devmount/GermanWordEmbeddings
Toolkit to obtain and preprocess German text corpora, train models and evaluate them with generated testsets. Built with Gensim and Tensorflow.
This toolkit helps researchers and linguists understand how German words relate to each other by analyzing large German text collections. It takes raw German text (like Wikipedia articles or news) as input, processes it, and then trains a model that outputs word embeddings. These embeddings represent words numerically, allowing users to explore semantic and syntactic relationships between German words.
242 stars. No commits in the last 6 months.
Use this if you need to create custom numerical representations (embeddings) for German words based on your own specific German text data, or if you want to evaluate existing German word embedding models.
Not ideal if you're looking for pre-trained word embeddings for English or other languages, or if you need an out-of-the-box solution without any Python scripting.
Stars
242
Forks
51
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Aug 21, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/devmount/GermanWordEmbeddings"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.