Total runs:
769.7K
Run Growth:
0
Growth Rate:
0.00%
Sponsored by
APIMart
nguyenvulebinh / vi-mrc-large
Model's Last Updated: March 14 2022
question-answering
Introduction of vi-mrc-large
Model Details of vi-mrc-large
Model Description
- Language model: XLM-RoBERTa
- Fine-tune: MRCQuestionAnswering
- Language: Vietnamese, Englsih
- Downstream-task: Extractive QA
- Dataset (combine English and Vietnamese):
This model is intended to be used for QA in the Vietnamese language so the valid set is Vietnamese only (but English works fine). The evaluation result below uses the VLSP MRC 2021 test set. This experiment achieves TOP 1 on the leaderboard.
| Public leaderboard | Private leaderboard |
|---|---|
|
|
MRCQuestionAnswering using XLM-RoBERTa as a pre-trained language model. By default, XLM-RoBERTa will split word in to sub-words. But in my implementation, I re-combine sub-words representation (after encoded by BERT layer) into word representation using sum strategy.
Using pre-trained model
- Hugging Face pipeline style ( NOT using sum features strategy ).
from transformers import pipeline
# model_checkpoint = "nguyenvulebinh/vi-mrc-large"
model_checkpoint = "nguyenvulebinh/vi-mrc-base"
nlp = pipeline('question-answering', model=model_checkpoint,
tokenizer=model_checkpoint)
QA_input = {
'question': "Bình là chuyên gia về gì ?",
'context': "Bình Nguyễn là một người đam mê với lĩnh vực xử lý ngôn ngữ tự nhiên . Anh nhận chứng chỉ Google Developer Expert năm 2020"
}
res = nlp(QA_input)
print('pipeline: {}'.format(res))
#{'score': 0.5782045125961304, 'start': 45, 'end': 68, 'answer': 'xử lý ngôn ngữ tự nhiên'}
- More accurate infer process ( Using sum features strategy )
from infer import tokenize_function, data_collator, extract_answer
from model.mrc_model import MRCQuestionAnswering
from transformers import AutoTokenizer
model_checkpoint = "nguyenvulebinh/vi-mrc-large"
#model_checkpoint = "nguyenvulebinh/vi-mrc-base"
tokenizer = AutoTokenizer.from_pretrained(model_checkpoint)
model = MRCQuestionAnswering.from_pretrained(model_checkpoint)
QA_input = {
'question': "Bình được công nhận với danh hiệu gì ?",
'context': "Bình Nguyễn là một người đam mê với lĩnh vực xử lý ngôn ngữ tự nhiên . Anh nhận chứng chỉ Google Developer Expert năm 2020"
}
inputs = [tokenize_function(*QA_input)]
inputs_ids = data_collator(inputs)
outputs = model(**inputs_ids)
answer = extract_answer(inputs, outputs, tokenizer)
print(answer)
# answer: Google Developer Expert. Score start: 0.9926977753639221, Score end: 0.9909810423851013
About
Built by Binh Nguyen
Runs of nguyenvulebinh vi-mrc-large on huggingface.co
135
Total runs
0
24-hour runs
0
3-day runs
-9.7K
7-day runs
-109.7K
30-day runs
More Information About vi-mrc-large huggingface.co Model
Url of vi-mrc-large
vi-mrc-large huggingface.co Url
Provider of vi-mrc-large huggingface.co
Other API from nguyenvulebinh
Updated:February 21 2023
Total runs:
25.7K
Run Growth:
-1.3K
Growth Rate:
-5.26%
Total runs:
8.1K
Run Growth:
2.1K
Growth Rate:
26.02%
Total runs:
4.7K
Run Growth:
4.1K
Growth Rate:
85.11%
Total runs:
2.6K
Run Growth:
-12.1K
Growth Rate:
-492.03%
Total runs:
766
Run Growth:
-2
Growth Rate:
-0.26%
Total runs:
270
Run Growth:
1
Growth Rate:
0.37%
Total runs:
226
Run Growth:
152
Growth Rate:
67.86%
Total runs:
193
Run Growth:
23
Growth Rate:
11.79%
Total runs:
191
Run Growth:
-196
Growth Rate:
-98.49%
Total runs:
155
Run Growth:
83
Growth Rate:
53.90%
Total runs:
138
Run Growth:
13
Growth Rate:
9.35%
Total runs:
84
Run Growth:
18
Growth Rate:
21.43%
Total runs:
75
Run Growth:
68
Growth Rate:
90.67%
Total runs:
62
Run Growth:
57
Growth Rate:
93.44%
Total runs:
58
Run Growth:
-115
Growth Rate:
-198.28%
Total runs:
57
Run Growth:
49
Growth Rate:
85.96%
Total runs:
56
Run Growth:
-60
Growth Rate:
-105.26%
Total runs:
43
Run Growth:
9
Growth Rate:
19.15%
Total runs:
41
Run Growth:
5
Growth Rate:
11.90%
Total runs:
33
Run Growth:
-120
Growth Rate:
-324.32%
Total runs:
32
Run Growth:
6
Growth Rate:
18.18%
Total runs:
30
Run Growth:
-172
Growth Rate:
-573.33%
Total runs:
28
Run Growth:
-77
Growth Rate:
-275.00%
Total runs:
21
Run Growth:
4
Growth Rate:
18.18%
Total runs:
19
Run Growth:
-3
Growth Rate:
-15.79%
Total runs:
15
Run Growth:
11
Growth Rate:
68.75%
Total runs:
13
Run Growth:
6
Growth Rate:
42.86%
Total runs:
13
Run Growth:
7
Growth Rate:
53.85%
Total runs:
12
Run Growth:
5
Growth Rate:
38.46%
Total runs:
11
Run Growth:
10
Growth Rate:
83.33%
Total runs:
10
Run Growth:
5
Growth Rate:
50.00%
Total runs:
10
Run Growth:
1
Growth Rate:
10.00%
Total runs:
10
Run Growth:
8
Growth Rate:
72.73%
Total runs:
9
Run Growth:
-17
Growth Rate:
-170.00%
Total runs:
8
Run Growth:
3
Growth Rate:
37.50%
Total runs:
6
Run Growth:
3
Growth Rate:
37.50%
Total runs:
3
Run Growth:
-1
Growth Rate:
-33.33%
Total runs:
2
Run Growth:
0
Growth Rate:
0.00%
Total runs:
1
Run Growth:
-1
Growth Rate:
-100.00%
Total runs:
0
Run Growth:
0
Growth Rate:
0.00%