Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/fursovia/geometric_embedding
"Zero-Training Sentence Embedding via Orthogonal Basis" paper implementation
https://github.com/fursovia/geometric_embedding
embeddings nlp
Last synced: 3 months ago
JSON representation
"Zero-Training Sentence Embedding via Orthogonal Basis" paper implementation
- Host: GitHub
- URL: https://github.com/fursovia/geometric_embedding
- Owner: fursovia
- Created: 2018-12-07T01:05:42.000Z (almost 6 years ago)
- Default Branch: master
- Last Pushed: 2018-12-23T08:46:01.000Z (almost 6 years ago)
- Last Synced: 2024-04-20T00:36:45.700Z (7 months ago)
- Topics: embeddings, nlp
- Language: Python
- Homepage:
- Size: 157 MB
- Stars: 19
- Watchers: 5
- Forks: 3
- Open Issues: 0
-
Metadata Files:
- Readme: readme.md
Awesome Lists containing this project
README
## Geometric Embedding Algorithm (GEM)
This is an implementation of Geometric Embedding Algorithm, a simple and robust non-parameterized approach for building sentence
representations. See the [paper](https://openreview.net/pdf?id=rJedbn0ctQ) for more details.The work is done as a project for [NLA course](http://nla.skoltech.ru/) at Skoltech.
### Example
```python
from gem import SentenceEmbedder
from embeddings import get_embedding_matrixsentences = ["We come from the land of the ice and snow",
"From the midnight sun where the hot springs blow"]
embedding_matrix, vocab = get_embedding_matrix('glove.6B.300d.txt')
embedder = SentenceEmbedder(sentences, embedding_matrix, vocab)embedded_sentences = embedder.gem(window_size=3, sigma_power=3)
```### Data used
* [GloVe embeddings](https://nlp.stanford.edu/projects/glove/)
* [LexVec embeddings](https://github.com/alexandres/lexvec)### Team
* [Alexey Bokhovkin](https://github.com/alexeybokhovkin)
* [Eugenia Cheskidova](https://github.com/fogside)
* [Ivan Fursov](https://github.com/fursovia)
* [Ruslan Rakhimov](https://github.com/rakhimovv)