model update
Browse files- README.md +158 -0
- config.json +1 -1
- eval/metric.first.answer.paragraph.questions_answers.lmqg_qag_esquad.default.json +1 -0
- eval/samples.test.hyp.paragraph.questions_answers.lmqg_qag_esquad.default.txt +0 -0
- eval/samples.validation.hyp.paragraph.questions_answers.lmqg_qag_esquad.default.txt +0 -0
- pytorch_model.bin +2 -2
- tokenizer_config.json +1 -1
- trainer_config.json +1 -0
README.md
ADDED
@@ -0,0 +1,158 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
|
2 |
+
---
|
3 |
+
license: cc-by-4.0
|
4 |
+
metrics:
|
5 |
+
- bleu4
|
6 |
+
- meteor
|
7 |
+
- rouge-l
|
8 |
+
- bertscore
|
9 |
+
- moverscore
|
10 |
+
language: es
|
11 |
+
datasets:
|
12 |
+
- lmqg/qag_esquad
|
13 |
+
pipeline_tag: text2text-generation
|
14 |
+
tags:
|
15 |
+
- questions and answers generation
|
16 |
+
widget:
|
17 |
+
- text: "del Ministerio de Desarrollo Urbano , Gobierno de la India."
|
18 |
+
example_title: "Questions & Answers Generation Example 1"
|
19 |
+
model-index:
|
20 |
+
- name: lmqg/mbart-large-cc25-esquad-qag
|
21 |
+
results:
|
22 |
+
- task:
|
23 |
+
name: Text2text Generation
|
24 |
+
type: text2text-generation
|
25 |
+
dataset:
|
26 |
+
name: lmqg/qag_esquad
|
27 |
+
type: default
|
28 |
+
args: default
|
29 |
+
metrics:
|
30 |
+
- name: BLEU4 (Question & Answer Generation)
|
31 |
+
type: bleu4_question_answer_generation
|
32 |
+
value: 2.92
|
33 |
+
- name: ROUGE-L (Question & Answer Generation)
|
34 |
+
type: rouge_l_question_answer_generation
|
35 |
+
value: 16.2
|
36 |
+
- name: METEOR (Question & Answer Generation)
|
37 |
+
type: meteor_question_answer_generation
|
38 |
+
value: 23.46
|
39 |
+
- name: BERTScore (Question & Answer Generation)
|
40 |
+
type: bertscore_question_answer_generation
|
41 |
+
value: 69.37
|
42 |
+
- name: MoverScore (Question & Answer Generation)
|
43 |
+
type: moverscore_question_answer_generation
|
44 |
+
value: 51.66
|
45 |
+
- name: QAAlignedF1Score-BERTScore (Question & Answer Generation)
|
46 |
+
type: qa_aligned_f1_score_bertscore_question_answer_generation
|
47 |
+
value: 78.8
|
48 |
+
- name: QAAlignedRecall-BERTScore (Question & Answer Generation)
|
49 |
+
type: qa_aligned_recall_bertscore_question_answer_generation
|
50 |
+
value: 81.21
|
51 |
+
- name: QAAlignedPrecision-BERTScore (Question & Answer Generation)
|
52 |
+
type: qa_aligned_precision_bertscore_question_answer_generation
|
53 |
+
value: 76.59
|
54 |
+
- name: QAAlignedF1Score-MoverScore (Question & Answer Generation)
|
55 |
+
type: qa_aligned_f1_score_moverscore_question_answer_generation
|
56 |
+
value: 54.0
|
57 |
+
- name: QAAlignedRecall-MoverScore (Question & Answer Generation)
|
58 |
+
type: qa_aligned_recall_moverscore_question_answer_generation
|
59 |
+
value: 55.63
|
60 |
+
- name: QAAlignedPrecision-MoverScore (Question & Answer Generation)
|
61 |
+
type: qa_aligned_precision_moverscore_question_answer_generation
|
62 |
+
value: 52.57
|
63 |
+
---
|
64 |
+
|
65 |
+
# Model Card of `lmqg/mbart-large-cc25-esquad-qag`
|
66 |
+
This model is fine-tuned version of [facebook/mbart-large-cc25](https://huggingface.co/facebook/mbart-large-cc25) for question & answer pair generation task on the [lmqg/qag_esquad](https://huggingface.co/datasets/lmqg/qag_esquad) (dataset_name: default) via [`lmqg`](https://github.com/asahi417/lm-question-generation).
|
67 |
+
|
68 |
+
|
69 |
+
### Overview
|
70 |
+
- **Language model:** [facebook/mbart-large-cc25](https://huggingface.co/facebook/mbart-large-cc25)
|
71 |
+
- **Language:** es
|
72 |
+
- **Training data:** [lmqg/qag_esquad](https://huggingface.co/datasets/lmqg/qag_esquad) (default)
|
73 |
+
- **Online Demo:** [https://autoqg.net/](https://autoqg.net/)
|
74 |
+
- **Repository:** [https://github.com/asahi417/lm-question-generation](https://github.com/asahi417/lm-question-generation)
|
75 |
+
- **Paper:** [https://arxiv.org/abs/2210.03992](https://arxiv.org/abs/2210.03992)
|
76 |
+
|
77 |
+
### Usage
|
78 |
+
- With [`lmqg`](https://github.com/asahi417/lm-question-generation#lmqg-language-model-for-question-generation-)
|
79 |
+
```python
|
80 |
+
from lmqg import TransformersQG
|
81 |
+
|
82 |
+
# initialize model
|
83 |
+
model = TransformersQG(language="es", model="lmqg/mbart-large-cc25-esquad-qag")
|
84 |
+
|
85 |
+
# model prediction
|
86 |
+
question_answer_pairs = model.generate_qa("a noviembre , que es también la estación lluviosa.")
|
87 |
+
|
88 |
+
```
|
89 |
+
|
90 |
+
- With `transformers`
|
91 |
+
```python
|
92 |
+
from transformers import pipeline
|
93 |
+
|
94 |
+
pipe = pipeline("text2text-generation", "lmqg/mbart-large-cc25-esquad-qag")
|
95 |
+
output = pipe("del Ministerio de Desarrollo Urbano , Gobierno de la India.")
|
96 |
+
|
97 |
+
```
|
98 |
+
|
99 |
+
## Evaluation
|
100 |
+
|
101 |
+
|
102 |
+
- ***Metric (Question & Answer Generation)***: [raw metric file](https://huggingface.co/lmqg/mbart-large-cc25-esquad-qag/raw/main/eval/metric.first.answer.paragraph.questions_answers.lmqg_qag_esquad.default.json)
|
103 |
+
|
104 |
+
| | Score | Type | Dataset |
|
105 |
+
|:--------------------------------|--------:|:--------|:-------------------------------------------------------------------|
|
106 |
+
| BERTScore | 69.37 | default | [lmqg/qag_esquad](https://huggingface.co/datasets/lmqg/qag_esquad) |
|
107 |
+
| Bleu_1 | 11.18 | default | [lmqg/qag_esquad](https://huggingface.co/datasets/lmqg/qag_esquad) |
|
108 |
+
| Bleu_2 | 6.31 | default | [lmqg/qag_esquad](https://huggingface.co/datasets/lmqg/qag_esquad) |
|
109 |
+
| Bleu_3 | 4.12 | default | [lmqg/qag_esquad](https://huggingface.co/datasets/lmqg/qag_esquad) |
|
110 |
+
| Bleu_4 | 2.92 | default | [lmqg/qag_esquad](https://huggingface.co/datasets/lmqg/qag_esquad) |
|
111 |
+
| METEOR | 23.46 | default | [lmqg/qag_esquad](https://huggingface.co/datasets/lmqg/qag_esquad) |
|
112 |
+
| MoverScore | 51.66 | default | [lmqg/qag_esquad](https://huggingface.co/datasets/lmqg/qag_esquad) |
|
113 |
+
| QAAlignedF1Score (BERTScore) | 78.8 | default | [lmqg/qag_esquad](https://huggingface.co/datasets/lmqg/qag_esquad) |
|
114 |
+
| QAAlignedF1Score (MoverScore) | 54 | default | [lmqg/qag_esquad](https://huggingface.co/datasets/lmqg/qag_esquad) |
|
115 |
+
| QAAlignedPrecision (BERTScore) | 76.59 | default | [lmqg/qag_esquad](https://huggingface.co/datasets/lmqg/qag_esquad) |
|
116 |
+
| QAAlignedPrecision (MoverScore) | 52.57 | default | [lmqg/qag_esquad](https://huggingface.co/datasets/lmqg/qag_esquad) |
|
117 |
+
| QAAlignedRecall (BERTScore) | 81.21 | default | [lmqg/qag_esquad](https://huggingface.co/datasets/lmqg/qag_esquad) |
|
118 |
+
| QAAlignedRecall (MoverScore) | 55.63 | default | [lmqg/qag_esquad](https://huggingface.co/datasets/lmqg/qag_esquad) |
|
119 |
+
| ROUGE_L | 16.2 | default | [lmqg/qag_esquad](https://huggingface.co/datasets/lmqg/qag_esquad) |
|
120 |
+
|
121 |
+
|
122 |
+
|
123 |
+
## Training hyperparameters
|
124 |
+
|
125 |
+
The following hyperparameters were used during fine-tuning:
|
126 |
+
- dataset_path: lmqg/qag_esquad
|
127 |
+
- dataset_name: default
|
128 |
+
- input_types: ['paragraph']
|
129 |
+
- output_types: ['questions_answers']
|
130 |
+
- prefix_types: None
|
131 |
+
- model: facebook/mbart-large-cc25
|
132 |
+
- max_length: 512
|
133 |
+
- max_length_output: 256
|
134 |
+
- epoch: 6
|
135 |
+
- batch: 8
|
136 |
+
- lr: 0.0001
|
137 |
+
- fp16: False
|
138 |
+
- random_seed: 1
|
139 |
+
- gradient_accumulation_steps: 8
|
140 |
+
- label_smoothing: 0.0
|
141 |
+
|
142 |
+
The full configuration can be found at [fine-tuning config file](https://huggingface.co/lmqg/mbart-large-cc25-esquad-qag/raw/main/trainer_config.json).
|
143 |
+
|
144 |
+
## Citation
|
145 |
+
```
|
146 |
+
@inproceedings{ushio-etal-2022-generative,
|
147 |
+
title = "{G}enerative {L}anguage {M}odels for {P}aragraph-{L}evel {Q}uestion {G}eneration",
|
148 |
+
author = "Ushio, Asahi and
|
149 |
+
Alva-Manchego, Fernando and
|
150 |
+
Camacho-Collados, Jose",
|
151 |
+
booktitle = "Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing",
|
152 |
+
month = dec,
|
153 |
+
year = "2022",
|
154 |
+
address = "Abu Dhabi, U.A.E.",
|
155 |
+
publisher = "Association for Computational Linguistics",
|
156 |
+
}
|
157 |
+
|
158 |
+
```
|
config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "lmqg_output/mbart-large-cc25-esquad-qag/
|
3 |
"_num_labels": 3,
|
4 |
"activation_dropout": 0.0,
|
5 |
"activation_function": "gelu",
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "lmqg_output/mbart-large-cc25-esquad-qag/model_rhkikp/epoch_5",
|
3 |
"_num_labels": 3,
|
4 |
"activation_dropout": 0.0,
|
5 |
"activation_function": "gelu",
|
eval/metric.first.answer.paragraph.questions_answers.lmqg_qag_esquad.default.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"validation": {"Bleu_1": 0.3775892312175896, "Bleu_2": 0.23764467891865557, "Bleu_3": 0.15670107714112402, "Bleu_4": 0.11181717354161862, "METEOR": 0.2558211200072406, "ROUGE_L": 0.2527730104939213, "BERTScore": 0.7797669092987145, "MoverScore": 0.5517274871835631, "QAAlignedF1Score (BERTScore)": 0.8105504386013652, "QAAlignedRecall (BERTScore)": 0.8093026194767589, "QAAlignedPrecision (BERTScore)": 0.812249749015112, "QAAlignedF1Score (MoverScore)": 0.5581592928354873, "QAAlignedRecall (MoverScore)": 0.5537112729030709, "QAAlignedPrecision (MoverScore)": 0.5630080858016486}, "test": {"Bleu_1": 0.1117971924460455, "Bleu_2": 0.06307115412416991, "Bleu_3": 0.04115312922262991, "Bleu_4": 0.029175771714137523, "METEOR": 0.23456585024468432, "ROUGE_L": 0.16203444172931028, "BERTScore": 0.6936825818450294, "MoverScore": 0.5165533664571743, "QAAlignedF1Score (BERTScore)": 0.7879629566119196, "QAAlignedRecall (BERTScore)": 0.8120647200994401, "QAAlignedPrecision (BERTScore)": 0.7659144650772157, "QAAlignedF1Score (MoverScore)": 0.5400310902912929, "QAAlignedRecall (MoverScore)": 0.5562879062744285, "QAAlignedPrecision (MoverScore)": 0.5256799550779248}}
|
eval/samples.test.hyp.paragraph.questions_answers.lmqg_qag_esquad.default.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
eval/samples.validation.hyp.paragraph.questions_answers.lmqg_qag_esquad.default.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:48838e59ff6c2d73dc7843b394464f8f3dd401f188d34d85a302be328a89a412
|
3 |
+
size 2444583801
|
tokenizer_config.json
CHANGED
@@ -12,7 +12,7 @@
|
|
12 |
"single_word": false
|
13 |
},
|
14 |
"model_max_length": 1024,
|
15 |
-
"name_or_path": "lmqg_output/mbart-large-cc25-esquad-qag/
|
16 |
"pad_token": "<pad>",
|
17 |
"sep_token": "</s>",
|
18 |
"special_tokens_map_file": null,
|
|
|
12 |
"single_word": false
|
13 |
},
|
14 |
"model_max_length": 1024,
|
15 |
+
"name_or_path": "lmqg_output/mbart-large-cc25-esquad-qag/model_rhkikp/epoch_5",
|
16 |
"pad_token": "<pad>",
|
17 |
"sep_token": "</s>",
|
18 |
"special_tokens_map_file": null,
|
trainer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"dataset_path": "lmqg/qag_esquad", "dataset_name": "default", "input_types": ["paragraph"], "output_types": ["questions_answers"], "prefix_types": null, "model": "facebook/mbart-large-cc25", "max_length": 512, "max_length_output": 256, "epoch": 6, "batch": 8, "lr": 0.0001, "fp16": false, "random_seed": 1, "gradient_accumulation_steps": 8, "label_smoothing": 0.0}
|