qurator-spk/neat
1
0
Fork 0
mirror of https://github.com/qurator-spk/neat.git synced 2025-06-09 11:49:54 +02:00
Code Issues Releases Wiki Activity

Update Preprocessing.md

Browse source
This commit is contained in:
Clemens Neudecker 2019-11-20 00:59:01 +01:00 • committed by GitHub
parent e7d0be2288
commit 9f2f3ba2d5
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
1 changed files with 2 additions and 4 deletions
Download patch file Download diff file Expand all files Collapse all files

6
docs/Preprocessing.md
View file

@ -10,12 +10,10 @@ Layout Analysis & Textline Extraction @[sbb_pixelwise_segmentation](https://gith
### OCR & Word Segmentation ### OCR & Word Segmentation
OCR is based on [OCR-D](https://github.com/OCR-D)'s [ocrd_tesserocr](https://github.com/OCR-D/ocrd_tesserocr) which requires [Tesseract](https://github.com/tesseract-ocr/tesseract) **>= 4.1.0**. The [Fraktur_5000000](https://ub-backup.bib.uni-mannheim.de/~stweil/ocrd-train/data/Fraktur_5000000/) model, which is trained on [GT4HistOCR](https://github.com/tesseract-ocr/tesstrain/wiki/GT4HistOCR) is used. OCR is based on [OCR-D](https://github.com/OCR-D)'s [ocrd_tesserocr](https://github.com/OCR-D/ocrd_tesserocr) which requires [Tesseract](https://github.com/tesseract-ocr/tesseract) **>= 4.1.0**. The [GT4HistOCR_2000000](https://ub-backup.bib.uni-mannheim.de/~stweil/ocrd-train/data/GT4HistOCR_2000000.traineddata) model, which is [trained](https://github.com/tesseract-ocr/tesstrain/wiki/GT4HistOCR) on the [GT4HistOCR](https://zenodo.org/record/1344132) corpus, is used. Further details are available in the [paper](https://arxiv.org/abs/1809.05501).
### Tokenization ### Tokenization
### Named Entity Recognition ### Named Entity Recognition
For Named Entity Recognition, a [BERT-Base](https://github.com/google-research/bert) model was trained for noisy OCR texts with historical spelling variation. For Named Entity Recognition, a [BERT-Base](https://github.com/google-research/bert) model was trained for noisy OCR texts with historical spelling variation. [sbb_ner](https://github.com/qurator-spk/sbb_ner) is using a combination of unsupervised training on a large (~2.3m pages) [corpus of German OCR](https://zenodo.org/record/3257041) in combination with supervised training on a small (47k tokens) [annotated corpus](https://github.com/EuropeanaNewspapers/ner-corpora/tree/master/enp_DE.sbb.bio). Further details are available in the [paper](https://corpora.linguistik.uni-erlangen.de/data/konvens/proceedings/papers/KONVENS2019_paper_4.pdf).
[sbb_ner](https://github.com/qurator-spk/sbb_ner) is using a combination of unsupervised training on a large (~2.3m pages) [corpus of German OCR](https://zenodo.org/record/3257041) from the Digital Collections of the Berlin State Library in combination with supervised training on a small (47k tokens) [annotated corpus](https://github.com/EuropeanaNewspapers/ner-corpora/tree/master/enp_DE.sbb.bio) of OCR from digitized historical newspapers of the Berlin State Library. Further details are available in the [paper](https://corpora.linguistik.uni-erlangen.de/data/konvens/proceedings/papers/KONVENS2019_paper_4.pdf).