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

项目总结 医疗保健中的语言获取解决方案几乎完全专注于提供口头医疗 尽管联邦和州法律要求为患有癌症的患者翻译书面信息 英语水平有限(LEP)。近年来，机器翻译取得了长足的进步，但 当涉及到医疗保健信息等任务关键型技术材料时， 纯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 与健康相关的材料，然后补充人类质量保证编辑。然而，协调 与具有技术医学知识的双语人类编辑一起进行机器翻译是一个挑战， 尤其是对于不太受支持的语言。翻译供应商目前将相关成本转嫁给 人类对医疗机构的援助。Canopy翻译项目将通过以下方式解决这些不足 实现一种新颖的人工辅助机器翻译(HAMT)过程。设想的工作流程 管理平台将利用机器翻译引擎加快将源文档初始呈现为 目标语言，然后邀请世界各地的双语医疗专业人员将人工编辑应用于 机器生成的翻译。双语投稿人，他们将获得免费访问我们的医疗 英语电子学习课程作为他们参与的一种激励，将通过游戏化完成编辑任务 学习练习。例如，菲律宾的一名护士有一口流利的他加路语和高级英语 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路文 以游戏化活动的形式一次翻译一个句子。其他投稿人将编辑相同的文本 额外的质量保证，以形成他加路文的最终抛光版本。然后，系统将组织 将最终翻译的内容转换为可重复使用的文档库。在第一阶段，我们将测试这种混合动力的可行性 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，在 我们将创建一个最低限度可行的产品，包括几个新的自然语言处理 (NLP)算法，并根据一组质量基准评估翻译输出。如果成功， 该项目将显著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人群的健康差距。

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.