Lowering the burden of medical translation by enabling international healthcare professionals as human editors of machine translations

让国际医疗保健专业人员担任机器翻译的人工编辑，减轻医学翻译的负担

• 批准号: 10603983
• 负责人: Katherine Riestenberg
• 金额: $ 26.58万
• 依托单位: TRANSCENDENT INTERNATIONAL, LLC
• 依托单位国家: 美国
• 财政年份: 2022
• 资助国家: 美国
• 起止时间: 2022-09-26 至 2023-03-31
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/10603983
• 关键词: Address; Algorithms; Back; Benchmarking; Caring; Civil Rights; Communities; E-learning; Evaluation; Exercise; Face; Financial Support; Goals; Health; Health Personnel; Health Professional; Health system; Healthcare; Hospitals; Human; Hybrids; Incentives; Individual; Infrastructure; Institution; International; Interview; Joints; Knowledge; Language; Laws; Learning; Libraries; Limited English Proficiency; Mainstreaming; Medical; Medical Students; Metadata; Mission; Multilingualism; Natural Language Processing; Nurses; Online Systems; Output; Patient Care; Patients; Phase; Philippines; Polishes; Population; Practice Management; Process; Production; Public Health Schools; Reduce health disparities; Research; Severities; Small Business Innovation Research Grant; Source; Speed; Students; Surveys; System; Text; Time; Translating; Translation Process; Translations; Update; Vendor; Woman; base; bilingualism; cost; cost effectiveness; crowdsourcing; experience; feasibility testing; global health; health care availability; health disparity; improved; innovation; machine translation; meetings; neglect; novel; pressure; product development; prototype; quality assurance; reconstitution; recruit

PROJECT SUMMARY Language access solutions in healthcare have focused almost exclusively on the provision of verbal medical interpretation, despite federal and state laws that mandate translation of written information for patients with limited English proficiency (LEP). In recent years, machine translation (MT) has made significant strides, but when it comes to mission-critical technical materials such as healthcare information, the accuracy rate of machine-only translations plummets. Thus, experts recommend MT as a starting point for translating health-related material then supplementing with human quality assurance editing. However, coordinating machine translation with bilingual human editors who have technical medical knowledge is a challenge, especially for less commonly supported languages. Translation vendors currently pass on the associated costs of human assistance to healthcare institutions. The Canopy Translate project will address these deficits by implementing a novel, human-assisted machine translation (HAMT) process. The envisioned workflow management platform will leverage MT engines to expedite the initial rendering of source documents into a target language, then invite bilingual healthcare professionals around the world to apply human editing to the machine-generated translation. The bilingual contributors, who will gain complimentary access to our Medical English eLearning courses as an incentive for their participation, will complete the editing task through gamified learning exercises. For example, a nurse in the Philippines has native fluency in Tagalog and advanced general English but desires to improve his medical English. He can edit a machine-generated Tagalog translation one sentence at a time in the form of a gamified activity. Other contributors will edit the same text for additional quality assurance to form the final, polished version in Tagalog. The system will then organize the final translated content into a reusable document library. In Phase I, we will test the feasibility of this hybrid HAMT approach for medical content. Upon meeting feasibility benchmarks, we will advance to Phase II, during which we will create a minimum viable product, encompassing several novel natural language processing (NLP) algorithms, and evaluate the translation output according to a set of quality benchmarks. If successful, this project will significantly improve the availability, speed, and cost-effectiveness of producing multilingual health content, with potential to reduce health disparities in LEP populations.

项目概要 医疗保健领域的语言访问解决方案几乎完全专注于提供口头医疗服务 尽管联邦和州法律强制要求为患有以下疾病的患者翻译书面信息，但仍需进行口译 英语水平有限 (LEP)。近年来，机器翻译 (MT) 取得了长足的进步，但 当涉及医疗保健信息等关键任务技术材料时， 仅机器翻译的数量直线下降。因此，专家建议将机器翻译作为翻译的起点 健康相关材料，然后辅以人工质量保证编辑。然而，协调 机器翻译与具有医学技术知识的双语人类编辑是一个挑战， 特别是对于不太受支持的语言。翻译供应商目前转嫁相关成本 对医疗机构的人力援助。 Canopy Translate 项目将通过以下方式解决这些缺陷 实施新颖的人工辅助机器翻译（HAMT）流程。设想的工作流程 管理平台将利用 MT 引擎来加快源文档的初始渲染速度 目标语言，然后邀请世界各地的双语医疗保健专业人员对目标语言进行人工编辑 机器生成的翻译。双语贡献者将免费获得我们的医疗服务 英语在线学习课程作为对他们参与的激励，将通过游戏化的方式完成编辑任务 学习练习。例如，菲律宾的一名护士拥有流利的他加禄语和高级语言 普通英语，但希望提高他的医学英语。他可以编辑机器生成的他加禄语 以游戏化活动的形式一次翻译一个句子。其他贡献者将编辑相同的文本 额外的质量保证，以形成他加禄语的最终抛光版本。然后系统会组织 最终翻译的内容到可重用的文档库中。在第一阶段，我们将测试这种混合动力的可行性 适用于医疗内容的 HAMT 方法。在达到可行性基准后，我们​​将进入第二阶段，期间 我们将创建一个最小可行产品，包含几种新颖的自然语言处理 （NLP）算法，并根据一组质量基准评估翻译输出。如果成功的话， 该项目将显着提高多语言制作的可用性、速度和成本效益 健康内容，有可能减少 LEP 人群的健康差异。