system HF staff commited on
Commit
c92336e
1 Parent(s): 7712645

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +18 -0
README.md ADDED
@@ -0,0 +1,18 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ## GigaBERT-v4
2
+ GigaBERT-v4 is a continued pre-training of [GigaBERT-v3](https://huggingface.co/lanwuwei/GigaBERT-v3-Arabic-and-English) on code-switched data, showing improved zero-shot transfer performance from English to Arabic on information extraction (IE) tasks. More details can be found in the following paper:
3
+
4
+ @inproceedings{lan2020gigabert,
5
+ author = {Lan, Wuwei and Chen, Yang and Xu, Wei and Ritter, Alan},
6
+ title = {GigaBERT: Zero-shot Transfer Learning from English to Arabic},
7
+ booktitle = {Proceedings of The 2020 Conference on Empirical Methods on Natural Language Processing (EMNLP)},
8
+ year = {2020}
9
+ }
10
+
11
+ ## Usage
12
+ ```
13
+ from transformers import *
14
+ tokenizer = BertTokenizer.from_pretrained("lanwuwei/GigaBERT-v4-Arabic-and-English", do_lower_case=True)
15
+ model = BertForTokenClassification.from_pretrained("lanwuwei/GigaBERT-v4-Arabic-and-English")
16
+ ```
17
+ More coda examples can be found [here](https://github.com/lanwuwei/GigaBERT).
18
+