@inproceedings{L16-1154,
 abstract = {We present further work on evaluation of the fully automatic post-correction of Early Dutch Books Online, a collection of 10,333 18th century books. In prior work we evaluated the new implementation of Text-Induced Corpus Clean-up (TICCL) on the basis of a single book Gold Standard derived from this collection. In the current paper we revisit the same collection on the basis of a sizeable 1020 item random sample of OCR post-corrected strings from the full collection. Both evaluations have their own stories to tell and lessons to teach.
},
 address = {Portorož, Slovenia},
 author = {Martin Reynaert},
 booktitle = {Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC 2016)},
 month = {May},
 pages = {967--974},
 publisher = {European Language Resources Association (ELRA)},
 title = {OCR Post-Correction Evaluation of Early Dutch Books Online - Revisited},
 url = {https://www.aclweb.org/anthology/L16-1154},
 year = {2016}
}