Center for Humanities Computing Aarhus's repositories
danish-foundation-models
A project for training foundational Danish language model
embedding-explorer
Tools for interactive visual exploration of semantic embeddings.
conspiracies
A python package for discovering and examining conspiracies using NLP.
llm-tweet-classification
Classifying tweets with large language models with zero- and few-shot learning.
epistemic-consequences-of-unfair-tools
Code from the paper titled "Epistemic consequences of unfair tools" (Lassen et al., forthcoming)
DDB_Tagger
A thesaurus based semantic tagger for Danish texts
roman_amphorae
Aoristic analysis of archaeological amphora data
CHR2024-website
Fork of the CHR24 website
DA_literary_SA
data & analysis for textual features influence on SA
dfm-sentence-transformers
Code for curating data and training sentence transformers for the Danish Foundation Models project.
fables-ancient-greek
Stylistic analysis of fables in ancient greek
fabula_dashboard
An interactive dashboard for FabulaNet, where users can upload a text and get a number of metrics visualised
gender-identification
Code and pipeline for gender identification based on names.
glove-semantic-explorer
Embedding explorer over arbitrary data using GloVe embeddings.
gospel-ancient-greek
Stylistic analysis for The Gospel of Mark in ancient greek.
graphematics
A collection of string processing and visualization scripts following the steps outlined in “Handbuch für die graphematisch-phonologische Analyse vormoderner niederdeutschen und niederländischen Texte".
scandi-eurovoc
Scripts to curate the Eurovoc dataset for Scandinavian entries.
unicode-default-word-boundary
Split words with Unicode's default word boundary specification
web-extractor
A tool for extracting DOM content and taking screenshots of websites
word-associations
Word associations in Indre Mission and Kirkeligt Samfund