julien-c's picture
julien-c
HF staff
Migrate images
2430fe1
metadata
language: de
thumbnail: https://huggingface.co/severinsimmler/literary-german-bert/raw/main/kfold.png

German BERT for literary texts

This German BERT is based on bert-base-german-dbmdz-cased, and has been adapted to the domain of literary texts by fine-tuning the language modeling task on the Corpus of German-Language Fiction. Afterwards the model was fine-tuned for named entity recognition on the DROC corpus, so you can use it to recognize protagonists in German novels.

Stats

Language modeling

The Corpus of German-Language Fiction consists of 3,194 documents with 203,516,988 tokens or 1,520,855 types. The publication year of the texts ranges from the 18th to the 20th century:

years

Results

After one epoch:

Model Perplexity
Vanilla BERT 6.82
Fine-tuned BERT 4.98

Named entity recognition

The provided model was also fine-tuned for two epochs on 10,799 sentences for training, validated on 547 and tested on 1,845 with three labels: B-PER, I-PER and O.

Results

Dataset Precision Recall F1
Dev 96.4 87.3 91.6
Test 92.8 94.9 93.8

The model has also been evaluated using 10-fold cross validation and compared with a classic Conditional Random Field baseline described in Jannidis et al. (2015):

kfold

References

Markus Krug, Lukas Weimer, Isabella Reger, Luisa Macharowsky, Stephan Feldhaus, Frank Puppe, Fotis Jannidis, Description of a Corpus of Character References in German Novels, 2018.

Fotis Jannidis, Isabella Reger, Lukas Weimer, Markus Krug, Martin Toepfer, Frank Puppe, Automatische Erkennung von Figuren in deutschsprachigen Romanen, 2015.