Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,72 @@
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
| 3 |
+
datasets:
|
| 4 |
+
- wikipedia
|
| 5 |
+
language:
|
| 6 |
+
- it
|
| 7 |
---
|
| 8 |
+
--------------------------------------------------------------------------------------------------
|
| 9 |
+
|
| 10 |
+
<body>
|
| 11 |
+
<span class="vertical-text" style="background-color:lightgreen;border-radius: 3px;padding: 3px;"> </span>
|
| 12 |
+
<br>
|
| 13 |
+
<span class="vertical-text" style="background-color:orange;border-radius: 3px;padding: 3px;"> </span>
|
| 14 |
+
<br>
|
| 15 |
+
<span class="vertical-text" style="background-color:lightblue;border-radius: 3px;padding: 3px;"> Model: Word2Vec</span>
|
| 16 |
+
<br>
|
| 17 |
+
<span class="vertical-text" style="background-color:tomato;border-radius: 3px;padding: 3px;"> Lang: IT</span>
|
| 18 |
+
<br>
|
| 19 |
+
<span class="vertical-text" style="background-color:lightgrey;border-radius: 3px;padding: 3px;"> </span>
|
| 20 |
+
<br>
|
| 21 |
+
<span class="vertical-text" style="background-color:#CF9FFF;border-radius: 3px;padding: 3px;"> </span>
|
| 22 |
+
</body>
|
| 23 |
+
|
| 24 |
+
--------------------------------------------------------------------------------------------------
|
| 25 |
+
|
| 26 |
+
<h3>Model description</h3>
|
| 27 |
+
|
| 28 |
+
This model is a <b>lightweight</b> and uncased version of <b>Word2Vec</b> <b>[1]</b> for the <b>italian</b> language. It's implemented in Gensim and it provides embeddings for 560.509 uncased italian words in a 100-dimensional vector space, resulting in a total model size of about 245 MB.
|
| 29 |
+
|
| 30 |
+
|
| 31 |
+
<h3>Training procedure</h3>
|
| 32 |
+
|
| 33 |
+
The model was trained on the italian split of the Wikipedia dataset (about 3.7GB, lowercased and pre-processed) for 10 epochs, using a window size of 5 and including words with a minimum count of 10, with an initial learning rate of 2.5e-3
|
| 34 |
+
|
| 35 |
+
|
| 36 |
+
<h3>Quick usage</h3>
|
| 37 |
+
|
| 38 |
+
Download the files in a local folder called "word2vec-light-uncased-it", then run:
|
| 39 |
+
|
| 40 |
+
```python
|
| 41 |
+
from gensim.models import KeyedVectors
|
| 42 |
+
|
| 43 |
+
model = KeyedVectors.load("./word2vec-light-uncased-it/word2vec.wordvectors", mmap='r')
|
| 44 |
+
|
| 45 |
+
model.most_similar("poesia", topn=5)
|
| 46 |
+
```
|
| 47 |
+
|
| 48 |
+
Expected output:
|
| 49 |
+
|
| 50 |
+
```
|
| 51 |
+
[('letteratura', 0.8193784356117249),
|
| 52 |
+
('poetica', 0.8115736246109009),
|
| 53 |
+
('narrativa', 0.7729100584983826),
|
| 54 |
+
('drammaturgia', 0.7576397061347961),
|
| 55 |
+
('prosa', 0.7552034854888916)]
|
| 56 |
+
```
|
| 57 |
+
|
| 58 |
+
<h3>Limitations</h3>
|
| 59 |
+
|
| 60 |
+
This lightweight model is trained on Wikipedia, so it's particularly suitable for natively digital text
|
| 61 |
+
from the world wide web, written in a correct and fluent form (like wikis, web pages, news, etc.).
|
| 62 |
+
|
| 63 |
+
However, it may show limitations when it comes to chaotic text, containing errors and slang expressions
|
| 64 |
+
(like social media posts) or when it comes to domain-specific text (like medical, financial or legal content).
|
| 65 |
+
|
| 66 |
+
<h3>References</h3>
|
| 67 |
+
|
| 68 |
+
[1] https://arxiv.org/abs/1301.3781
|
| 69 |
+
|
| 70 |
+
<h3>License</h3>
|
| 71 |
+
|
| 72 |
+
The model is released under <b>Apache-2.0</b> license
|