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]
@inproceedings{JiangHWDUD21,
title = {Impact of OCR Quality on BERT Embeddings in the Domain Classification of Book Excerpts},
author = {Ming Jiang and Yuerong Hu and Glen Worthey and Ryan C. Dubnicek and Ted Underwood and J. Stephen Downie},
year = {2021},
url = {http://ceur-ws.org/Vol-2989/long_paper43.pdf},
researchr = {https://researchr.org/publication/JiangHWDUD21},
cites = {0},
citedby = {0},
pages = {266-279},
booktitle = {Proceedings of the Conference on Computational Humanities Research, CHR2021, Amsterdam, The Netherlands, November 17-19, 2021},
editor = {Maud Ehrmann and Folgert Karsdorp and Melvin Wevers and Tara Lee Andrews and Manuel Burghardt and Mike Kestemont and Enrique Manjavacas and Michael Piotrowski and Joris van Zundert},
volume = {2989},
series = {CEUR Workshop Proceedings},
publisher = {CEUR-WS.org},
}