{"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/generalizing-over-long-tail-concepts-for","title":"Generalizing over Long Tail Concepts for Medical Term Normalization","arxiv_id":"2210.11947","date":"2022-10-21","proceeding":null,"authors":["Beatrice Portelli","Simone Scaboro","Enrico Santus","Hooman Sedghamiz","Emmanuele Chersoni","Giuseppe Serra"],"abstract":"Medical term normalization consists in mapping a piece of text to a large number of output classes. Given the small size of the annotated datasets and the extremely long tail distribution of the concepts, it is of utmost importance to develop models that are capable to generalize to scarce or unseen concepts. An important attribute of most target ontologies is their hierarchical structure. In this paper we introduce a simple and effective learning strategy that leverages such information to enhance the generalizability of both discriminative and generative models. The evaluation shows that the proposed strategy produces state-of-the-art performance on seen concepts and consistent improvements on unseen ones, allowing also for efficient zero-shot knowledge transfer across text typologies and datasets.","url_abs":"https://arxiv.org/abs/2210.11947v2","url_pdf":"https://arxiv.org/pdf/2210.11947v2.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":"generalizing-over-long-tail-concepts-for","repo_url":"https://github.com/ailabudinegit/ontology-pretraining-code","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"attribute","task_name":"Attribute"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2210.11947","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.11947"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+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":"deterministic:regex_extraction","url":"https://github.com/cambridgeltl/sapbert","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/GanjinZero/CODER","reach":null}],"summary":{"ran":1,"unverified":3},"by_repo_kind":{"found_in_text":{"samples":4,"ran":1,"repositories":2}},"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":4,"samples":[{"code_sha256_prefix":"6c111eafbced44f7","entry":"MultiSimilarityLoss","repo":"GanjinZero/CODER","repo_kind":"found_in_text","path":"pretrain/loss.py","file_url":"https://github.com/GanjinZero/CODER/blob/HEAD/pretrain/loss.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"6c111eafbced44f7"}},{"code_sha256_prefix":"334e9e0c4d7d65cc","entry":"check_k","repo":"cambridgeltl/sapbert","repo_kind":"found_in_text","path":"evaluation/utils.py","file_url":"https://github.com/cambridgeltl/sapbert/blob/HEAD/evaluation/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"334e9e0c4d7d65cc"}},{"code_sha256_prefix":"e7ee5f7a818a94d9","entry":"check_label","repo":"cambridgeltl/sapbert","repo_kind":"found_in_text","path":"evaluation/utils.py","file_url":"https://github.com/cambridgeltl/sapbert/blob/HEAD/evaluation/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"e7ee5f7a818a94d9"}},{"code_sha256_prefix":"25c16c8be2b5a879","entry":"evaluate_topk_acc","repo":"cambridgeltl/sapbert","repo_kind":"found_in_text","path":"evaluation/utils.py","file_url":"https://github.com/cambridgeltl/sapbert/blob/HEAD/evaluation/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"25c16c8be2b5a879"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}