Hugging Face's logo

nlpaueb
/
sec-bert-base

Fill-Mask
Transformers
PyTorch
TensorFlow
English
bert
pretraining
finance
financial
Inference Endpoints
Model card Files Community
2
nlpaueb commited on
Commit
ca4f005
·
1 Parent(s): 8f7d6ce

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +4 -7
README.md CHANGED
@@ -17,7 +17,7 @@ widget:
17
 
18
  # SEC-BERT
19
 
20
- <img align="center" src="https://i.ibb.co/0yz81K9/sec-bert-logo.png" alt="sec-bert-logo" width="400"/>
21
 
22
  SEC-BERT is a family of BERT models for the financial domain, intended to assist financial NLP research and FinTech applications.
23
  SEC-BERT consists of the following models:
@@ -60,8 +60,7 @@ model = AutoModel.from_pretrained("nlpaueb/sec-bert-base")
60
  | **SEC-BERT-BASE** | increased (0.678), decreased (0.282), declined (0.017), grew (0.016), rose (0.004)
61
  | **SEC-BERT-NUM** | increased (0.753), decreased (0.211), grew (0.019), declined (0.010), rose (0.006)
62
  | **SEC-BERT-SHAPE** | increased (0.747), decreased (0.214), grew (0.021), declined (0.013), rose (0.002)
63
-
64
-
65
  | Sample | Masked Token |
66
  | --------------------------------------------------- | ------------ |
67
  | Total net sales decreased 2% or $5.4 [MASK] during 2019 compared to 2018. | billion
@@ -72,8 +71,7 @@ model = AutoModel.from_pretrained("nlpaueb/sec-bert-base")
72
  | **SEC-BERT-BASE** | million (0.972), billion (0.028), millions (0.000), ##million (0.000), m (0.000)
73
  | **SEC-BERT-NUM** | million (0.974), billion (0.012), , (0.010), thousand (0.003), m (0.000)
74
  | **SEC-BERT-SHAPE** | million (0.978), billion (0.021), % (0.000), , (0.000), millions (0.000)
75
-
76
-
77
  | Sample | Masked Token |
78
  | --------------------------------------------------- | ------------ |
79
  | Total net sales decreased [MASK]% or $5.4 billion during 2019 compared to 2018. | 2
@@ -84,8 +82,7 @@ model = AutoModel.from_pretrained("nlpaueb/sec-bert-base")
84
  | **SEC-BERT-BASE** | 13 (0.045), 12 (0.040), 11 (0.040), 14 (0.035), 10 (0.035)
85
  | **SEC-BERT-NUM** | [NUM] (1.000), one (0.000), five (0.000), three (0.000), seven (0.000)
86
  | **SEC-BERT-SHAPE** | [XX] (0.316), [XX.X] (0.253), [X.X] (0.237), [X] (0.188), [X.XX] (0.002)
87
-
88
-
89
  | Sample | Masked Token |
90
  | --------------------------------------------------- | ------------ |
91
  | Total net sales decreased 2[MASK] or $5.4 billion during 2019 compared to 2018. | %
 
17
 
18
  # SEC-BERT
19
 
20
+ <img align="center" src="https://i.ibb.co/0yz81K9/sec-bert-logo.png" alt="SEC-BERT" width="400"/>
21
 
22
  SEC-BERT is a family of BERT models for the financial domain, intended to assist financial NLP research and FinTech applications.
23
  SEC-BERT consists of the following models:
 
60
  | **SEC-BERT-BASE** | increased (0.678), decreased (0.282), declined (0.017), grew (0.016), rose (0.004)
61
  | **SEC-BERT-NUM** | increased (0.753), decreased (0.211), grew (0.019), declined (0.010), rose (0.006)
62
  | **SEC-BERT-SHAPE** | increased (0.747), decreased (0.214), grew (0.021), declined (0.013), rose (0.002)
63
+ ---
 
64
  | Sample | Masked Token |
65
  | --------------------------------------------------- | ------------ |
66
  | Total net sales decreased 2% or $5.4 [MASK] during 2019 compared to 2018. | billion
 
71
  | **SEC-BERT-BASE** | million (0.972), billion (0.028), millions (0.000), ##million (0.000), m (0.000)
72
  | **SEC-BERT-NUM** | million (0.974), billion (0.012), , (0.010), thousand (0.003), m (0.000)
73
  | **SEC-BERT-SHAPE** | million (0.978), billion (0.021), % (0.000), , (0.000), millions (0.000)
74
+ ---
 
75
  | Sample | Masked Token |
76
  | --------------------------------------------------- | ------------ |
77
  | Total net sales decreased [MASK]% or $5.4 billion during 2019 compared to 2018. | 2
 
82
  | **SEC-BERT-BASE** | 13 (0.045), 12 (0.040), 11 (0.040), 14 (0.035), 10 (0.035)
83
  | **SEC-BERT-NUM** | [NUM] (1.000), one (0.000), five (0.000), three (0.000), seven (0.000)
84
  | **SEC-BERT-SHAPE** | [XX] (0.316), [XX.X] (0.253), [X.X] (0.237), [X] (0.188), [X.XX] (0.002)
85
+ ---
 
86
  | Sample | Masked Token |
87
  | --------------------------------------------------- | ------------ |
88
  | Total net sales decreased 2[MASK] or $5.4 billion during 2019 compared to 2018. | %