Fostering Collaborative Breakthroughs in Heritage Science through Machine Learning and Data Science

25年前，美国国家科学基金会对数字图书馆计划的投资刺激了文化馆藏的数字化，并开发了以以前不可能的方式分析这些馆藏的工具。本次会议汇集了遗产和计算机科学方面的专家，以研究这方面的最新进展，并利用数据科学、人工智能、机器学习和成像等一系列工具和技术，确定对具有文化意义的文物藏品进行新颖研究的具体需求和机会。会议的重点是如何设计和实施人工智能系统，以处理遗产收藏的关键问题，例如处理损害，在不造成额外损害的情况下提取有用的数据，使来自不同收藏的数据能够进行有意义的比较，并标记数据以支持机器学习，以及制定代表框架标准以支持学术进步。会议组织者将制作并传播一份共识报告，总结新的技术方法和解决整个文化遗产收藏类别中长期存在的问题的途径。会议的对话和协同活动将扩展围绕成像、人工智能和数据科学的传统思维和分析框架，这将解决具有快速传播到文化遗产潜力的基本挑战。该奖项反映了美国国家科学基金会的法定使命，并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，被认为值得支持。

A quarter century ago, NSF’s investment in the Digital Library Initiative stimulated the digitization of cultural collections, and the development of tools to analyze those collections in ways that were not possible before. This conference brings together experts in heritage and computer science to examine the state of the art in this effort and to identify specific needs and opportunities for novel research on collections of culturally significant artifacts using the whole range of tools and techniques from data science, artificial intelligence, machine learning and imaging. The conference is focused on the how AI systems can be designed and implemented to deal with critical problems for heritage collections such as dealing with damage, extracting useful data without causing additional damage, enabling data from disparate collections to be meaningfully compared and labeling data to support machine learning, and developing standards for representational frameworks to support scholarly advances. The conference organizers will produce and disseminate a consensus report summarizing the pathways to new technical approaches and solutions to long-standing problems within entire classes of cultural heritage collections. The dialog and synergistic activities of the meeting will expand the conventional thinking and the analysis framework around imaging, artificial intelligence, and data science, which will address fundamental challenges with the potential for rapid diffusion into cultural heritage.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.