danlou's picture
Update README.md
93b451e
metadata
language: en
tags:
  - timelms
  - twitter
license: mit
datasets:
  - twitter-api

Twitter March 2021 (RoBERTa-base, 111M)

This is a RoBERTa-base model trained on 111.26M tweets until the end of March 2021. 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-mar2021"
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) 0.42688  getting
2) 0.30230  not
3) 0.07375  fully
4) 0.03619  already
5) 0.03055  being
------------------------------
I keep forgetting to bring a <mask>.
1) 0.07603  mask
2) 0.04933  book
3) 0.04029  knife
4) 0.03461  laptop
5) 0.03069  bag
------------------------------
Looking forward to watching <mask> Game tonight!
1) 0.53945  the
2) 0.27647  The
3) 0.03881  End
4) 0.01711  this
5) 0.00831  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-mar2021"
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) 0.99106 The movie was great
2) 0.96662 Just finished reading 'Embeddings in NLP'
3) 0.96150 I just ordered fried chicken 🐣
4) 0.95560 What time is the next game?

Example Feature Extraction

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

MODEL = "cardiffnlp/twitter-roberta-base-mar2021"
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)