Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Multilingual word vectors in 78 languages
| Date | Stars |
|---|---|
| 2026-07-24 | 1202 |
| 2026-07-25 | 1202 |
| 2026-07-28 | 1202 |
| 2026-07-30 | 1202 |
| 2026-08-06 | 1202 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
> **Note**
> This repository is no longer actively maintained by Babylon Health. For further assistance, reach out to the paper authors.
# Aligning the fastText vectors of 78 languages
Facebook recently open-sourced word vectors in [89 languages](https://github.com/facebookresearch/fastText/blob/master/pretrained-vectors.md). However these vectors are monolingual; meaning that while similar words within a language share similar vectors, translation words from different languages do not have similar vectors. In [a recent paper at ICLR 2017](https://arxiv.org/abs/1702.03859), we showed how the SVD can be used to learn a linear transformation (a matrix), which aligns monolingual vectors from two languages in a single vector space. In this repository we provide 78 matrices, which can be used to align the majority of the fastText languages in a single space.
This readme explains how the matrices should be used. We also present a simple evaluation task, where we show we are able to successfully predict the translations of words in multiple languages. Our procedure relies on collecting bilingual training dictionaries of word pairs in two languages, but remarkably we are able to successfully predict the translations of words between language pairs for which we had no training dictionary!
Word embeddings define the similarity between two words by the normalised inner product of their vectors. The matrices in this repository place languages in a single space, **without changing any of these monolingual similarity relationships**. When you use the resulting multilingual vectors for monolingual tasks, they will perform exactly the same as the original vectors. To learn more about word embeddings, check out [Colah's blog](http://colah.github.io/posts/2014-07-NLP-RNNs-Representations/) or [Sam's introduction to vector representations](https://web.archive.org/web/20201111222742/https://www.samtalksml.net/aligning-vector-representations/).
Note that since we released this repository Facebook have released an additional 204 languages; however the word vectors of the original 90 languages have not changed, and the transformations provided in this repository will still work. If you would like to learn your own alignment matrices, we provide an example in [align_your_own.ipynb](./align_your_own.ipynb).
If you use this repository, please cite:
*Offline bilingual word vectors, orthogonal transformations and the inverted softmax
Samuel L. Smith, David H. P. Turban, Steven Hamblin and Nils Y. Hammerla
ICLR 2017 (conference track)*
### TLDR, just tell me what to do!
Clone a local copy of this repository, and download the fastText vectors you need from [here](https://github.com/facebookresearch/fastText/blob/master/pretrained-vectors.md). I'm going to assume you've downloaded the vectors for French and Russian in the text format. Let's say we want to compare the similarity of "chat" and "кот". We load the word vectors:
```python
from fasttext import FastVector
fr_dictionary = FastVector(vector_file='wiki.fr.vec')
ru_dictionary = FastVector(vector_file='wiki.ru.vec')
```
We can extract the word vectors and calculate their cosine similarity:
```python
fr_vector = fr_dictionary["chat"]
ru_vector = ru_dictionary["кот"]
print(FastVector.cosine_similarity(fr_vector, ru_vector))
# Result should be 0.02
```
The cosine similarity runs between -1 and 1. It seems that "chat" and "кот" are neither similar nor dissimilar. But now we apply the transformations to align the two dictionaries in a single space:
```python
fr_dictionary.apply_transform('alignment_matrices/fr.txt')
ru_dictionary.apply_transform('alignment_matrices/ru.txt')
```
And re-evaluate the cosine similarity:
```python
print(FastVector.cosine_similarity(fr_dictionary["chat"], ru_dictionary["кот"]))
# Result should be 0.43
```
Turns out "chat" and "кот" are pretty similar after all. This is good, since they both mean "cat".
### Ok, so how did Excerpt of 17,400 characters
Read on GitHub
7
5
4
1
1
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:9744884e713c4c90, topic:nlp, topic:natural-language-processing, topic:machine-translation