The Newspaper Navigator Dataset: Extracting Headlines and Visual Content from 16 Million Historic Newspaper Pages in Chronicling America.

@inproceedings{lee-2020-newspaper, author = {Benjamin Charles Germain Lee and Jaime Mears and Eileen Jakeway and Meghan Ferriter and Chris Adams and Nathan Yarasavage and Deborah Thomas and Kate Zwaard and Daniel S. Weld}, editor = {Mathieu d'Aquin and Stefan Dietze and Claudia Hauff and Edward Curry and Philippe Cudr\'{e}-Mauroux}, title = {{The Newspaper Navigator Dataset: Extracting Headlines and Visual Content from 16 Million Historic Newspaper Pages in Chronicling America}}, booktitle = {{CIKM '20: The 29th ACM International Conference on Information and Knowledge Management, Virtual Event, Ireland, October 19-23, 2020}}, pages = {3055--3062}, publisher = {ACM}, year = {2020}, url = {https://doi.org/10.1145/3340531.3412767}, doi = {https://doi.org/10.1145/3340531.3412767} }