{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/a-dataset-for-plain-language-adaptation-of","title":"A Dataset for Plain Language Adaptation of Biomedical Abstracts","arxiv_id":"2210.12242","date":"2022-10-21","proceeding":null,"authors":["Kush Attal","Brian Ondov","Dina Demner-Fushman"],"abstract":"Though exponentially growing health-related literature has been made available to a broad audience online, the language of scientific articles can be difficult for the general public to understand. Therefore, adapting this expert-level language into plain language versions is necessary for the public to reliably comprehend the vast health-related literature. Deep Learning algorithms for automatic adaptation are a possible solution; however, gold standard datasets are needed for proper evaluation. Proposed datasets thus far consist of either pairs of comparable professional- and general public-facing documents or pairs of semantically similar sentences mined from such documents. This leads to a trade-off between imperfect alignments and small test sets. To address this issue, we created the Plain Language Adaptation of Biomedical Abstracts dataset. This dataset is the first manually adapted dataset that is both document- and sentence-aligned. The dataset contains 750 adapted abstracts, totaling 7643 sentence pairs. Along with describing the dataset, we benchmark automatic adaptation on the dataset with state-of-the-art Deep Learning approaches, setting baselines for future research.","url_abs":"https://arxiv.org/abs/2210.12242v1","url_pdf":"https://arxiv.org/pdf/2210.12242v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"a-dataset-for-plain-language-adaptation-of","repo_url":"https://github.com/attal-kush/PLABA","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"articles","task_name":"Articles"},{"task_slug":"sentence","task_name":"Sentence"}],"methods":[{"method_slug":"test","method_name":"Test"}],"datasets_introduced":[{"slug":"plaba","name":"PLABA","full_name":"Plain Language Adaptation of Biomedical Abstracts"}],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2210.12242","atlas_url":"https://app.syntology.ai/?focus=2210.12242","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.12242"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/attal-kush/PLABA","reach":null}],"summary":{"ran_honours":2},"by_repo_kind":{"official":{"samples":2,"ran":2,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":2,"samples":[{"code_sha256_prefix":"697060ab0524f257","entry":"D_SARIngram","repo":"attal-kush/PLABA","repo_kind":"official","path":"Metrics.py","file_url":"https://github.com/attal-kush/PLABA/blob/HEAD/Metrics.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"697060ab0524f257"}},{"code_sha256_prefix":"e5d2c53a58697e53","entry":"count_length","repo":"attal-kush/PLABA","repo_kind":"official","path":"Metrics.py","file_url":"https://github.com/attal-kush/PLABA/blob/HEAD/Metrics.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e5d2c53a58697e53"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}