Update README.md
Browse files
README.md
CHANGED
@@ -9,4 +9,154 @@ datasets:
|
|
9 |
language:
|
10 |
- sr
|
11 |
library_name: fasttext
|
12 |
-
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
9 |
language:
|
10 |
- sr
|
11 |
library_name: fasttext
|
12 |
+
---
|
13 |
+
|
14 |
+
<table style="width:100%;height:100%">
|
15 |
+
<tr>
|
16 |
+
<td colspan=2>
|
17 |
+
<h2>FastText</h2>
|
18 |
+
</td>
|
19 |
+
</tr>
|
20 |
+
<tr style="width:100%;height:100%">
|
21 |
+
<td width=50%>
|
22 |
+
<p>Обучаван над корпусом српског језика - 9.5 милијарди речи</p>
|
23 |
+
<p>Међу датотекама се налазе модели у Gensim, али и оригиналном формату</p>
|
24 |
+
</td>
|
25 |
+
<td>
|
26 |
+
<p>Trained on the Serbian language corpus - 9.5 billion words</p>
|
27 |
+
<p>The files include models in both Gensim and the original format.</p>
|
28 |
+
</td>
|
29 |
+
</tr>
|
30 |
+
</table>
|
31 |
+
|
32 |
+
|
33 |
+
```python
|
34 |
+
from gensim.models import FastText
|
35 |
+
model = Word2Vec.load("TeslaFT")
|
36 |
+
examples = [
|
37 |
+
("dim", "zavesa"),
|
38 |
+
("staklo", "zavesa"),
|
39 |
+
("ormar", "zavesa"),
|
40 |
+
("prozor", "zavesa"),
|
41 |
+
("draperija", "zavesa")
|
42 |
+
]
|
43 |
+
for e in examples:
|
44 |
+
model.wv.cosine_similarities(ft.wv[e[0]], ft.wv[[e[1]]])[0]
|
45 |
+
```
|
46 |
+
```
|
47 |
+
0.5305264
|
48 |
+
0.7095266
|
49 |
+
0.6041575
|
50 |
+
0.5771946
|
51 |
+
0.8870213
|
52 |
+
```
|
53 |
+
|
54 |
+
<div class="inline-flex flex-col" style="line-height: 1.5;padding-right:50px">
|
55 |
+
<div style="text-align: center; margin-top: 3px; font-size: 16px; font-weight: 800">Editor</div>
|
56 |
+
<a href="https://huggingface.co/procesaur">
|
57 |
+
<div class="flex">
|
58 |
+
<div
|
59 |
+
style="display:DISPLAY_1; margin-left: auto; margin-right: auto; width: 92px; height:92px; border-radius: 50%;
|
60 |
+
background-size: cover; background-image: url('https://cdn-uploads.huggingface.co/production/uploads/1673534533167-63bc254fb8c61b8aa496a39b.jpeg?w=200&h=200&f=face')">
|
61 |
+
</div>
|
62 |
+
</div>
|
63 |
+
</a>
|
64 |
+
<div style="text-align: center; font-size: 16px; font-weight: 800">Mihailo Škorić</div>
|
65 |
+
<div>
|
66 |
+
<a href="https://huggingface.co/procesaur">
|
67 |
+
<div style="text-align: center; font-size: 14px;">@procesaur</div>
|
68 |
+
</a>
|
69 |
+
</div>
|
70 |
+
</div>
|
71 |
+
</div>
|
72 |
+
|
73 |
+
<div id="zastava">
|
74 |
+
<div class="grb">
|
75 |
+
<img src="https://www.ai.gov.rs/img/logo_60x120-2.png" style="position:relative; left:30px; z-index:10; height:85px">
|
76 |
+
</div>
|
77 |
+
<table width=100% style="border:0px">
|
78 |
+
<tr style="background-color:#C6363C;width:100%;border:0px;height:30px"><td style="width:100vw"></td></tr>
|
79 |
+
<tr style="background-color:#0C4076;width:100%;border:0px;height:30px"><td></td></tr>
|
80 |
+
<tr style="background-color:#ffffff;width:100%;border:0px;height:30px"><td></td></tr>
|
81 |
+
</table>
|
82 |
+
</div>
|
83 |
+
|
84 |
+
<table style="width:100%;height:100%">
|
85 |
+
<tr style="width:100%;height:100%">
|
86 |
+
<td width=50%>
|
87 |
+
<p>Истраживање jе спроведено уз подршку Фонда за науку Републике Србиjе, #7276, Text Embeddings – Serbian Language Applications – TESLA</p>
|
88 |
+
</td>
|
89 |
+
<td>
|
90 |
+
<p>This research was supported by the Science Fund of the Republic of Serbia, #7276, Text Embeddings - Serbian Language Applications - TESLA</p>
|
91 |
+
</td>
|
92 |
+
</tr>
|
93 |
+
</table>
|
94 |
+
|
95 |
+
|
96 |
+
|
97 |
+
<style>
|
98 |
+
.ffeat: {
|
99 |
+
color:red
|
100 |
+
}
|
101 |
+
|
102 |
+
.cover {
|
103 |
+
width: 100%;
|
104 |
+
margin-bottom: 5pt
|
105 |
+
}
|
106 |
+
|
107 |
+
.highlight-container, .highlight {
|
108 |
+
position: relative;
|
109 |
+
text-decoration:none
|
110 |
+
}
|
111 |
+
|
112 |
+
.highlight-container {
|
113 |
+
display: inline-block;
|
114 |
+
|
115 |
+
}
|
116 |
+
|
117 |
+
.highlight{
|
118 |
+
color:white;
|
119 |
+
text-transform:uppercase;
|
120 |
+
font-size: 16pt;
|
121 |
+
}
|
122 |
+
|
123 |
+
.highlight-container{
|
124 |
+
padding:5px 10px
|
125 |
+
}
|
126 |
+
|
127 |
+
.highlight-container:before {
|
128 |
+
content: " ";
|
129 |
+
display: block;
|
130 |
+
height: 100%;
|
131 |
+
width: 100%;
|
132 |
+
margin-left: 0px;
|
133 |
+
margin-right: 0px;
|
134 |
+
position: absolute;
|
135 |
+
background: #e80909;
|
136 |
+
transform: rotate(2deg);
|
137 |
+
top: -1px;
|
138 |
+
left: -1px;
|
139 |
+
border-radius: 20% 25% 20% 24%;
|
140 |
+
padding: 10px 18px 18px 10px;
|
141 |
+
}
|
142 |
+
|
143 |
+
div.grb, #zastava>table {
|
144 |
+
position:absolute;
|
145 |
+
top:0px;
|
146 |
+
left: 0px;
|
147 |
+
margin:0px
|
148 |
+
}
|
149 |
+
|
150 |
+
div.grb>img, #zastava>table{
|
151 |
+
margin:0px
|
152 |
+
}
|
153 |
+
|
154 |
+
#zastava {
|
155 |
+
position: relative;
|
156 |
+
margin-bottom:120px
|
157 |
+
}
|
158 |
+
|
159 |
+
p {
|
160 |
+
font-size:14pt
|
161 |
+
}
|
162 |
+
</style>
|