# <a name="introduction"></a> BERTweet: A pre-trained language model for English Tweets 

BERTweet is the first public large-scale language model pre-trained for English Tweets. BERTweet is trained based on the [RoBERTa](https://github.com/pytorch/fairseq/blob/master/examples/roberta/README.md)  pre-training procedure. The corpus used to pre-train BERTweet consists of 850M English Tweets (16B word tokens ~ 80GB), containing 845M Tweets streamed from 01/2012 to 08/2019 and 5M Tweets related to the **COVID-19** pandemic. The general architecture and experimental results of BERTweet can be found in our [paper](https://aclanthology.org/2020.emnlp-demos.2/):

    @inproceedings{bertweet,
    title     = {{BERTweet: A pre-trained language model for English Tweets}},
    author    = {Dat Quoc Nguyen and Thanh Vu and Anh Tuan Nguyen},
    booktitle = {Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations},
    pages     = {9--14},
    year      = {2020}
    }

**Please CITE** our paper when BERTweet is used to help produce published results or is incorporated into other software.

For further information or requests, please go to [BERTweet's homepage](https://github.com/VinAIResearch/BERTweet)!

### Main results

<p float="left">
<img width="275" alt="postagging" src="https://user-images.githubusercontent.com/2412555/135724590-01d8d435-262d-44fe-a383-cd39324fe190.png" />
<img width="275" alt="ner" src="https://user-images.githubusercontent.com/2412555/135724598-1e3605e7-d8ce-4c5e-be4a-62ae8501fae7.png" />
</p>

<p float="left">
<img width="275" alt="sentiment" src="https://user-images.githubusercontent.com/2412555/135724597-f1981f1e-fe73-4c03-b1ff-0cae0cc5f948.png" />
<img width="275" alt="irony" src="https://user-images.githubusercontent.com/2412555/135724595-15f4f2c8-bbb6-4ee6-82a0-034769dec183.png" />
</p>

### <a name="models2"></a> Pre-trained models 


Model | #params | Arch. | Pre-training data
---|---|---|---
`vinai/bertweet-base` | 135M | base | 850M English Tweets (cased)
`vinai/bertweet-covid19-base-cased` | 135M | base | 23M COVID-19 English Tweets (cased)
`vinai/bertweet-covid19-base-uncased` | 135M | base | 23M COVID-19 English Tweets (uncased)
`vinai/bertweet-large` | 355M | large | 873M English Tweets (cased) 

### <a name="usage2"></a> Example usage 


```python
import torch
from transformers import AutoModel, AutoTokenizer 

bertweet = AutoModel.from_pretrained("vinai/bertweet-base")

# For transformers v4.x+: 
tokenizer = AutoTokenizer.from_pretrained("vinai/bertweet-base", use_fast=False)

# For transformers v3.x: 
# tokenizer = AutoTokenizer.from_pretrained("vinai/bertweet-base")

# INPUT TWEET IS ALREADY NORMALIZED!
line = "SC has first two presumptive cases of coronavirus , DHEC confirms HTTPURL via @USER :crying_face:"

input_ids = torch.tensor([tokenizer.encode(line)])

with torch.no_grad():
    features = bertweet(input_ids)  # Models outputs are now tuples
    
## With TensorFlow 2.0+:
# from transformers import TFAutoModel
# bertweet = TFAutoModel.from_pretrained("vinai/bertweet-base")
```

### <a name="preprocess"></a> Normalize raw input Tweets 

Before applying `fastBPE` to the pre-training corpus of 850M English Tweets, we tokenized these  Tweets using `TweetTokenizer` from the NLTK toolkit and used the `emoji` package to translate emotion icons into text strings (here, each icon is referred to as a word token).   We also normalized the Tweets by converting user mentions and web/url links into special tokens `@USER` and `HTTPURL`, respectively. Thus it is recommended to also apply the same pre-processing step for BERTweet-based downstream applications w.r.t. the raw input Tweets. BERTweet provides this pre-processing step by enabling the `normalization` argument. This argument currently only supports models "`vinai/bertweet-base`", "`vinai/bertweet-covid19-base-cased`" and "`vinai/bertweet-covid19-base-uncased`".

 - Install `emoji`: `pip3 install emoji==0.6.0`
 - The `emoji` version must be either 0.5.4 or 0.6.0. Newer `emoji` versions have been updated to newer versions of the Emoji Charts, thus not consistent with the one used for pre-processing our pre-training Tweet corpus. 

```python
import torch
from transformers import AutoTokenizer

# Load the AutoTokenizer with a normalization mode if the input Tweet is raw
tokenizer = AutoTokenizer.from_pretrained("vinai/bertweet-base", normalization=True)

# from transformers import BertweetTokenizer
# tokenizer = BertweetTokenizer.from_pretrained("vinai/bertweet-base", normalization=True)

line = "SC has first two presumptive cases of coronavirus, DHEC confirms https://postandcourier.com/health/covid19/sc-has-first-two-presumptive-cases-of-coronavirus-dhec-confirms/article_bddfe4ae-5fd3-11ea-9ce4-5f495366cee6.html?utm_medium=social&utm_source=twitter&utm_campaign=user-share… via @postandcourier"

input_ids = torch.tensor([tokenizer.encode(line)])
```