igorsterner
commited on
Commit
•
cec0752
1
Parent(s):
4050ee0
Upload README.md
Browse files
README.md
ADDED
@@ -0,0 +1,49 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
language:
|
3 |
+
- multilingual
|
4 |
+
- en
|
5 |
+
- de
|
6 |
+
license: mit
|
7 |
+
widget:
|
8 |
+
- text: "ich glaub ich muss echt rewatchen like i so empty was soll ich denn jetzt machen"
|
9 |
+
example_title: "Example 1"
|
10 |
+
---
|
11 |
+
|
12 |
+
# German-English Code-Switching Identification
|
13 |
+
|
14 |
+
The [Tongueswitcher BERT](https://huggingface.co/igorsterner/german-english-code-switching-bert) model finetuned for German--English identification. It was introduced in [this paper](). This model is case sensitive.
|
15 |
+
|
16 |
+
## Overview
|
17 |
+
- **Initializd language model:** german-english-code-switching-bert
|
18 |
+
- **Training data:** The Denglish Corpus
|
19 |
+
- **Infrastructure**: 1x Nvidia A100 GPU
|
20 |
+
- **Published**: 16 October 2023
|
21 |
+
|
22 |
+
## Hyperparameters
|
23 |
+
|
24 |
+
```
|
25 |
+
batch_size = 16
|
26 |
+
epochs = 3
|
27 |
+
n_steps = 789
|
28 |
+
max_seq_len = 512
|
29 |
+
learning_rate = 3e-5
|
30 |
+
weight_decay = 0.01
|
31 |
+
Adam beta = (0.9, 0.999)
|
32 |
+
lr_schedule = LinearWarmup
|
33 |
+
seed = 2021
|
34 |
+
```
|
35 |
+
|
36 |
+
## Authors
|
37 |
+
- Igor Sterner: `is473 [at] cam.ac.uk`
|
38 |
+
- Simone Teufel: `sht25 [at] cam.ac.uk`
|
39 |
+
|
40 |
+
### BibTeX entry and citation info
|
41 |
+
|
42 |
+
```bibtex
|
43 |
+
@inproceedings{sterner2023tongueswitcher,
|
44 |
+
author = {Igor Sterner and Simone Teufel},
|
45 |
+
title = {TongueSwitcher: Fine-Grained Identification of German-English Code-Switching},
|
46 |
+
booktitle = {Sixth Workshop on Computational Approaches to Linguistic Code-Switching},
|
47 |
+
year = {2023},
|
48 |
+
}
|
49 |
+
```
|