Ming Jiang, Yuerong Hu, Glen Worthey, Ryan C. Dubnicek, Ted Underwood, J. Stephen Downie. Impact of OCR Quality on BERT Embeddings in the Domain Classification of Book Excerpts. In Maud Ehrmann, Folgert Karsdorp, Melvin Wevers, Tara Lee Andrews, Manuel Burghardt, Mike Kestemont, Enrique Manjavacas, Michael Piotrowski, Joris van Zundert, editors, Proceedings of the Conference on Computational Humanities Research, CHR2021, Amsterdam, The Netherlands, November 17-19, 2021. Volume 2989 of CEUR Workshop Proceedings, pages 266-279, CEUR-WS.org, 2021. [doi]