radmada/FinBERT-BaseVocab-Cased

Usage

from transformers import BertTokenizer, BertForSequenceClassification
import numpy as np

finbert = BertForSequenceClassification.from_pretrained('yiyanghkust/finbert-tone',num_labels=3)
tokenizer = BertTokenizer.from_pretrained('yiyanghkust/finbert-tone')

sentences = ["there is a shortage of capital, and we need extra financing", 
             "growth is strong and we have plenty of liquidity", 
             "there are doubts about our finances", 
             "profits are flat"]

inputs = tokenizer(sentences, return_tensors="pt", padding=True)
outputs = finbert(**inputs)[0]

labels = {0:'neutral', 1:'positive',2:'negative'}
for idx, sent in enumerate(sentences):
    print(sent, '----', labels[np.argmax(outputs.detach().numpy()[idx])])
    
'''
there is a shortage of capital, and we need extra financing ---- negative
growth is strong and we have plenty of liquidity ---- positive
there are doubts about our finances ---- negative
profits are flat ---- neutral
'''

Cite

@misc{yang2020finbert,
    title={FinBERT: A Pretrained Language Model for Financial Communications},
    author={Yi Yang and Mark Christopher Siy UY and Allen Huang},
    year={2020},
    eprint={2006.08097},
    archivePrefix={arXiv},
    }

License

---

license: apache-2.0