Commit
•
4057f98
1
Parent(s):
0fd7b3a
Upload 7 files
Browse files- README.md +96 -0
- config.json +27 -0
- gitattributes.txt +17 -0
- qa_model_robust.bin +3 -0
- special_tokens_map.json +1 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
README.md
ADDED
@@ -0,0 +1,96 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
language:
|
3 |
+
- vi
|
4 |
+
- vn
|
5 |
+
- en
|
6 |
+
tags:
|
7 |
+
- question-answering
|
8 |
+
- pytorch
|
9 |
+
datasets:
|
10 |
+
- squad
|
11 |
+
license: cc-by-nc-4.0
|
12 |
+
pipeline_tag: question-answering
|
13 |
+
metrics:
|
14 |
+
- squad
|
15 |
+
widget:
|
16 |
+
- text: "Bình là chuyên gia về gì ?"
|
17 |
+
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"
|
18 |
+
- text: "Bình được công nhận với danh hiệu gì ?"
|
19 |
+
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"
|
20 |
+
---
|
21 |
+
## Model Description
|
22 |
+
|
23 |
+
- Language model: [XLM-RoBERTa](https://huggingface.co/transformers/model_doc/xlmroberta.html)
|
24 |
+
- Fine-tune: [MRCQuestionAnswering](https://github.com/nguyenvulebinh/extractive-qa-mrc)
|
25 |
+
- Language: Vietnamese, Englsih
|
26 |
+
- Downstream-task: Extractive QA
|
27 |
+
- Dataset (combine English and Vietnamese):
|
28 |
+
- [Squad 2.0](https://rajpurkar.github.io/SQuAD-explorer/)
|
29 |
+
- [mailong25](https://github.com/mailong25/bert-vietnamese-question-answering/tree/master/dataset)
|
30 |
+
- [UIT-ViQuAD](https://www.aclweb.org/anthology/2020.coling-main.233/)
|
31 |
+
- [MultiLingual Question Answering](https://github.com/facebookresearch/MLQA)
|
32 |
+
|
33 |
+
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 using 10% of the Vietnamese dataset.
|
34 |
+
|
35 |
+
|
36 |
+
| Model | EM | F1 |
|
37 |
+
| ------------- | ------------- | ------------- |
|
38 |
+
| [base](https://huggingface.co/nguyenvulebinh/vi-mrc-base) | 76.43 | 84.16 |
|
39 |
+
| [large](https://huggingface.co/nguyenvulebinh/vi-mrc-large) | 77.32 | 85.46 |
|
40 |
+
|
41 |
+
|
42 |
+
[MRCQuestionAnswering](https://github.com/nguyenvulebinh/extractive-qa-mrc) using [XLM-RoBERTa](https://huggingface.co/transformers/model_doc/xlmroberta.html) 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.
|
43 |
+
|
44 |
+
## Using pre-trained model
|
45 |
+
|
46 |
+
[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1Yqgdfaca7L94OyQVnq5iQq8wRTFvVZjv?usp=sharing)
|
47 |
+
|
48 |
+
- Hugging Face pipeline style (**NOT using sum features strategy**).
|
49 |
+
|
50 |
+
```python
|
51 |
+
from transformers import pipeline
|
52 |
+
# model_checkpoint = "nguyenvulebinh/vi-mrc-large"
|
53 |
+
model_checkpoint = "nguyenvulebinh/vi-mrc-base"
|
54 |
+
nlp = pipeline('question-answering', model=model_checkpoint,
|
55 |
+
tokenizer=model_checkpoint)
|
56 |
+
QA_input = {
|
57 |
+
'question': "Bình là chuyên gia về gì ?",
|
58 |
+
'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"
|
59 |
+
}
|
60 |
+
res = nlp(QA_input)
|
61 |
+
print('pipeline: {}'.format(res))
|
62 |
+
#{'score': 0.5782045125961304, 'start': 45, 'end': 68, 'answer': 'xử lý ngôn ngữ tự nhiên'}
|
63 |
+
```
|
64 |
+
|
65 |
+
- More accurate infer process ([**Using sum features strategy**](https://github.com/nguyenvulebinh/extractive-qa-mrc))
|
66 |
+
|
67 |
+
```python
|
68 |
+
from infer import tokenize_function, data_collator, extract_answer
|
69 |
+
from model.mrc_model import MRCQuestionAnswering
|
70 |
+
from transformers import AutoTokenizer
|
71 |
+
|
72 |
+
# model_checkpoint = "nguyenvulebinh/vi-mrc-large"
|
73 |
+
model_checkpoint = "nguyenvulebinh/vi-mrc-base"
|
74 |
+
tokenizer = AutoTokenizer.from_pretrained(model_checkpoint)
|
75 |
+
model = MRCQuestionAnswering.from_pretrained(model_checkpoint)
|
76 |
+
|
77 |
+
QA_input = {
|
78 |
+
'question': "Bình được công nhận với danh hiệu gì ?",
|
79 |
+
'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"
|
80 |
+
}
|
81 |
+
|
82 |
+
inputs = [tokenize_function(*QA_input)]
|
83 |
+
inputs_ids = data_collator(inputs)
|
84 |
+
outputs = model(**inputs_ids)
|
85 |
+
answer = extract_answer(inputs, outputs, tokenizer)
|
86 |
+
|
87 |
+
print(answer)
|
88 |
+
# answer: Google Developer Expert. Score start: 0.9926977753639221, Score end: 0.9909810423851013
|
89 |
+
```
|
90 |
+
|
91 |
+
## About
|
92 |
+
|
93 |
+
*Built by Binh Nguyen*
|
94 |
+
[![Follow](https://img.shields.io/twitter/follow/nguyenvulebinh?style=social)](https://twitter.com/intent/follow?screen_name=nguyenvulebinh)
|
95 |
+
For more details, visit the project repository.
|
96 |
+
[![GitHub stars](https://img.shields.io/github/stars/nguyenvulebinh/extractive-qa-mrc?style=social)](https://github.com/nguyenvulebinh/extractive-qa-mrc)
|
config.json
ADDED
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "xlm-roberta-base",
|
3 |
+
"architectures": [
|
4 |
+
"XLMRobertaForQuestionAnswering"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"eos_token_id": 2,
|
9 |
+
"gradient_checkpointing": false,
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_dropout_prob": 0.1,
|
12 |
+
"hidden_size": 768,
|
13 |
+
"initializer_range": 0.02,
|
14 |
+
"intermediate_size": 3072,
|
15 |
+
"layer_norm_eps": 1e-05,
|
16 |
+
"max_position_embeddings": 514,
|
17 |
+
"model_type": "roberta",
|
18 |
+
"num_attention_heads": 12,
|
19 |
+
"num_hidden_layers": 12,
|
20 |
+
"output_past": true,
|
21 |
+
"pad_token_id": 1,
|
22 |
+
"position_embedding_type": "absolute",
|
23 |
+
"transformers_version": "4.8.2",
|
24 |
+
"type_vocab_size": 1,
|
25 |
+
"use_cache": true,
|
26 |
+
"vocab_size": 250002
|
27 |
+
}
|
gitattributes.txt
ADDED
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
*.bin.* filter=lfs diff=lfs merge=lfs -text
|
2 |
+
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
3 |
+
*.bin filter=lfs diff=lfs merge=lfs -text
|
4 |
+
*.h5 filter=lfs diff=lfs merge=lfs -text
|
5 |
+
*.tflite filter=lfs diff=lfs merge=lfs -text
|
6 |
+
*.tar.gz filter=lfs diff=lfs merge=lfs -text
|
7 |
+
*.ot filter=lfs diff=lfs merge=lfs -text
|
8 |
+
*.onnx filter=lfs diff=lfs merge=lfs -text
|
9 |
+
*.arrow filter=lfs diff=lfs merge=lfs -text
|
10 |
+
*.ftz filter=lfs diff=lfs merge=lfs -text
|
11 |
+
*.joblib filter=lfs diff=lfs merge=lfs -text
|
12 |
+
*.model filter=lfs diff=lfs merge=lfs -text
|
13 |
+
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
14 |
+
*.pb filter=lfs diff=lfs merge=lfs -text
|
15 |
+
*.pt filter=lfs diff=lfs merge=lfs -text
|
16 |
+
*.pth filter=lfs diff=lfs merge=lfs -text
|
17 |
+
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
qa_model_robust.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:19be6e4d2f8a31bcf159420fd7af8591df71b3094d60ce5e1b63c504ecc493d4
|
3 |
+
size 2235508081
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "xlm-roberta-base", "tokenizer_class": "XLMRobertaTokenizer"}
|