lbourdois commited on
Commit
1e63a60
1 Parent(s): 19947c7

Create README.md

Browse files
Files changed (1) hide show
  1. README.md +49 -0
README.md ADDED
@@ -0,0 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - word2vec
4
+ language: wa
5
+ license: gpl-3.0
6
+ ---
7
+
8
+ ## Description
9
+ Word embedding model trained by Al-Rfou et al.
10
+
11
+
12
+ ## How to use?
13
+
14
+ ```
15
+ import pickle
16
+ from numpy import dot
17
+ from numpy.linalg import norm
18
+ from huggingface_hub import hf_hub_download
19
+ words, embeddings = pickle.load(open(hf_hub_download(repo_id="Word2vec/polyglot_words_embeddings_en", filename="words_embeddings_en.pkl"), 'rb'),encoding="latin1")
20
+
21
+ word = "Irish"
22
+ a = embeddings[words.index(word)]
23
+ most_similar = []
24
+ for i in range(len(embeddings)):
25
+ if i != words.index(word):
26
+ b = embeddings[i]
27
+ cos_sim = dot(a, b)/(norm(a)*norm(b))
28
+ most_similar.append(cos_sim)
29
+ else:
30
+ most_similar.append(0)
31
+
32
+ words[most_similar.index(max(most_similar))]
33
+ ```
34
+
35
+ ## Citation
36
+
37
+ ```
38
+ @InProceedings{polyglot:2013:ACL-CoNLL,
39
+ author = {Al-Rfou, Rami and Perozzi, Bryan and Skiena, Steven},
40
+ title = {Polyglot: Distributed Word Representations for Multilingual NLP},
41
+ booktitle = {Proceedings of the Seventeenth Conference on Computational Natural Language Learning},
42
+ month = {August},
43
+ year = {2013},
44
+ address = {Sofia, Bulgaria},
45
+ publisher = {Association for Computational Linguistics},
46
+ pages = {183--192},
47
+ url = {http://www.aclweb.org/anthology/W13-3520}
48
+ }
49
+ ```