Skip to main content

GLEM is a lemmatizer for Ancient Greek.

Project description

# glem GLEM is a lemmatizer for Ancient Greek.

It has been created in the project ‘Unraveling the Language of Perspective’ (, which is supported by the EU under FP7, ERC Starting Grant 338421-Perspective.

The paper ‘A memory-based lemmatizer for Ancient Greek’ reports on how it works, what material it uses, and what the accuracy is. It can be found in the repository and at

A webservice where you can upload texts that you want to have lemmatized can be found at


Just Python 3 for the simple word list based lemmatizer.

To add machine learning based lemmatization that also takes into account the context, you also need [Frog]( By far the easiest way to install Frog is to use [LaMachine](


Run: python3 install

We recommend using LaMachine or a Python virtual environment of your own. Alternatively for a global installation, prepend sudo.

Example usage

Glem comes with a pretrained model, based on lemmas chosen by humans (in the UiO PROIEL project, PI: Dag Haug), for Herodotus. If you are inside the Lamachine environment (something like `lamachine/bin/activate`), you can use it (with or without Frog) as follows:

`glem -f input.txt`

The files for this model can be found in `glem/pretrained_models/herodotus` .

Project details

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

Glem-1.3.0.tar.gz (15.8 kB view hashes)

Uploaded source

Supported by

AWS AWS Cloud computing Datadog Datadog Monitoring Fastly Fastly CDN Google Google Object Storage and Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page