model update
Browse files
README.md
CHANGED
@@ -33,205 +33,186 @@ model-index:
|
|
33 |
metrics:
|
34 |
- name: BLEU4
|
35 |
type: bleu4
|
36 |
-
value:
|
37 |
- name: ROUGE-L
|
38 |
type: rouge-l
|
39 |
-
value:
|
40 |
- name: METEOR
|
41 |
type: meteor
|
42 |
-
value:
|
43 |
- name: BERTScore
|
44 |
type: bertscore
|
45 |
-
value:
|
46 |
- name: MoverScore
|
47 |
type: moverscore
|
48 |
-
value:
|
49 |
- task:
|
50 |
name: Text2text Generation
|
51 |
type: text2text-generation
|
52 |
dataset:
|
53 |
-
name: lmqg/
|
54 |
type: default
|
55 |
args: default
|
56 |
metrics:
|
57 |
- name: BLEU4
|
58 |
type: bleu4
|
59 |
-
value:
|
60 |
- name: ROUGE-L
|
61 |
type: rouge-l
|
62 |
-
value: 0.
|
63 |
- name: METEOR
|
64 |
type: meteor
|
65 |
-
value: 0.
|
66 |
- name: BERTScore
|
67 |
type: bertscore
|
68 |
-
value: 0.
|
69 |
- name: MoverScore
|
70 |
type: moverscore
|
71 |
-
value: 0.
|
72 |
- task:
|
73 |
name: Text2text Generation
|
74 |
type: text2text-generation
|
75 |
dataset:
|
76 |
-
name: lmqg/
|
77 |
type: default
|
78 |
args: default
|
79 |
metrics:
|
80 |
- name: BLEU4
|
81 |
type: bleu4
|
82 |
-
value:
|
83 |
- name: ROUGE-L
|
84 |
type: rouge-l
|
85 |
-
value: 0.
|
86 |
- name: METEOR
|
87 |
type: meteor
|
88 |
-
value: 0.
|
89 |
- name: BERTScore
|
90 |
type: bertscore
|
91 |
-
value: 0.
|
92 |
- name: MoverScore
|
93 |
type: moverscore
|
94 |
-
value: 0.
|
95 |
- task:
|
96 |
name: Text2text Generation
|
97 |
type: text2text-generation
|
98 |
dataset:
|
99 |
-
name: lmqg/
|
100 |
type: default
|
101 |
args: default
|
102 |
metrics:
|
103 |
- name: BLEU4
|
104 |
type: bleu4
|
105 |
-
value:
|
106 |
- name: ROUGE-L
|
107 |
type: rouge-l
|
108 |
-
value: 0.
|
109 |
- name: METEOR
|
110 |
type: meteor
|
111 |
-
value: 0.
|
112 |
- name: BERTScore
|
113 |
type: bertscore
|
114 |
-
value: 0.
|
115 |
- name: MoverScore
|
116 |
type: moverscore
|
117 |
-
value: 0.
|
118 |
- task:
|
119 |
name: Text2text Generation
|
120 |
type: text2text-generation
|
121 |
dataset:
|
122 |
-
name: lmqg/
|
123 |
type: default
|
124 |
args: default
|
125 |
metrics:
|
126 |
- name: BLEU4
|
127 |
type: bleu4
|
128 |
-
value:
|
129 |
- name: ROUGE-L
|
130 |
type: rouge-l
|
131 |
-
value: 0.
|
132 |
- name: METEOR
|
133 |
type: meteor
|
134 |
-
value: 0.
|
135 |
- name: BERTScore
|
136 |
type: bertscore
|
137 |
-
value: 0.
|
138 |
- name: MoverScore
|
139 |
type: moverscore
|
140 |
-
value: 0.
|
141 |
- task:
|
142 |
name: Text2text Generation
|
143 |
type: text2text-generation
|
144 |
dataset:
|
145 |
-
name: lmqg/
|
146 |
type: default
|
147 |
args: default
|
148 |
metrics:
|
149 |
- name: BLEU4
|
150 |
type: bleu4
|
151 |
-
value:
|
152 |
- name: ROUGE-L
|
153 |
type: rouge-l
|
154 |
-
value: 0.
|
155 |
- name: METEOR
|
156 |
type: meteor
|
157 |
-
value: 0.
|
158 |
- name: BERTScore
|
159 |
type: bertscore
|
160 |
-
value: 0.
|
161 |
- name: MoverScore
|
162 |
type: moverscore
|
163 |
-
value: 0.
|
164 |
- task:
|
165 |
name: Text2text Generation
|
166 |
type: text2text-generation
|
167 |
dataset:
|
168 |
-
name: lmqg/
|
169 |
type: default
|
170 |
args: default
|
171 |
metrics:
|
172 |
- name: BLEU4
|
173 |
type: bleu4
|
174 |
-
value:
|
175 |
- name: ROUGE-L
|
176 |
type: rouge-l
|
177 |
-
value: 0.
|
178 |
- name: METEOR
|
179 |
type: meteor
|
180 |
-
value: 0.
|
181 |
- name: BERTScore
|
182 |
type: bertscore
|
183 |
-
value: 0.
|
184 |
- name: MoverScore
|
185 |
type: moverscore
|
186 |
-
value: 0.
|
187 |
- task:
|
188 |
name: Text2text Generation
|
189 |
type: text2text-generation
|
190 |
dataset:
|
191 |
-
name: lmqg/
|
192 |
type: default
|
193 |
args: default
|
194 |
metrics:
|
195 |
- name: BLEU4
|
196 |
type: bleu4
|
197 |
-
value:
|
198 |
- name: ROUGE-L
|
199 |
type: rouge-l
|
200 |
-
value: 0.
|
201 |
- name: METEOR
|
202 |
type: meteor
|
203 |
-
value: 0.
|
204 |
- name: BERTScore
|
205 |
type: bertscore
|
206 |
-
value: 0.
|
207 |
- name: MoverScore
|
208 |
type: moverscore
|
209 |
-
value: 0.
|
210 |
---
|
211 |
|
212 |
# Model Card of `lmqg/mt5-small-squad`
|
213 |
-
This model is fine-tuned version of [google/mt5-small](https://huggingface.co/google/mt5-small) for question generation task on the
|
214 |
-
[lmqg/qg_squad](https://huggingface.co/datasets/lmqg/qg_squad) (dataset_name: default) via [`lmqg`](https://github.com/asahi417/lm-question-generation).
|
215 |
|
216 |
|
217 |
-
Please cite our paper if you use the model ([https://arxiv.org/abs/2210.03992](https://arxiv.org/abs/2210.03992)).
|
218 |
-
|
219 |
-
```
|
220 |
-
|
221 |
-
@inproceedings{ushio-etal-2022-generative,
|
222 |
-
title = "{G}enerative {L}anguage {M}odels for {P}aragraph-{L}evel {Q}uestion {G}eneration",
|
223 |
-
author = "Ushio, Asahi and
|
224 |
-
Alva-Manchego, Fernando and
|
225 |
-
Camacho-Collados, Jose",
|
226 |
-
booktitle = "Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing",
|
227 |
-
month = dec,
|
228 |
-
year = "2022",
|
229 |
-
address = "Abu Dhabi, U.A.E.",
|
230 |
-
publisher = "Association for Computational Linguistics",
|
231 |
-
}
|
232 |
-
|
233 |
-
```
|
234 |
-
|
235 |
### Overview
|
236 |
- **Language model:** [google/mt5-small](https://huggingface.co/google/mt5-small)
|
237 |
- **Language:** en
|
@@ -243,48 +224,53 @@ Please cite our paper if you use the model ([https://arxiv.org/abs/2210.03992](h
|
|
243 |
### Usage
|
244 |
- With [`lmqg`](https://github.com/asahi417/lm-question-generation#lmqg-language-model-for-question-generation-)
|
245 |
```python
|
246 |
-
|
247 |
from lmqg import TransformersQG
|
|
|
248 |
# initialize model
|
249 |
-
model = TransformersQG(language=
|
|
|
250 |
# model prediction
|
251 |
-
|
252 |
|
253 |
```
|
254 |
|
255 |
- With `transformers`
|
256 |
```python
|
257 |
-
|
258 |
from transformers import pipeline
|
259 |
-
# initialize model
|
260 |
-
pipe = pipeline("text2text-generation", 'lmqg/mt5-small-squad')
|
261 |
-
# question generation
|
262 |
-
question = pipe('<hl> Beyonce <hl> further expanded her acting career, starring as blues singer Etta James in the 2008 musical biopic, Cadillac Records.')
|
263 |
|
264 |
-
|
|
|
265 |
|
266 |
-
|
267 |
|
|
|
268 |
|
269 |
-
### Metrics
|
270 |
|
271 |
-
|
272 |
-
|:--------|:-----|------:|--------:|-------:|----------:|-----------:|-----:|
|
273 |
-
| [lmqg/qg_squad](https://huggingface.co/datasets/lmqg/qg_squad) | default | 0.217 | 0.489 | 0.238 | 0.9 | 0.627 | [link](https://huggingface.co/lmqg/mt5-small-squad/raw/main/eval/metric.first.sentence.paragraph_answer.question.lmqg_qg_squad.default.json) |
|
274 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
275 |
|
276 |
|
277 |
-
|
278 |
|
279 |
-
| Dataset | Type |
|
280 |
-
|
281 |
-
| [lmqg/
|
282 |
-
| [lmqg/
|
283 |
-
| [lmqg/
|
284 |
-
| [lmqg/
|
285 |
-
| [lmqg/
|
286 |
-
| [lmqg/
|
287 |
-
| [lmqg/
|
288 |
|
289 |
|
290 |
## Training hyperparameters
|
@@ -310,7 +296,6 @@ The full configuration can be found at [fine-tuning config file](https://hugging
|
|
310 |
|
311 |
## Citation
|
312 |
```
|
313 |
-
|
314 |
@inproceedings{ushio-etal-2022-generative,
|
315 |
title = "{G}enerative {L}anguage {M}odels for {P}aragraph-{L}evel {Q}uestion {G}eneration",
|
316 |
author = "Ushio, Asahi and
|
|
|
33 |
metrics:
|
34 |
- name: BLEU4
|
35 |
type: bleu4
|
36 |
+
value: 21.65
|
37 |
- name: ROUGE-L
|
38 |
type: rouge-l
|
39 |
+
value: 48.95
|
40 |
- name: METEOR
|
41 |
type: meteor
|
42 |
+
value: 23.83
|
43 |
- name: BERTScore
|
44 |
type: bertscore
|
45 |
+
value: 90.01
|
46 |
- name: MoverScore
|
47 |
type: moverscore
|
48 |
+
value: 62.75
|
49 |
- task:
|
50 |
name: Text2text Generation
|
51 |
type: text2text-generation
|
52 |
dataset:
|
53 |
+
name: lmqg/qg_dequad
|
54 |
type: default
|
55 |
args: default
|
56 |
metrics:
|
57 |
- name: BLEU4
|
58 |
type: bleu4
|
59 |
+
value: 9.242783121165897e-12
|
60 |
- name: ROUGE-L
|
61 |
type: rouge-l
|
62 |
+
value: 0.01556150764938016
|
63 |
- name: METEOR
|
64 |
type: meteor
|
65 |
+
value: 0.04809700451843158
|
66 |
- name: BERTScore
|
67 |
type: bertscore
|
68 |
+
value: 0.7353078946893743
|
69 |
- name: MoverScore
|
70 |
type: moverscore
|
71 |
+
value: 0.5036973829954939
|
72 |
- task:
|
73 |
name: Text2text Generation
|
74 |
type: text2text-generation
|
75 |
dataset:
|
76 |
+
name: lmqg/qg_esquad
|
77 |
type: default
|
78 |
args: default
|
79 |
metrics:
|
80 |
- name: BLEU4
|
81 |
type: bleu4
|
82 |
+
value: 0.0059191752064594125
|
83 |
- name: ROUGE-L
|
84 |
type: rouge-l
|
85 |
+
value: 0.05208940592236566
|
86 |
- name: METEOR
|
87 |
type: meteor
|
88 |
+
value: 0.06021086135293597
|
89 |
- name: BERTScore
|
90 |
type: bertscore
|
91 |
+
value: 0.7494422899749911
|
92 |
- name: MoverScore
|
93 |
type: moverscore
|
94 |
+
value: 0.5062373132800192
|
95 |
- task:
|
96 |
name: Text2text Generation
|
97 |
type: text2text-generation
|
98 |
dataset:
|
99 |
+
name: lmqg/qg_frquad
|
100 |
type: default
|
101 |
args: default
|
102 |
metrics:
|
103 |
- name: BLEU4
|
104 |
type: bleu4
|
105 |
+
value: 0.0171464639522496
|
106 |
- name: ROUGE-L
|
107 |
type: rouge-l
|
108 |
+
value: 0.1583673053928925
|
109 |
- name: METEOR
|
110 |
type: meteor
|
111 |
+
value: 0.08244973027319356
|
112 |
- name: BERTScore
|
113 |
type: bertscore
|
114 |
+
value: 0.7291012183458674
|
115 |
- name: MoverScore
|
116 |
type: moverscore
|
117 |
+
value: 0.509610854598101
|
118 |
- task:
|
119 |
name: Text2text Generation
|
120 |
type: text2text-generation
|
121 |
dataset:
|
122 |
+
name: lmqg/qg_itquad
|
123 |
type: default
|
124 |
args: default
|
125 |
metrics:
|
126 |
- name: BLEU4
|
127 |
type: bleu4
|
128 |
+
value: 0.005438910607183992
|
129 |
- name: ROUGE-L
|
130 |
type: rouge-l
|
131 |
+
value: 0.05010570221421983
|
132 |
- name: METEOR
|
133 |
type: meteor
|
134 |
+
value: 0.05890828426558759
|
135 |
- name: BERTScore
|
136 |
type: bertscore
|
137 |
+
value: 0.7260160158030385
|
138 |
- name: MoverScore
|
139 |
type: moverscore
|
140 |
+
value: 0.5023119088393686
|
141 |
- task:
|
142 |
name: Text2text Generation
|
143 |
type: text2text-generation
|
144 |
dataset:
|
145 |
+
name: lmqg/qg_jaquad
|
146 |
type: default
|
147 |
args: default
|
148 |
metrics:
|
149 |
- name: BLEU4
|
150 |
type: bleu4
|
151 |
+
value: 4.4114578660129224e-08
|
152 |
- name: ROUGE-L
|
153 |
type: rouge-l
|
154 |
+
value: 0.06084267343290677
|
155 |
- name: METEOR
|
156 |
type: meteor
|
157 |
+
value: 0.005149267426183168
|
158 |
- name: BERTScore
|
159 |
type: bertscore
|
160 |
+
value: 0.6608093198082075
|
161 |
- name: MoverScore
|
162 |
type: moverscore
|
163 |
+
value: 0.46526108687696893
|
164 |
- task:
|
165 |
name: Text2text Generation
|
166 |
type: text2text-generation
|
167 |
dataset:
|
168 |
+
name: lmqg/qg_koquad
|
169 |
type: default
|
170 |
args: default
|
171 |
metrics:
|
172 |
- name: BLEU4
|
173 |
type: bleu4
|
174 |
+
value: 1.4750917137316939e-12
|
175 |
- name: ROUGE-L
|
176 |
type: rouge-l
|
177 |
+
value: 0.0006466767450454226
|
178 |
- name: METEOR
|
179 |
type: meteor
|
180 |
+
value: 0.007310046912436679
|
181 |
- name: BERTScore
|
182 |
type: bertscore
|
183 |
+
value: 0.6634288882769679
|
184 |
- name: MoverScore
|
185 |
type: moverscore
|
186 |
+
value: 0.4586124640357038
|
187 |
- task:
|
188 |
name: Text2text Generation
|
189 |
type: text2text-generation
|
190 |
dataset:
|
191 |
+
name: lmqg/qg_ruquad
|
192 |
type: default
|
193 |
args: default
|
194 |
metrics:
|
195 |
- name: BLEU4
|
196 |
type: bleu4
|
197 |
+
value: 4.229109829516021e-12
|
198 |
- name: ROUGE-L
|
199 |
type: rouge-l
|
200 |
+
value: 0.009881091250723615
|
201 |
- name: METEOR
|
202 |
type: meteor
|
203 |
+
value: 0.017796529053904556
|
204 |
- name: BERTScore
|
205 |
type: bertscore
|
206 |
+
value: 0.7089446693028568
|
207 |
- name: MoverScore
|
208 |
type: moverscore
|
209 |
+
value: 0.49098728551715626
|
210 |
---
|
211 |
|
212 |
# Model Card of `lmqg/mt5-small-squad`
|
213 |
+
This model is fine-tuned version of [google/mt5-small](https://huggingface.co/google/mt5-small) for question generation task on the [lmqg/qg_squad](https://huggingface.co/datasets/lmqg/qg_squad) (dataset_name: default) via [`lmqg`](https://github.com/asahi417/lm-question-generation).
|
|
|
214 |
|
215 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
216 |
### Overview
|
217 |
- **Language model:** [google/mt5-small](https://huggingface.co/google/mt5-small)
|
218 |
- **Language:** en
|
|
|
224 |
### Usage
|
225 |
- With [`lmqg`](https://github.com/asahi417/lm-question-generation#lmqg-language-model-for-question-generation-)
|
226 |
```python
|
|
|
227 |
from lmqg import TransformersQG
|
228 |
+
|
229 |
# initialize model
|
230 |
+
model = TransformersQG(language="en", model="lmqg/mt5-small-squad")
|
231 |
+
|
232 |
# model prediction
|
233 |
+
questions = model.generate_q(list_context="William Turner was an English painter who specialised in watercolour landscapes", list_answer="William Turner")
|
234 |
|
235 |
```
|
236 |
|
237 |
- With `transformers`
|
238 |
```python
|
|
|
239 |
from transformers import pipeline
|
|
|
|
|
|
|
|
|
240 |
|
241 |
+
pipe = pipeline("text2text-generation", "lmqg/mt5-small-squad")
|
242 |
+
output = pipe("<hl> Beyonce <hl> further expanded her acting career, starring as blues singer Etta James in the 2008 musical biopic, Cadillac Records.")
|
243 |
|
244 |
+
```
|
245 |
|
246 |
+
## Evaluation
|
247 |
|
|
|
248 |
|
249 |
+
- ***Metric (Question Generation)***: [raw metric file](https://huggingface.co/lmqg/mt5-small-squad/raw/main/eval/metric.first.sentence.paragraph_answer.question.lmqg_qg_squad.default.json)
|
|
|
|
|
250 |
|
251 |
+
| | Score | Type | Dataset |
|
252 |
+
|:-----------|--------:|:--------|:---------------------------------------------------------------|
|
253 |
+
| BERTScore | 90.01 | default | [lmqg/qg_squad](https://huggingface.co/datasets/lmqg/qg_squad) |
|
254 |
+
| Bleu_1 | 54.07 | default | [lmqg/qg_squad](https://huggingface.co/datasets/lmqg/qg_squad) |
|
255 |
+
| Bleu_2 | 37.62 | default | [lmqg/qg_squad](https://huggingface.co/datasets/lmqg/qg_squad) |
|
256 |
+
| Bleu_3 | 28.18 | default | [lmqg/qg_squad](https://huggingface.co/datasets/lmqg/qg_squad) |
|
257 |
+
| Bleu_4 | 21.65 | default | [lmqg/qg_squad](https://huggingface.co/datasets/lmqg/qg_squad) |
|
258 |
+
| METEOR | 23.83 | default | [lmqg/qg_squad](https://huggingface.co/datasets/lmqg/qg_squad) |
|
259 |
+
| MoverScore | 62.75 | default | [lmqg/qg_squad](https://huggingface.co/datasets/lmqg/qg_squad) |
|
260 |
+
| ROUGE_L | 48.95 | default | [lmqg/qg_squad](https://huggingface.co/datasets/lmqg/qg_squad) |
|
261 |
|
262 |
|
263 |
+
- ***Metrics (Question Generation, Out-of-Domain)***
|
264 |
|
265 |
+
| Dataset | Type | BERTScore| Bleu_4 | METEOR | MoverScore | ROUGE_L | Link |
|
266 |
+
|:--------|:-----|---------:|-------:|-------:|-----------:|--------:|-----:|
|
267 |
+
| [lmqg/qg_dequad](https://huggingface.co/datasets/lmqg/qg_dequad) | default | 73.53 | 0.0 | 4.81 | 50.37 | 1.56 | [link](https://huggingface.co/lmqg/mt5-small-squad/raw/main/eval_ood/metric.first.sentence.paragraph_answer.question.lmqg_qg_dequad.default.json) |
|
268 |
+
| [lmqg/qg_esquad](https://huggingface.co/datasets/lmqg/qg_esquad) | default | 74.94 | 0.59 | 6.02 | 50.62 | 5.21 | [link](https://huggingface.co/lmqg/mt5-small-squad/raw/main/eval_ood/metric.first.sentence.paragraph_answer.question.lmqg_qg_esquad.default.json) |
|
269 |
+
| [lmqg/qg_frquad](https://huggingface.co/datasets/lmqg/qg_frquad) | default | 72.91 | 1.71 | 8.24 | 50.96 | 15.84 | [link](https://huggingface.co/lmqg/mt5-small-squad/raw/main/eval_ood/metric.first.sentence.paragraph_answer.question.lmqg_qg_frquad.default.json) |
|
270 |
+
| [lmqg/qg_itquad](https://huggingface.co/datasets/lmqg/qg_itquad) | default | 72.6 | 0.54 | 5.89 | 50.23 | 5.01 | [link](https://huggingface.co/lmqg/mt5-small-squad/raw/main/eval_ood/metric.first.sentence.paragraph_answer.question.lmqg_qg_itquad.default.json) |
|
271 |
+
| [lmqg/qg_jaquad](https://huggingface.co/datasets/lmqg/qg_jaquad) | default | 66.08 | 0.0 | 0.51 | 46.53 | 6.08 | [link](https://huggingface.co/lmqg/mt5-small-squad/raw/main/eval_ood/metric.first.sentence.paragraph_answer.question.lmqg_qg_jaquad.default.json) |
|
272 |
+
| [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) | default | 66.34 | 0.0 | 0.73 | 45.86 | 0.06 | [link](https://huggingface.co/lmqg/mt5-small-squad/raw/main/eval_ood/metric.first.sentence.paragraph_answer.question.lmqg_qg_koquad.default.json) |
|
273 |
+
| [lmqg/qg_ruquad](https://huggingface.co/datasets/lmqg/qg_ruquad) | default | 70.89 | 0.0 | 1.78 | 49.1 | 0.99 | [link](https://huggingface.co/lmqg/mt5-small-squad/raw/main/eval_ood/metric.first.sentence.paragraph_answer.question.lmqg_qg_ruquad.default.json) |
|
274 |
|
275 |
|
276 |
## Training hyperparameters
|
|
|
296 |
|
297 |
## Citation
|
298 |
```
|
|
|
299 |
@inproceedings{ushio-etal-2022-generative,
|
300 |
title = "{G}enerative {L}anguage {M}odels for {P}aragraph-{L}evel {Q}uestion {G}eneration",
|
301 |
author = "Ushio, Asahi and
|