Explore projects

Normalization of historical German

Backend für die Software des DFG-Projekts CALLIDUS (Kooperation aus Fachdidaktik Latein, Korpuslinguistik und CMS): Flask & Postgres

Scripts & other stuff for the HU-Berlin Geoprocessing in Python (WS 2019/2020)

CI tests

Backend für die Software des DFG-Projekts CALLIDUS (Kooperation aus Fachdidaktik Latein, Korpuslinguistik und CMS): Flask & Postgres

Vocabulary training in Latin with a REST API and web frontend

Multimodal Machine Learning Seminar 2020: Offense Meme Classification using M-BERT

An algorithm for literal citation detection.

A framework for annotation projection.

We provide a review of the literature on the labor market integration of immigrant women in Europe and some current descriptive statistics.

This is the template repository for the Cocoyum corpus which is presented at ICLDC 7. Here, we provide templates for the conversion and visualization of three file formats (ELAN, Toolbox, FLEx) to ANNIS.

This is an early version of a Python script to add POS tags to Praat TextGrid files. It integrates several taggers into one interface, for example the TreeTagger, SpaCy and HanoverTagger. Also, normalized tiers can be added using a value pair file. Link to the newer version: https://scm.cms.hu-berlin.de/langerob/tiertagger