cardiffnlp / twitter-roberta-base-mar2022

Twitter March 2022 (RoBERTa-base, 128M)

This is a RoBERTa-base model trained on 128.06M tweets until the end of March 2022. More details and performance scores are available in the TimeLMs paper .

Below, we provide some usage examples using the standard Transformers interface. For another interface more suited to comparing predictions and perplexity scores between models trained at different temporal intervals, check the TimeLMs repository .

For other models trained until different periods, check this table .

Preprocess Text

Replace usernames and links for placeholders: "@user" and "http". If you're interested in retaining verified users which were also retained during training, you may keep the users listed here .

def preprocess(text):
    preprocessed_text = []
    for t in text.split(): # expects whitespace tokenization
        if len(t) > 1:
            t = '@user' if t[0] == '@' and t.count('@') == 1 else t
            t = 'http' if t.startswith('http') else t
        preprocessed_text.append(t)
    return ' '.join(preprocessed_text)

Example Masked Language Model

from transformers import pipeline, AutoTokenizer

MODEL = "cardiffnlp/twitter-roberta-base-mar2022"
fill_mask = pipeline("fill-mask", model=MODEL, tokenizer=MODEL)
tokenizer = AutoTokenizer.from_pretrained(MODEL)

def pprint(candidates, n):
    for i in range(n):
        token = tokenizer.decode(candidates[i]['token'])
        score = candidates[i]['score']
        print("%d) %.5f %s" % (i+1, score, token))

texts = [
    "So glad I'm <mask> vaccinated.",
    "I keep forgetting to bring a <mask>.",
    "Looking forward to watching <mask> Game tonight!",
]

for text in texts:
    t = preprocess(text)
    print(f"{'-'*30}\n{t}")
    candidates = fill_mask(t)
    pprint(candidates, 5)

Output:

------------------------------
So glad I'm <mask> vaccinated.
1) 0.34390  fully
2) 0.28177  not
3) 0.16473  getting
4) 0.04932  still
5) 0.01754  double
------------------------------
I keep forgetting to bring a <mask>.
1) 0.05391  book
2) 0.04560  mask
3) 0.03456  pen
4) 0.03251  lighter
5) 0.03098  charger
------------------------------
Looking forward to watching <mask> Game tonight!
1) 0.60744  the
2) 0.15224  The
3) 0.02575  this
4) 0.01450  End
5) 0.01035  Championship

Example Tweet Embeddings

from transformers import AutoTokenizer, AutoModel, TFAutoModel
import numpy as np
from scipy.spatial.distance import cosine
from collections import Counter

def get_embedding(text):  # naive approach for demonstration
  text = preprocess(text)
  encoded_input = tokenizer(text, return_tensors='pt')
  features = model(**encoded_input)
  features = features[0].detach().cpu().numpy() 
  return np.mean(features[0], axis=0) 


MODEL = "cardiffnlp/twitter-roberta-base-mar2022"
tokenizer = AutoTokenizer.from_pretrained(MODEL)
model = AutoModel.from_pretrained(MODEL)

query = "The book was awesome"
tweets = ["I just ordered fried chicken 🐣", 
          "The movie was great",
          "What time is the next game?",
          "Just finished reading 'Embeddings in NLP'"]

sims = Counter()
for tweet in tweets:
    sim = 1 - cosine(get_embedding(query), get_embedding(tweet))
    sims[tweet] = sim

print('Most similar to: ', query)
print(f"{'-'*30}")
for idx, (tweet, sim) in enumerate(sims.most_common()):
    print("%d) %.5f %s" % (idx+1, sim, tweet))

Output:

Most similar to:  The book was awesome
------------------------------
1) 0.98985 The movie was great
2) 0.96122 Just finished reading 'Embeddings in NLP'
3) 0.95733 I just ordered fried chicken 🐣
4) 0.93271 What time is the next game?

Example Feature Extraction

from transformers import AutoTokenizer, AutoModel, TFAutoModel
import numpy as np

MODEL = "cardiffnlp/twitter-roberta-base-mar2022"
tokenizer = AutoTokenizer.from_pretrained(MODEL)

text = "Good night 😊"
text = preprocess(text)

# Pytorch
model = AutoModel.from_pretrained(MODEL)
encoded_input = tokenizer(text, return_tensors='pt')
features = model(**encoded_input)
features = features[0].detach().cpu().numpy() 
features_mean = np.mean(features[0], axis=0) 
#features_max = np.max(features[0], axis=0)

# # Tensorflow
# model = TFAutoModel.from_pretrained(MODEL)
# encoded_input = tokenizer(text, return_tensors='tf')
# features = model(encoded_input)
# features = features[0].numpy()
# features_mean = np.mean(features[0], axis=0) 
# #features_max = np.max(features[0], axis=0)