human-centered-summarization
commited on
Commit
·
d021823
1
Parent(s):
02b1c37
Update README.md
Browse files
README.md
CHANGED
@@ -58,37 +58,6 @@ output = model.generate(
|
|
58 |
print(tokenizer.decode(output[0], skip_special_tokens=True))
|
59 |
# Generated Output: Saudi bank to pay a 3.5% premium to Samba share price. Gulf region’s third-largest lender will have total assets of $220 billion
|
60 |
|
61 |
-
```
|
62 |
-
and also in Tensorflow
|
63 |
-
|
64 |
-
```Python
|
65 |
-
from transformers import PegasusTokenizer, TFPegasusForConditionalGeneration
|
66 |
-
|
67 |
-
# Let's load the model and the tokenizer
|
68 |
-
model_name = "human-centered-summarization/financial-summarization-pegasus"
|
69 |
-
tokenizer = PegasusTokenizer.from_pretrained(model_name)
|
70 |
-
model = TFPegasusForConditionalGeneration.from_pretrained(model_name)
|
71 |
-
|
72 |
-
# Some text to summarize here
|
73 |
-
text_to_summarize = "National Commercial Bank (NCB), Saudi Arabia’s largest lender by assets, agreed to buy rival Samba Financial Group for $15 billion in the biggest banking takeover this year.NCB will pay 28.45 riyals ($7.58) for each Samba share, according to a statement on Sunday, valuing it at about 55.7 billion riyals. NCB will offer 0.739 new shares for each Samba share, at the lower end of the 0.736-0.787 ratio the banks set when they signed an initial framework agreement in June.The offer is a 3.5% premium to Samba’s Oct. 8 closing price of 27.50 riyals and about 24% higher than the level the shares traded at before the talks were made public. Bloomberg News first reported the merger discussions.The new bank will have total assets of more than $220 billion, creating the Gulf region’s third-largest lender. The entity’s $46 billion market capitalization nearly matches that of Qatar National Bank QPSC, which is still the Middle East’s biggest lender with about $268 billion of assets."
|
74 |
-
|
75 |
-
# Tokenize our text
|
76 |
-
input_ids = tokenizer(text_to_summarize, return_tensors="tf").input_ids
|
77 |
-
|
78 |
-
# Generate the output (Here, we use beam search but you can also use any other strategy you like)
|
79 |
-
output = model.generate(
|
80 |
-
input_ids,
|
81 |
-
max_length=32,
|
82 |
-
num_beams=5,
|
83 |
-
early_stopping=True
|
84 |
-
)
|
85 |
-
|
86 |
-
# Finally, we can print the generated summary
|
87 |
-
print(tokenizer.decode(output[0], skip_special_tokens=True))
|
88 |
-
# Generated Output: Saudi bank to pay a 3.5% premium to Samba share price. Gulf region’s third-largest lender will have total assets of $220 billion
|
89 |
-
|
90 |
-
|
91 |
-
|
92 |
|
93 |
## Evaluation Results
|
94 |
The results before and after the fine-tuning on our dataset are shown below:
|
|
|
58 |
print(tokenizer.decode(output[0], skip_special_tokens=True))
|
59 |
# Generated Output: Saudi bank to pay a 3.5% premium to Samba share price. Gulf region’s third-largest lender will have total assets of $220 billion
|
60 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
61 |
|
62 |
## Evaluation Results
|
63 |
The results before and after the fine-tuning on our dataset are shown below:
|