{"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/embedding-transfer-for-low-resource-medical","title":"Embedding Transfer for Low-Resource Medical Named Entity Recognition: A Case Study on Patient Mobility","arxiv_id":"1806.02814","date":"2018-06-07","proceeding":"WS 2018 7","authors":["Denis Newman-Griffis","Ayah Zirikly"],"abstract":"Functioning is gaining recognition as an important indicator of global\nhealth, but remains under-studied in medical natural language processing\nresearch. We present the first analysis of automatically extracting\ndescriptions of patient mobility, using a recently-developed dataset of free\ntext electronic health records. We frame the task as a named entity recognition\n(NER) problem, and investigate the applicability of NER techniques to mobility\nextraction. As text corpora focused on patient functioning are scarce, we\nexplore domain adaptation of word embeddings for use in a recurrent neural\nnetwork NER system. We find that embeddings trained on a small in-domain corpus\nperform nearly as well as those learned from large out-of-domain corpora, and\nthat domain adaptation techniques yield additional improvements in both\nprecision and recall. Our analysis identifies several significant challenges in\nextracting descriptions of patient mobility, including the length and\ncomplexity of annotated entities and high linguistic variability in mobility\ndescriptions.","url_abs":"http://arxiv.org/abs/1806.02814v1","url_pdf":"http://arxiv.org/pdf/1806.02814v1.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":"embedding-transfer-for-low-resource-medical","repo_url":"https://github.com/drgriffis/NeuralVecmap","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"domain-adaptation","task_name":"Domain Adaptation"},{"task_slug":"medical-named-entity-recognition","task_name":"Medical Named Entity Recognition"},{"task_slug":"cg","task_name":"NER"},{"task_slug":"named-entity-recognition-1","task_name":"Named Entity Recognition"},{"task_slug":"named-entity-recognition-ner","task_name":"Named Entity Recognition (NER)"},{"task_slug":"word-embeddings","task_name":"Word Embeddings"},{"task_slug":"named-entity-recognition","task_name":"named-entity-recognition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1806.02814","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}