{"url":"/task/sentence-embeddings-for-biomedical-texts","name":"Sentence Embeddings For Biomedical Texts","slug":"sentence-embeddings-for-biomedical-texts","description_markdown":null,"categories":[{"name":"Natural Language Processing","url":"/area/natural-language-processing"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":3,"papers_with_code":2,"benchmarks":2,"benchmark_tables_in_archive":2,"benchmark_tables_shown":2,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":1,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/sentence-embeddings-for-biomedical-texts-on","slug":"sentence-embeddings-for-biomedical-texts-on","dataset":"BIOSSES","dataset_url":"/dataset/biosses","rows_in_archive":14,"metrics":["Pearson Correlation"],"first_row_in_archive_order":{"model":"Supervised combination of: Jaccard, Q-gram, sent2vec, Paragraph vector DM, skip-thoughts, fastText","paper_title":"Neural sentence embedding models for semantic similarity estimation in the biomedical domain","paper_url":"/paper/neural-sentence-embedding-models-for-semantic","paper_date":"2021-10-01","arxiv_id":"2110.15708","code_links":[{"title":"kathrinblagec/neural-sentence-embedding-models-for-biomedical-applications","url":"https://github.com/kathrinblagec/neural-sentence-embedding-models-for-biomedical-applications"}],"syntology":null}},{"leaderboard":"/sota/sentence-embeddings-for-biomedical-texts-on-2","slug":"sentence-embeddings-for-biomedical-texts-on-2","dataset":"MedSTS","dataset_url":null,"rows_in_archive":4,"metrics":["Pearson Correlation"],"first_row_in_archive_order":{"model":"BioSentVec (PubMed + MIMIC-III)","paper_title":"BioSentVec: creating sentence embeddings for biomedical texts","paper_url":"/paper/biosentvec-creating-sentence-embeddings-for","paper_date":"2018-10-22","arxiv_id":"1810.09302","code_links":[{"title":"ncbi-nlp/BioSentVec","url":"https://github.com/ncbi-nlp/BioSentVec"},{"title":"ncbi-nlp/BLUE_Benchmark","url":"https://github.com/ncbi-nlp/BLUE_Benchmark"},{"title":"ncbi-nlp/BioWordVec","url":"https://github.com/ncbi-nlp/BioWordVec"},{"title":"ESBigeard/paper_graph","url":"https://github.com/ESBigeard/paper_graph"}],"syntology":null}}],"datasets":[{"url":"/dataset/biosses","name":"BIOSSES","full_name":"Biomedical Semantic Similarity Estimation System","num_papers_in_archive":38}],"subtasks":[],"parent_tasks":[{"url":"/task/sentence-embeddings","name":"Sentence Embeddings"}],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":2,"of":2,"tagged_in_all":3,"items":[{"url":"/paper/biosentvec-creating-sentence-embeddings-for","title":"BioSentVec: creating sentence embeddings for biomedical texts","date":"2018-10-22","arxiv_id":"1810.09302","repositories_listed":4,"syntology":null},{"url":"/paper/neural-sentence-embedding-models-for-semantic","title":"Neural sentence embedding models for semantic similarity estimation in the biomedical domain","date":"2021-10-01","arxiv_id":"2110.15708","repositories_listed":1,"syntology":null}],"syntology_records":0,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}