Diachronic normalisation of Polish texts

Transform old Polish texts into modern spelling. [ver. 1.0.0]

# submitter when ver. description dev-0 CharMatch dev-1 CharMatch test-A CharMatch
7 p/tlen 2020-04-22 19:16 1.0.0 PSI-Toolkit Diachroniser 2020 1.0000 0.2045 0.2934
1 p/tlen 2019-10-26 19:38 1.0.0 Lucene Transducers 0.21 1.0000 0.6724 0.6580
2 p/tlen 2019-10-19 20:13 1.0.0 Lucene Transducers 20 1.0000 0.6143 0.6189
8 p/tlen 2018-03-30 12:49 1.0.0 PSI-Toolkit better-diachronizer 1.0000 0.1375 0.1951
3 p/tlen 2018-03-17 11:07 1.0.0 use Lucene token filter with sub-word variants (v. 0.15) 1.0000 0.6110 0.6093
9 Paweł Skórzewski 2018-03-16 20:38 1.0.0 Raw normalization N/A 0.0150 0.0284
4 p/tlen 2018-03-16 13:25 1.0.0 use Lucene filter with words mined using word2vec (v. 0.14) 1.0000 0.6061 0.6031
5 p/tlen 2018-03-16 11:16 1.0.0 use Lucene filter without OCR fixes (v. 0.13) 1.0000 0.6122 0.5833
6 p/tlen 2018-03-15 20:55 1.0.0 use Lucene token filter (v. 0.12) 1.0000 0.5181 0.4656
10 p/tlen 2018-03-15 20:47 1.0.0 do nothing stupid 0.0000 0.0000 0.0000