explaingit

clips/dutchembeddings

Analysis updated 2026-08-15 · repo last pushed 2021-06-11

★ 86PythonAudience · developerComplexity · 2/5DormantLicenseSetup · easy

TLDR

Pre-built word embeddings for Dutch that map how words relate to each other mathematically, saving you from training a model on millions of Dutch texts yourself. Downloadable files in standard format ready to load into Python.

Mindmap

mindmap
  root((repo))
    What it does
      Pre-built Dutch word vectors
      Two sizes available
      No training needed
    Data sources
      Dutch Wikipedia
      Roularta news articles
      COW web corpus
    Use cases
      Dutch chatbots
      Sentiment analysis
      Dutch language research
    Tech stack
      Python
      gensim library
      word2vec format
    Tools included
      relation.py evaluator
      Analogy testing
      Standard text format
    License
      Creative Commons for data
      GPL for code
      Free with attribution

Code map

Detail Auto

An interactive map of this repo's files and how they connect — its source is parsed live in your browser. Click Visualize to build it.

filefunction / class

What do people build with it?

USE CASE 1

Build a Dutch chatbot that understands word relationships without training your own model.

USE CASE 2

Analyze sentiment in Dutch customer reviews using pre-computed word vectors.

USE CASE 3

Research Dutch language semantics by testing word analogy relationships.

USE CASE 4

Power a Dutch-language search or recommendation system with word similarity data.

What is it built with?

Pythongensimword2vec

How does it compare?

clips/dutchembeddingsthestageai/edge-lmvoidtherapist31/mecchachameleon-mecchabionix
Stars868686
LanguagePythonPythonPython
Last pushed2021-06-11——
MaintenanceDormant——
Setup difficultyeasymoderateeasy
Complexity2/53/52/5
Audiencedeveloperdevelopergeneral

Figures from each repo's GitHub metadata at analysis time.

How do you get it running?

Difficulty · easy Time to first run · 5min

Download the embedding files from the repo and load them with gensim's KeyedVectors, no GPU or training required.

The embedding files are free to use under Creative Commons with attribution, and the code is under GPL so you must share any modifications if you distribute your changes.

In plain English

Dutchembeddings gives you pre-built "word embeddings" for the Dutch language, essentially a mathematical map of how Dutch words relate to each other. Instead of you having to train a model on millions of Dutch texts yourself, this project has already done that work and packaged the results as downloadable files. Word embeddings represent each word as a list of numbers (a vector) so that similar words end up with similar numbers. This lets software understand that "koning" (king) and "koningin" (queen) are related, or that "hond" (dog) and "kat" (cat) are closer to each other than either is to "computer." The project built these from several Dutch text collections, including Dutch Wikipedia, news articles from the Roularta corpus, and a large web-based corpus called COW. They offer two sizes: 160-dimensional and 320-dimensional vectors, and recommend the larger ones for better quality. This is aimed at anyone building Dutch-language NLP applications, a startup making a Dutch chatbot, a researcher studying Dutch semantics, or a company doing sentiment analysis on Dutch customer reviews. If you're building something that needs to understand Dutch text and you don't have the time or data to train your own word vectors from scratch, this gives you a ready-to-use resource. The files are in a standard word2vec text format, so they load easily into popular Python libraries like gensim. The project also includes a small evaluation tool called relation.py that lets you test how well a given embedding model captures word relationships, similar to the famous "king - man + woman = queen" test. The embeddings are released under a Creative Commons license and the code under GPL, so they're free to use with attribution.

Copy-paste prompts

Prompt 1
Load the Dutch word embeddings from this repo using gensim and find the 10 words most similar to 'koning' and 'koningin' in Dutch.
Prompt 2
Use relation.py from this repo to run a king minus man plus woman equals queen analogy test on the Dutch embeddings and explain the results.
Prompt 3
Write a Python script that loads the 320-dimensional Dutch embeddings from this repo and computes the similarity between 'hond', 'kat', and 'computer' to show which words are most related.
Prompt 4
Compare the 160-dimensional and 320-dimensional Dutch embedding models from this repo by running the same set of word analogy tests and reporting which performs better.

Frequently asked questions

What is dutchembeddings?

Pre-built word embeddings for Dutch that map how words relate to each other mathematically, saving you from training a model on millions of Dutch texts yourself. Downloadable files in standard format ready to load into Python.

What language is dutchembeddings written in?

Mainly Python. The stack also includes Python, gensim, word2vec.

Is dutchembeddings actively maintained?

Dormant — no commits in 2+ years (last push 2021-06-11).

What license does dutchembeddings use?

The embedding files are free to use under Creative Commons with attribution, and the code is under GPL so you must share any modifications if you distribute your changes.

How hard is dutchembeddings to set up?

Setup difficulty is rated easy, with roughly 5min to a first successful run.

Who is dutchembeddings for?

Mainly developer.

Open on GitHub → Explain another repo

This repo across BitVibe Labs

Verify against the repo before relying on details.

Alternatives & similar repos