FAI: A Human-Centered Approach to Developing Accessible and Reliable Machine Translation

FAI：以人为本的方法来开发可访问且可靠的机器翻译

• 批准号: 2147292
• 负责人: Marine Carpuat
• 金额: $ 39.3万
• 依托单位: University of Maryland, College Park
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2022
• 资助国家: 美国
• 起止时间: 2022-03-01 至 2025-02-28
• 项目状态: 未结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2147292&HistoricalAwards=false
• 关键词: FAI; Human; Centered; Approach; Developing

This Fairness in AI project aims to develop technology to reliably enhance cross-lingual communication in high-stakes contexts, such as when a person needs to communicate with someone who does not speak their language to get health care advice or apply for a job. While machine translation technology is frequently used in these conditions, existing systems often make errors that can have severe consequences for a patient or a job applicant. Further, it is challenging for people to know when automatic translations might be wrong when they do not understand the source or target language for translation. This project addresses this issue by developing accessible and reliable machine translation for lay users. It will provide mechanisms to guide users to recognize and recover from translation errors, and help them make better decisions given imperfect translations. As a result, more people will be able to use machine translation reliably to communicate across language barriers, which can have far-reaching positive consequences on their lives.Specifically, this project contributes advances in natural language processing and interaction design for a bot that can be added to any text-based conversation, where it can play a role similar to an interpreter. The bot will guide users to write appropriate inputs for machine translation, help users understand outputs, and intervene when it detects miscommunication and conversational breakdowns. The design of the bot will follow a human-centered design process, consisting of need-finding studies, iterative system development and deployment, and user evaluations via controlled experiments. On the back-end, the bot will rely on quality estimation models that automatically detect translation errors to produce useful guidance for end-users. The data, models, and design recommendations generated by this project will advance computational research in multiple ways. It will lead to new machine translation quality estimation techniques that take into account the impact of errors on end-users; it will expand the scope of explainable artificial intelligence research to encompass the considerable risks and harms caused by language generation tools, and it will generate new interface design that assists lay users' sense making of artificial intelligence systems.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.

该项目旨在开发技术，以可靠地增强高风险环境中的跨语言沟通，例如当一个人需要与不会说他们的语言的人沟通以获得医疗保健建议或申请工作时。虽然机器翻译技术经常用于这些情况，但现有系统经常会出错，可能会对患者或求职者造成严重后果。此外，当人们不理解翻译的源语言或目标语言时，知道自动翻译何时可能是错误的是具有挑战性的。该项目通过为外行用户开发可访问和可靠的机器翻译来解决这个问题。它将提供指导用户识别翻译错误并从中恢复的机制，并帮助他们在不完美的翻译中做出更好的决定。因此，越来越多的人将能够使用机器翻译可靠地跨越语言障碍进行交流，这可能会对他们的生活产生深远的积极影响。具体来说，该项目为机器人的自然语言处理和交互设计做出了贡献，该机器人可以添加到任何基于文本的对话中，在那里它可以扮演类似于翻译的角色。机器人将引导用户为机器翻译编写适当的输入，帮助用户理解输出，并在检测到误解和对话故障时进行干预。机器人的设计将遵循以人为本的设计过程，包括需求发现研究、迭代系统开发和部署以及通过受控实验进行的用户评估。在后端，机器人将依赖于质量评估模型，自动检测翻译错误，为最终用户提供有用的指导。该项目产生的数据、模型和设计建议将以多种方式推进计算研究。这将导致新的机器翻译质量评估技术，考虑到错误对最终用户的影响;它将扩大可解释的人工智能研究的范围，以涵盖语言生成工具造成的相当大的风险和危害，它将产生新的界面设计，帮助非专业用户对人工智能系统的理解。该奖项反映了NSF的法定使命，通过使用基金会的知识价值和更广泛的影响审查标准进行评估，认为值得支持。

项目成果

Bridging Background Knowledge Gaps in Translation with Automatic Explicitation

通过自动解释弥合翻译中的背景知识差距

• DOI: 10.18653/v1/2023.emnlp-main.603
• 发表时间: 2023
• 期刊: Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
• 作者: Han, HyoJung;Boyd-Graber, Jordan;Carpuat, Marine
• 通讯作者: Carpuat, Marine

Quality Estimation via Backtranslation at the WMT 2022 Quality Estimation Task

WMT 2022 质量评估任务中通过回译进行质量评估

• 发表时间: 2022
• 期刊: Proceedings of the Seventh Conference on Machine Translation (WMT
• 作者: Sweta Agrawal, Nikita Mehandru

Explaining with Contrastive Phrasal Highlighting: A Case Study in Assisting Humans to Detect Translation Differences

用对比短语突出显示进行解释：协助人类检测翻译差异的案例研究

• DOI: 10.18653/v1/2023.emnlp-main.690
• 发表时间: 2023
• 期刊: Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
• 作者: Briakou, Eleftheria;Goyal, Navita;Carpuat, Marine
• 通讯作者: Carpuat, Marine

Physician Detection of Clinical Harm in Machine Translation: Quality Estimation Aids in Reliance and Backtranslation Identifies Critical Errors

机器翻译中临床危害的医生检测：质量估计有助于信赖和反向翻译识别关键错误

• DOI: 10.18653/v1/2023.emnlp-main.712
• 发表时间: 2023
• 期刊: Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
• 作者: Mehandru, Nikita;Agrawal, Sweta;Xiao, Yimin;Gao, Ge;Khoong, Elaine;Carpuat, Marine;Salehi, Niloufar
• 通讯作者: Salehi, Niloufar