cardiffnlp/twitter-roberta-base-mar2022-15M-incr

Twitter June 2022 (RoBERTa-base, 154M)

This is a RoBERTa-base model trained on 153.86M tweets until the end of June 2022 (15M tweets increment). 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():
        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-mar2022-15M-incr"
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) 0.35668  not
2) 0.27636  fully
3) 0.18418  getting
4) 0.03197  still
5) 0.02259  triple
------------------------------
I keep forgetting to bring a <mask>.
1) 0.04261  book
2) 0.04233  backpack
3) 0.04161  charger
4) 0.03892  mask
5) 0.03636  lighter
------------------------------
Looking forward to watching <mask> Game tonight!
1) 0.55292  the
2) 0.17813  The
3) 0.03052  this
4) 0.01565  Championship
5) 0.01391  End

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-mar2022-15M-incr"
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) 0.98951 The movie was great
2) 0.96042 Just finished reading 'Embeddings in NLP'
3) 0.95454 I just ordered fried chicken 🐣
4) 0.95148 What time is the next game?

Example Feature Extraction

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

MODEL = "cardiffnlp/twitter-roberta-base-mar2022-15M-incr"
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)