README.md

---
license: mit
language:
- en
tags:
- embeddings
- word2vec
---

# Embeddings

## Paper Refs. :

- [Mikolov et al 2013 - Distributed Representations of Words and Phrases (SGNS)](https://arxiv.org/pdf/1310.4546.pdf)
- [Rong, Xin 2014 - word2vec Parameter Learning Explained](https://arxiv.org/abs/1411.2738)
- [Levy & Goldberg 2014 - Neural Word Embedding as Implicit Matrix Factorization](https://papers.nips.cc/paper/2014/hash/feab05aa91085b7a8012516bc3533958-Abstract.html)

## Results
- **Nearest neighbours: strong** (e.g. `france → spain, italy, germany`)
- **Analogies: ~14% top-1** (semantic > morphological; limited by the small 17M-token corpus)

## Limitations
Small corpus → weak on analogies (esp. capital-country, morphology). For better analogy
accuracy, train on a larger corpus (enwik9+). Lowercased English only; drops OOV.

## Usage snippet 

```python
from huggingface_hub import hf_hub_download
import torch
import torch.nn.functional as F

path = hf_hub_download(repo_id="ocdbytes/embeddings", filename="embeddings_200.pt")
# weights_only=False because the checkpoint bundles Python dicts (word2idx/idx2word),
# which the default restricted loader (torch>=2.6) may reject.
ck = torch.load(path, map_location="cpu", weights_only=False)

syn0 = ck["syn0"]
word2idx, idx2word = ck["word2idx"], ck["idx2word"]
emb = F.normalize(syn0, dim=1)

def neighbours(word, n=10):
    i = word2idx[word]
    sims = emb @ emb[i]
    top = sims.topk(n + 1).indices.tolist()
    return [idx2word[j] for j in top if j != i][:n]

def analogy(a, b, c, n=5):
    t = F.normalize(emb[word2idx[b]] - emb[word2idx[a]] + emb[word2idx[c]], dim=0)
    sims = emb @ t
    ban = {word2idx[a], word2idx[b], word2idx[c]}
    top = sims.topk(n + len(ban)).indices.tolist()
    return [idx2word[j] for j in top if j not in ban][:n]

print(neighbours("king"))                      # -> ['viii', 'elizabeth', 'queen', ...]
print(analogy("france", "paris", "germany"))   # -> ['berlin', ...]
```

## Code 

- [ocdbytes-ai/embeddings](https://github.com/ocdbytes-ai/embeddings)