Update README.md
Browse files
README.md
CHANGED
@@ -1,3 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
```python
|
2 |
import torch
|
3 |
from scipy.spatial.distance import cosine
|
@@ -26,4 +38,16 @@ embeddings = torch.sum(
|
|
26 |
|
27 |
# Compute a semantic similarity via the cosine distance
|
28 |
semantic_sim = 1 - cosine(embeddings[0], embeddings[1])
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
29 |
```
|
|
|
1 |
+
# DeCLUTR-small
|
2 |
+
|
3 |
+
## Model description
|
4 |
+
|
5 |
+
The corresponding model from our paper: [DeCLUTR: Deep Contrastive Learning for Unsupervised Textual Representations](https://arxiv.org/abs/2006.03659).
|
6 |
+
|
7 |
+
## Intended uses & limitations
|
8 |
+
|
9 |
+
The model is intended to be used as a universal sentence encoder, similar to [Google's Universal Sentence Encoder](https://tfhub.dev/google/universal-sentence-encoder/4) or [Sentence Transformers](https://github.com/UKPLab/sentence-transformers).
|
10 |
+
|
11 |
+
#### How to use
|
12 |
+
|
13 |
```python
|
14 |
import torch
|
15 |
from scipy.spatial.distance import cosine
|
|
|
38 |
|
39 |
# Compute a semantic similarity via the cosine distance
|
40 |
semantic_sim = 1 - cosine(embeddings[0], embeddings[1])
|
41 |
+
```
|
42 |
+
|
43 |
+
### BibTeX entry and citation info
|
44 |
+
|
45 |
+
```bibtex
|
46 |
+
@article{Giorgi2020DeCLUTRDC,
|
47 |
+
title={DeCLUTR: Deep Contrastive Learning for Unsupervised Textual Representations},
|
48 |
+
author={John M Giorgi and Osvald Nitski and Gary D. Bader and Bo Wang},
|
49 |
+
journal={ArXiv},
|
50 |
+
year={2020},
|
51 |
+
volume={abs/2006.03659}
|
52 |
+
}
|
53 |
```
|