Widespread efforts by libraries, archives, and museums have drastically improved digital access to cultural heritage collections. Yet, scholars and the public alike face a persistent challenge: how to explore and analyze these collections, which frequently contain millions of items, amounting to terabytes and even petabytes of data. Moreover, these collections often suffer from imperfect metadata, perpetuating unevenness surrounding discoverability. My interdisciplinary research in this field of “computing cultural heritage” addresses this question by bringing together approaches from artificial intelligence, library & information science, and the digital humanities in order to build, evaluate, and critically analyze large-scale search systems for digital collections. In this presentation, I will share my genealogy of work in this space, with a particular focus on two case studies. The first case study is my work with LC Labs to develop Newspaper Navigator to extract visual content from 16+ million newspaper pages and build an AI-powered search system of over 1.5 million extracted photographs. The second case study is my ongoing work to re-imagine search and discovery for .gov domain web archives. I will conclude with a horizon of computing cultural heritage, toward guiding principles that will shape this work and AI4LAM in the coming decade. This includes a particular focus on responsible AI practices.
Biography: Benjamin Charles Germain Lee is an incoming Assistant Professor in the Information School at the University of Washington. He is currently a Kluge Fellow in Digital Studies at the Library of Congress. Ben received his Ph.D. in Computer Science & Engineering from the University of Washington, which was supported by a National Science Foundation Graduate Research Fellowship in machine learning. He served as the inaugural Digital Humanities Associate Fellow at the United States Holocaust Memorial Museum, as well as a Visiting Fellow in Harvard’s History Department. Ben also served as a 2020 Innovator in Residence at the Library of Congress and the 2020-2021 Richard and Ina Willner Memorial Fellow in the Stroum Center for Jewish Studies at the University of Washington.