Added description and citation
Browse files
README.md
CHANGED
@@ -13,16 +13,25 @@ license: apache-2.0
|
|
13 |
|
14 |
---
|
15 |
|
|
|
16 |
|
|
|
17 |
|
|
|
18 |
|
|
|
19 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
20 |
|
21 |
-
|
22 |
-
|
23 |
-
|
24 |
-
|
25 |
-
|
26 |
-
|
27 |
-
|
28 |
-
|
|
|
13 |
|
14 |
---
|
15 |
|
16 |
+
# BERTić* [bert-ich] /bɜrtitʃ/ - A transformer language model for Bosnian, Croatian, Montenegrin and Serbian
|
17 |
|
18 |
+
* The name should resemble the facts (1) that the model was trained in Zagreb, Croatia, where diminutives ending in -ić (as in fotić, smajlić, hengić etc.) are very popular, and (2) that most surnames in the countries where these languages are spoken end in -ić (with diminutive etymology as well).
|
19 |
|
20 |
+
This is the smaller generator of the main [discriminator model](https://huggingface.co/classla/bcms-bertic), useful if you want to continue pre-training the discriminator model.
|
21 |
|
22 |
+
If you use the model, please cite the following paper:
|
23 |
|
24 |
+
```
|
25 |
+
@inproceedings{ljubesic-lauc-2021-bertic,
|
26 |
+
title = "{BERT}i{\'c} - The Transformer Language Model for {B}osnian, {C}roatian, {M}ontenegrin and {S}erbian",
|
27 |
+
author = "Ljube{\v{s}}i{\'c}, Nikola and Lauc, Davor",
|
28 |
+
booktitle = "Proceedings of the 8th Workshop on Balto-Slavic Natural Language Processing",
|
29 |
+
month = apr,
|
30 |
+
year = "2021",
|
31 |
+
address = "Kiyv, Ukraine",
|
32 |
+
publisher = "Association for Computational Linguistics",
|
33 |
+
url = "https://www.aclweb.org/anthology/2021.bsnlp-1.5",
|
34 |
+
pages = "37--42",
|
35 |
|
36 |
+
}
|
37 |
+
```
|
|
|
|
|
|
|
|
|
|
|
|