Update README.md
Browse files
README.md
CHANGED
@@ -1,3 +1,38 @@
|
|
1 |
---
|
2 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
+
language: "en"
|
3 |
+
tags:
|
4 |
+
- twitter
|
5 |
+
- masked-token-prediction
|
6 |
+
- election2020
|
7 |
+
- politics
|
8 |
+
license: "gpl-3.0"
|
9 |
---
|
10 |
+
|
11 |
+
# Pre-trained BERT on Twitter US Political Election 2020
|
12 |
+
|
13 |
+
Pre-trained weights for [PoliBERTweet: A Pre-trained Language Model for Analyzing Political Content on Twitter](XXX), LREC 2022.
|
14 |
+
|
15 |
+
We use the initialized weights from [BERTweet](https://huggingface.co/vinai/bertweet-base) or `vinai/bertweet-base`.
|
16 |
+
|
17 |
+
# Training Data
|
18 |
+
|
19 |
+
This model is pre-trained on over 83 million English tweets about the 2020 US Presidential Election.
|
20 |
+
|
21 |
+
# Training Objective
|
22 |
+
|
23 |
+
This model is initialized with BERTweet and trained with an MLM objective.
|
24 |
+
|
25 |
+
# Reference
|
26 |
+
|
27 |
+
- [PoliBERTweet: A Pre-trained Language Model for Analyzing Political Content on Twitter](XXX), LREC 2022.
|
28 |
+
|
29 |
+
# Citation
|
30 |
+
```bibtex
|
31 |
+
@inproceedings{kawintiranon2022polibertweet,
|
32 |
+
title = {PoliBERTweet: A Pre-trained Language Model for Analyzing Political Content on Twitter},
|
33 |
+
author = {Kawintiranon, Kornraphop and Singh, Lisa},
|
34 |
+
booktitle = {Proceedings of the Language Resources and Evaluation Conference},
|
35 |
+
year = {2022},
|
36 |
+
publisher = {European Language Resources Association}
|
37 |
+
}
|
38 |
+
```
|