DADAlytics - Linked Jazz - Women of Jazz - Zena Latto Project - Local 496 Project - The Mary Berenson Project - Drawings of the Florentine Painters

DADAlytics logo

With the generous support from IMLS, the Semantic Lab Team has developed a prototype of DADAlytics, a modular tool that performs supervised entity extraction from archival documents for generating linked open datasets, lowering barriers to entry for institutions seeking to create linked open data from archival materials. This project builds on previous work to develop the Linked Jazz Transcript Analyzer, extending that tool’s functionality and making it more widely available for use by other institutions. Grant funds supported the research and data gathering needed to inform the redesign and reengineering of the tool, including an environmental scan, a series of meetings with key stakeholders, and the development of a prototype.

Grant Information
Preliminary Project Proposal
Final Project Proposal
Grant Announcement

Stakeholder Meetings
6 November 2017 - Agenda
6 November 2017 - Meeting Notes

Named-Entity Recognition Toolchain
About the Toolchain
Toolchain Demo

Tool Testing
Overview of Documents Used for Tool Testing
Manual Markup vs. DADAlytics Automatic Extraction

Institute of Museum and Library Services
Tulane University - Jeff Rubin
Digital Initiatives & Publishing, Howard-Tilton Memorial Library

Harvard University - Ilaria della Monica
Villa I Tatti Center for Italian Renaissance Studies

University of Minnesota - Cecily Marcus
Umbra Search, Givens Collection of African-American Literature

Carnegie Hall - Robert Hudson

Whitney Museum of American Art - Farris Wahbeh
Research Resources

Linked Jazz logo

The jazz community is defined by the relationships that exist between musicians, mentors, rivals, lovers and friends. Exposing these connections and identifying the rich networks they produce is the aim of Linked Jazz. The Linked Jazz project investigates the application of Linked Open Data technologies to digitized jazz history materials to uncover meaningful connections between documents and data related to the personal and professional lives of jazz artists.

The Linked Open Data tools and methods developed for the Linked Jazz project have opened new and unprecedented avenues of research and community engagement. Our work has generated the subprojects listed below.

With the support of:

The Mary Berenson Project logo

An Exploratory Study into the Mining and Linking of the Mary Berenson Archive at Villa I Tatti, Harvard University Center for Italian Renaissance Studies

The Mary Berenson Project investigates the application of computational analysis techniques to archival documents to automate the generation of linked open data with the goal of creating networked narratives. Supported by the Pratt School of Information Faculty Innovation Fund and in collaboration with The Harvard University Center for Italian Renaissance Studies, Villa I Tatti, the project focuses on the collections of diaries and letters from the Berenson Archives held at the Villa I Tatti.

Mary Berenson (Philadelphia, PA 1864-1944 Florence, Italy) was an art historian, critic and wife of Italian Renaissance art historian Bernard Berenson. While she worked in the shadow of her more renowned husband, Mary is now credited with having had significant influence over his scholarly work and having been instrumental in developing the rich social circle of intellectuals, artists and art collectors that surrounded the couple during the years spent at their residence Villa I Tatti in Florence—now The Harvard University Center for Italian Renaissance Studies.

Mary Berenson’s archive, a rich collection of letters, personal diaries, literary journals and notes, both published and unpublished, is part of the Bernard and Mary Berenson Papers (1880-2002) held at the Biblioteca Berenson at the Villa I Tatti. This trove of primary source material has enormous historical value, but has yet to be fully explored.

Photograph of Mary Berenson in the Public Domain

With the support of:

Pratt Institute School of Information logo The Euopean Association for Digital Humanities logo

Drawings of the Florentine Painters logo

Florentine Renaissance Drawings: A Linked Catalogue for the Semantic Web

The Drawings of the Florentine Painters is an online resource that allows users to simultaneously search through all three editions of art historian Bernard Berenson’s seminal work “The Drawings of the Florentine Painters”. This project is supported by a 2015 Digital Resources Grant awarded by the Samuel H. Kress Foundation to Villa I Tatti, The Harvard University Center for Italian Renaissance Studies.

Principle investigators are Lukas Klic and Jonathan Nelson of Villa I Tatti. Design, methodology, technical advising, and project management by Matt Miller, Cristina Pattuelli, and Alexandra Provo. For further information, please see the Background of The Project, Full List of Contributors, or the 2017 ARLIS/NA Review of “The Drawings of the Florentine Painters”. The entire dataset is openly available in RDF for reuse under a Creative Commons Attribution-ShareAlike license.

Recent Publications:
Klic, L., Nelson, J.K., Pattuelli, M. C., and Provo, A. (2018). Florentine Renaissance Drawings: A linked catalog for the Semantic Web. Art Documentation. (37)1, 33-43. DOI:

Klic, L., Miller, M., Nelson, J., Pattuelli, M. C. and Provo, A. (2017). The drawings of the Florentine painters: From print catalog to Linked Open Data. The Code4Lib Journal, 38(October 2017).