commit files to HF hub
Browse files- README.md +138 -0
- eval/metric.first.answer.paragraph_answer.question.lmqg_qg_ruquad.default.json +1 -0
- eval/metric.first.sentence.paragraph_answer.question.lmqg_qg_ruquad.default.json +1 -0
- eval/samples.test.hyp.paragraph_answer.question.lmqg_qg_ruquad.default.txt +0 -0
- eval/samples.validation.hyp.paragraph_answer.question.lmqg_qg_ruquad.default.txt +0 -0
README.md
ADDED
@@ -0,0 +1,138 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
|
2 |
+
---
|
3 |
+
license: cc-by-4.0
|
4 |
+
metrics:
|
5 |
+
- bleu4
|
6 |
+
- meteor
|
7 |
+
- rouge-l
|
8 |
+
- bertscore
|
9 |
+
- moverscore
|
10 |
+
language: ru
|
11 |
+
datasets:
|
12 |
+
- lmqg/qg_ruquad
|
13 |
+
pipeline_tag: text2text-generation
|
14 |
+
tags:
|
15 |
+
- question generation
|
16 |
+
widget:
|
17 |
+
- text: "Нелишним будет отметить, что, развивая это направление, Д. И. Менделеев, поначалу априорно выдвинув идею о температуре, при которой высота мениска будет нулевой, <hl> в мае 1860 года <hl> провёл серию опытов."
|
18 |
+
example_title: "Question Generation Example 1"
|
19 |
+
- text: "Однако, франкоязычный <hl> Квебек <hl> практически никогда не включается в состав Латинской Америки."
|
20 |
+
example_title: "Question Generation Example 2"
|
21 |
+
- text: "Классическим примером международного синдиката XX века была группа компаний <hl> Де Бирс <hl> , которая в 1980-е годы контролировала до 90 % мировой торговли алмазами."
|
22 |
+
example_title: "Question Generation Example 3"
|
23 |
+
model-index:
|
24 |
+
- name: vocabtrimmer/mt5-small-trimmed-ru-5000-ruquad-qg
|
25 |
+
results:
|
26 |
+
- task:
|
27 |
+
name: Text2text Generation
|
28 |
+
type: text2text-generation
|
29 |
+
dataset:
|
30 |
+
name: lmqg/qg_ruquad
|
31 |
+
type: default
|
32 |
+
args: default
|
33 |
+
metrics:
|
34 |
+
- name: BLEU4 (Question Generation)
|
35 |
+
type: bleu4_question_generation
|
36 |
+
value: 18.11
|
37 |
+
- name: ROUGE-L (Question Generation)
|
38 |
+
type: rouge_l_question_generation
|
39 |
+
value: 32.84
|
40 |
+
- name: METEOR (Question Generation)
|
41 |
+
type: meteor_question_generation
|
42 |
+
value: 27.7
|
43 |
+
- name: BERTScore (Question Generation)
|
44 |
+
type: bertscore_question_generation
|
45 |
+
value: 85.89
|
46 |
+
- name: MoverScore (Question Generation)
|
47 |
+
type: moverscore_question_generation
|
48 |
+
value: 63.99
|
49 |
+
---
|
50 |
+
|
51 |
+
# Model Card of `vocabtrimmer/mt5-small-trimmed-ru-5000-ruquad-qg`
|
52 |
+
This model is fine-tuned version of [vocabtrimmer/mt5-small-trimmed-ru-5000](https://huggingface.co/vocabtrimmer/mt5-small-trimmed-ru-5000) for question generation task on the [lmqg/qg_ruquad](https://huggingface.co/datasets/lmqg/qg_ruquad) (dataset_name: default) via [`lmqg`](https://github.com/asahi417/lm-question-generation).
|
53 |
+
|
54 |
+
|
55 |
+
### Overview
|
56 |
+
- **Language model:** [vocabtrimmer/mt5-small-trimmed-ru-5000](https://huggingface.co/vocabtrimmer/mt5-small-trimmed-ru-5000)
|
57 |
+
- **Language:** ru
|
58 |
+
- **Training data:** [lmqg/qg_ruquad](https://huggingface.co/datasets/lmqg/qg_ruquad) (default)
|
59 |
+
- **Online Demo:** [https://autoqg.net/](https://autoqg.net/)
|
60 |
+
- **Repository:** [https://github.com/asahi417/lm-question-generation](https://github.com/asahi417/lm-question-generation)
|
61 |
+
- **Paper:** [https://arxiv.org/abs/2210.03992](https://arxiv.org/abs/2210.03992)
|
62 |
+
|
63 |
+
### Usage
|
64 |
+
- With [`lmqg`](https://github.com/asahi417/lm-question-generation#lmqg-language-model-for-question-generation-)
|
65 |
+
```python
|
66 |
+
from lmqg import TransformersQG
|
67 |
+
|
68 |
+
# initialize model
|
69 |
+
model = TransformersQG(language="ru", model="vocabtrimmer/mt5-small-trimmed-ru-5000-ruquad-qg")
|
70 |
+
|
71 |
+
# model prediction
|
72 |
+
questions = model.generate_q(list_context="Нелишним будет отметить, что, развивая это направление, Д. И. Менделеев, поначалу априорно выдвинув идею о температуре, при которой высота мениска будет нулевой, в мае 1860 года провёл серию опытов.", list_answer="в мае 1860 года")
|
73 |
+
|
74 |
+
```
|
75 |
+
|
76 |
+
- With `transformers`
|
77 |
+
```python
|
78 |
+
from transformers import pipeline
|
79 |
+
|
80 |
+
pipe = pipeline("text2text-generation", "vocabtrimmer/mt5-small-trimmed-ru-5000-ruquad-qg")
|
81 |
+
output = pipe("Нелишним будет отметить, что, развивая это направление, Д. И. Менделеев, поначалу априорно выдвинув идею о температуре, при которой высота мениска будет нулевой, <hl> в мае 1860 года <hl> провёл серию опытов.")
|
82 |
+
|
83 |
+
```
|
84 |
+
|
85 |
+
## Evaluation
|
86 |
+
|
87 |
+
|
88 |
+
- ***Metric (Question Generation)***: [raw metric file](https://huggingface.co/vocabtrimmer/mt5-small-trimmed-ru-5000-ruquad-qg/raw/main/eval/metric.first.sentence.paragraph_answer.question.lmqg_qg_ruquad.default.json)
|
89 |
+
|
90 |
+
| | Score | Type | Dataset |
|
91 |
+
|:-----------|--------:|:--------|:-----------------------------------------------------------------|
|
92 |
+
| BERTScore | 85.89 | default | [lmqg/qg_ruquad](https://huggingface.co/datasets/lmqg/qg_ruquad) |
|
93 |
+
| Bleu_1 | 33.9 | default | [lmqg/qg_ruquad](https://huggingface.co/datasets/lmqg/qg_ruquad) |
|
94 |
+
| Bleu_2 | 27.03 | default | [lmqg/qg_ruquad](https://huggingface.co/datasets/lmqg/qg_ruquad) |
|
95 |
+
| Bleu_3 | 21.98 | default | [lmqg/qg_ruquad](https://huggingface.co/datasets/lmqg/qg_ruquad) |
|
96 |
+
| Bleu_4 | 18.11 | default | [lmqg/qg_ruquad](https://huggingface.co/datasets/lmqg/qg_ruquad) |
|
97 |
+
| METEOR | 27.7 | default | [lmqg/qg_ruquad](https://huggingface.co/datasets/lmqg/qg_ruquad) |
|
98 |
+
| MoverScore | 63.99 | default | [lmqg/qg_ruquad](https://huggingface.co/datasets/lmqg/qg_ruquad) |
|
99 |
+
| ROUGE_L | 32.84 | default | [lmqg/qg_ruquad](https://huggingface.co/datasets/lmqg/qg_ruquad) |
|
100 |
+
|
101 |
+
|
102 |
+
|
103 |
+
## Training hyperparameters
|
104 |
+
|
105 |
+
The following hyperparameters were used during fine-tuning:
|
106 |
+
- dataset_path: lmqg/qg_ruquad
|
107 |
+
- dataset_name: default
|
108 |
+
- input_types: paragraph_answer
|
109 |
+
- output_types: question
|
110 |
+
- prefix_types: None
|
111 |
+
- model: vocabtrimmer/mt5-small-trimmed-ru-5000
|
112 |
+
- max_length: 512
|
113 |
+
- max_length_output: 32
|
114 |
+
- epoch: 9
|
115 |
+
- batch: 16
|
116 |
+
- lr: 0.001
|
117 |
+
- fp16: False
|
118 |
+
- random_seed: 1
|
119 |
+
- gradient_accumulation_steps: 4
|
120 |
+
- label_smoothing: 0.15
|
121 |
+
|
122 |
+
The full configuration can be found at [fine-tuning config file](https://huggingface.co/vocabtrimmer/mt5-small-trimmed-ru-5000-ruquad-qg/raw/main/trainer_config.json).
|
123 |
+
|
124 |
+
## Citation
|
125 |
+
```
|
126 |
+
@inproceedings{ushio-etal-2022-generative,
|
127 |
+
title = "{G}enerative {L}anguage {M}odels for {P}aragraph-{L}evel {Q}uestion {G}eneration",
|
128 |
+
author = "Ushio, Asahi and
|
129 |
+
Alva-Manchego, Fernando and
|
130 |
+
Camacho-Collados, Jose",
|
131 |
+
booktitle = "Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing",
|
132 |
+
month = dec,
|
133 |
+
year = "2022",
|
134 |
+
address = "Abu Dhabi, U.A.E.",
|
135 |
+
publisher = "Association for Computational Linguistics",
|
136 |
+
}
|
137 |
+
|
138 |
+
```
|
eval/metric.first.answer.paragraph_answer.question.lmqg_qg_ruquad.default.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"validation": {"Bleu_1": 0.33323020440153595, "Bleu_2": 0.26470998793218703, "Bleu_3": 0.2139568271125248, "Bleu_4": 0.17480922076421068}, "test": {"Bleu_1": 0.33688396241964036, "Bleu_2": 0.268631472631107, "Bleu_3": 0.21852280912727243, "Bleu_4": 0.18002580188556194}}
|
eval/metric.first.sentence.paragraph_answer.question.lmqg_qg_ruquad.default.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"validation": {"Bleu_1": 0.33483442598914326, "Bleu_2": 0.26596888349329795, "Bleu_3": 0.21497285755105475, "Bleu_4": 0.17565047953392995, "METEOR": 0.2773956745082658, "ROUGE_L": 0.3282422738500797, "BERTScore": 0.8594390359252493, "MoverScore": 0.6407921382112461}, "test": {"Bleu_1": 0.339000418235041, "Bleu_2": 0.2702824314533164, "Bleu_3": 0.21983029496766632, "Bleu_4": 0.18105948228750052, "METEOR": 0.2770127167278592, "ROUGE_L": 0.3284407933203291, "BERTScore": 0.858903289381471, "MoverScore": 0.6398641873490714}}
|
eval/samples.test.hyp.paragraph_answer.question.lmqg_qg_ruquad.default.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
eval/samples.validation.hyp.paragraph_answer.question.lmqg_qg_ruquad.default.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|