with_task":"/datasets/task/sentence-similarity"}],"languages":[],"variants":["BIOSSES"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/tabilab/biosses","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/qanastek/Biosses-BLUE","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/biosses","frameworks":["tf","pytorch","jax"]}],"num_papers_in_archive":38,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/sentence-embeddings-for-biomedical-texts-on","task":"Sentence Embeddings For Biomedical Texts","dataset_variant":"BIOSSES","rows":14,"metrics":["Pearson Correlation"],"first_row_in_archive_order":{"model":"Supervised combination of: Jaccard, Q-gram, sent2vec, Paragraph vector DM, skip-thoughts, fastText","paper":"/paper/neural-sentence-embedding-models-for-semantic","metrics":{"Pearson Correlation":"0.871"},"code_links":[{"title":"kathrinblagec/neural-sentence-embedding-models-for-biomedical-applications","url":"https://github.com/kathrinblagec/neural-sentence-embedding-models-for-biomedical-applications"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/semantic-similarity-on-biosses","task":"Semantic Similarity","dataset_variant":"BIOSSES","rows":3,"metrics":["Pearson Correlation"],"first_row_in_archive_order":{"model":"BioLinkBERT (large)","paper":"/paper/linkbert-pretraining-language-models-with","metrics":{"Pearson Correlation":"0.9363"},"code_links":[{"title":"michiyasunaga/LinkBERT","url":"https://github.com/michiyasunaga/LinkBERT"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/linkbert-pretraining-language-models-with","title":"LinkBERT: Pretraining Language Models with Document Links","date":"2022-03-29","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":14,"samples_ran":0,"samples_unverified":14,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/neural-sentence-embedding-models-for-semantic","title":"Neural sentence embedding models for semantic similarity estimation in the biomedical domain","date":"2021-10-01","rows_on_this_dataset":9,"code_links":1,"syntology":null},{"paper":"/paper/transfer-learning-in-biomedical-natural","title":"Transfer Learning in Biomedical Natural Language Processing: An Evaluation of BERT and ELMo on Ten Benchmarking Datasets","date":"2019-06-13","rows_on_this_dataset":1,"code_links":4,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":2,"samples_ran":0,"samples_unverified":2,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/biosentvec-creating-sentence-embeddings-for","title":"BioSentVec: creating sentence embeddings for biomedical texts","date":"2018-10-22","rows_on_this_dataset":4,"code_links":4,"syntology":null},{"paper":"/paper/biosses-a-semantic-sentence-similarity","title":"BIOSSES: A Semantic Sentence Similarity Estimation System for the Biomedical Domain","date":"2017-07-15","rows_on_this_dataset":1,"code_links":0,"syntology":null}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":2,"samples_harvested":16,"samples_ran":0,"samples_unverified":16,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":2,"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."}