The goal of the T3 research lab is to improve access to digital image collections in museums and libraries for art historians, museum professionals, and the general public. This project combines text mining, social tagging, and trust inferencing to enrich metadata and personalize retrieval. The initial T3 project, funded by the U.S. Institute for Museum and Library Services (IMLS) under a National Leadership Grant for Research to the University of Maryland, is a collaborative, cross-disciplinary project comprised of academic researchers, digital librarians, and museum professionals. We explore the application of techniques from computational linguistics and social tagging to the creation of linkages between the formal academic language of museums and the vernacular language of social tagging. We use text mining algorithms, taxonomies, and lexical resources to identify suggested terms and aid users in tagging images and then retrieving images based on tags assigned from many different perspectives. We use the trust a user places in particular metadata sources to infer a weighted set of results for their search. Considering these weights in ranking algorithms—along with term relationships from lexical resources—will produce high-quality, focused, personalized retrieval of works from museum collections. Related work, funded by the Library of Congress under a National Digital Information Infrastructure and Preservation Program (NDIIPP) grant to the University of Illinois at Urbana-Champaign Library, explores the problem space of automatically recognizing, extracting, classifying, and disambiguating named entities (e.g., the names of people, places, and organizations) from digitized text. We develop, evaluate and link Named Entity Recognition (NER) and Entity Resolution with tools used for search and access. Name identification and extraction tools, particularly when integrated with a resolution into an authority file (e.g., WorldCat Identities, Wikipedia, etc.), can enhance reliable subject access for a document collection, improving document discoverability by end-users.

The T3 project was supported in part by a grant from the Institute of Museum and Library Services (IMLS). Any views, findings, conclusions or recommendations expressed in this website do not necessarily represent those of IMLS or any other sponsor.