
MHGTagger annotates Middle High German sentences with part-of-speech
tags, normalized forms and lemmas. This tagger is also contained in
the RNNTagger distribution (https://www.cis.lmu.de/~schmid/tools/RNNTagger).
It was trained on the Referenzkorpus Mittelhochdeutsch
(https://www.linguistics.rub.de/rem/index.html).


Installation
------------

Run the following commands
> python3 -m venv venv/
> source venv/bin/activate
> python3 -m pip install torch --index-url https://download.pytorch.org/whl/cpu
> python3 -m pip install numpy
> ./rnn-tagger-middle-high-german.sh test.txt 
> deactivate


Usage
-----

Processing of texts without sentence boundaries:

input format: 1 word per line (see the file test.txt for an example)

Run the following commands:
> source venv/bin/activate
> ./tag-and-lemmatize.sh file.txt > file-annotated.txt
> deactivate


Processing of texts with sentence boundaries:

input format: 1 word per line, empty line after each sentence
(see test2.txt for an example)

Run the following commands:
> source venv/bin/activate
> ./tag-and-lemmatize.sh -s file.txt > file-annotated.txt
> deactivate
