asahi417 commited on
Commit
d94f733
1 Parent(s): 9ef46e0

model update

Browse files
Files changed (1) hide show
  1. README.md +14 -14
README.md CHANGED
@@ -7,21 +7,21 @@ metrics:
7
  - rouge-l
8
  - bertscore
9
  - moverscore
10
- language: en
11
  datasets:
12
  - lmqg/qg_dequad
13
  pipeline_tag: text2text-generation
14
  tags:
15
  - question generation
16
  widget:
17
- - text: "<hl> Beyonce <hl> further expanded her acting career, starring as blues singer Etta James in the 2008 musical biopic, Cadillac Records."
18
  example_title: "Question Generation Example 1"
19
- - text: "Beyonce further expanded her acting career, starring as blues singer <hl> Etta James <hl> in the 2008 musical biopic, Cadillac Records."
20
  example_title: "Question Generation Example 2"
21
- - text: "Beyonce further expanded her acting career, starring as blues singer Etta James in the 2008 musical biopic, <hl> Cadillac Records <hl> ."
22
  example_title: "Question Generation Example 3"
23
  model-index:
24
- - name: lmqg/mt5-small-dequad
25
  results:
26
  - task:
27
  name: Text2text Generation
@@ -66,13 +66,13 @@ model-index:
66
  value: 64.37
67
  ---
68
 
69
- # Model Card of `lmqg/mt5-small-dequad`
70
  This model is fine-tuned version of [google/mt5-small](https://huggingface.co/google/mt5-small) for question generation task on the [lmqg/qg_dequad](https://huggingface.co/datasets/lmqg/qg_dequad) (dataset_name: default) via [`lmqg`](https://github.com/asahi417/lm-question-generation).
71
 
72
 
73
  ### Overview
74
  - **Language model:** [google/mt5-small](https://huggingface.co/google/mt5-small)
75
- - **Language:** en
76
  - **Training data:** [lmqg/qg_dequad](https://huggingface.co/datasets/lmqg/qg_dequad) (default)
77
  - **Online Demo:** [https://autoqg.net/](https://autoqg.net/)
78
  - **Repository:** [https://github.com/asahi417/lm-question-generation](https://github.com/asahi417/lm-question-generation)
@@ -84,10 +84,10 @@ This model is fine-tuned version of [google/mt5-small](https://huggingface.co/go
84
  from lmqg import TransformersQG
85
 
86
  # initialize model
87
- model = TransformersQG(language="en", model="lmqg/mt5-small-dequad")
88
 
89
  # model prediction
90
- questions = model.generate_q(list_context="William Turner was an English painter who specialised in watercolour landscapes", list_answer="William Turner")
91
 
92
  ```
93
 
@@ -95,15 +95,15 @@ questions = model.generate_q(list_context="William Turner was an English painter
95
  ```python
96
  from transformers import pipeline
97
 
98
- pipe = pipeline("text2text-generation", "lmqg/mt5-small-dequad")
99
- output = pipe("<hl> Beyonce <hl> further expanded her acting career, starring as blues singer Etta James in the 2008 musical biopic, Cadillac Records.")
100
 
101
  ```
102
 
103
  ## Evaluation
104
 
105
 
106
- - ***Metric (Question Generation)***: [raw metric file](https://huggingface.co/lmqg/mt5-small-dequad/raw/main/eval/metric.first.sentence.paragraph_answer.question.lmqg_qg_dequad.default.json)
107
 
108
  | | Score | Type | Dataset |
109
  |:-----------|--------:|:--------|:-----------------------------------------------------------------|
@@ -117,7 +117,7 @@ output = pipe("<hl> Beyonce <hl> further expanded her acting career, starring as
117
  | ROUGE_L | 10.08 | default | [lmqg/qg_dequad](https://huggingface.co/datasets/lmqg/qg_dequad) |
118
 
119
 
120
- - ***Metric (Question & Answer Generation)***: QAG metrics are computed with *the gold answer* and generated question on it for this model, as the model cannot provide an answer. [raw metric file](https://huggingface.co/lmqg/mt5-small-dequad/raw/main/eval/metric.first.answer.paragraph.questions_answers.lmqg_qg_dequad.default.json)
121
 
122
  | | Score | Type | Dataset |
123
  |:--------------------------------|--------:|:--------|:-----------------------------------------------------------------|
@@ -149,7 +149,7 @@ The following hyperparameters were used during fine-tuning:
149
  - gradient_accumulation_steps: 4
150
  - label_smoothing: 0.15
151
 
152
- The full configuration can be found at [fine-tuning config file](https://huggingface.co/lmqg/mt5-small-dequad/raw/main/trainer_config.json).
153
 
154
  ## Citation
155
  ```
 
7
  - rouge-l
8
  - bertscore
9
  - moverscore
10
+ language: de
11
  datasets:
12
  - lmqg/qg_dequad
13
  pipeline_tag: text2text-generation
14
  tags:
15
  - question generation
16
  widget:
17
+ - text: "Empfangs- und Sendeantenne sollen in ihrer Polarisation übereinstimmen, andernfalls <hl> wird die Signalübertragung stark gedämpft. <hl>"
18
  example_title: "Question Generation Example 1"
19
+ - text: "das erste weltweit errichtete Hermann Brehmer <hl> 1855 <hl> im niederschlesischen ''Görbersdorf'' (heute Sokołowsko, Polen)."
20
  example_title: "Question Generation Example 2"
21
+ - text: "Er muss Zyperngrieche sein und wird direkt für <hl> fünf Jahre <hl> gewählt (Art. 43 Abs. 1 der Verfassung) und verfügt über weitreichende Exekutivkompetenzen."
22
  example_title: "Question Generation Example 3"
23
  model-index:
24
+ - name: lmqg/mt5-small-dequad-qg
25
  results:
26
  - task:
27
  name: Text2text Generation
 
66
  value: 64.37
67
  ---
68
 
69
+ # Model Card of `lmqg/mt5-small-dequad-qg`
70
  This model is fine-tuned version of [google/mt5-small](https://huggingface.co/google/mt5-small) for question generation task on the [lmqg/qg_dequad](https://huggingface.co/datasets/lmqg/qg_dequad) (dataset_name: default) via [`lmqg`](https://github.com/asahi417/lm-question-generation).
71
 
72
 
73
  ### Overview
74
  - **Language model:** [google/mt5-small](https://huggingface.co/google/mt5-small)
75
+ - **Language:** de
76
  - **Training data:** [lmqg/qg_dequad](https://huggingface.co/datasets/lmqg/qg_dequad) (default)
77
  - **Online Demo:** [https://autoqg.net/](https://autoqg.net/)
78
  - **Repository:** [https://github.com/asahi417/lm-question-generation](https://github.com/asahi417/lm-question-generation)
 
84
  from lmqg import TransformersQG
85
 
86
  # initialize model
87
+ model = TransformersQG(language="de", model="lmqg/mt5-small-dequad-qg")
88
 
89
  # model prediction
90
+ questions = model.generate_q(list_context="das erste weltweit errichtete Hermann Brehmer 1855 im niederschlesischen ''Görbersdorf'' (heute Sokołowsko, Polen).", list_answer="1855")
91
 
92
  ```
93
 
 
95
  ```python
96
  from transformers import pipeline
97
 
98
+ pipe = pipeline("text2text-generation", "lmqg/mt5-small-dequad-qg")
99
+ output = pipe("Empfangs- und Sendeantenne sollen in ihrer Polarisation übereinstimmen, andernfalls <hl> wird die Signalübertragung stark gedämpft. <hl>")
100
 
101
  ```
102
 
103
  ## Evaluation
104
 
105
 
106
+ - ***Metric (Question Generation)***: [raw metric file](https://huggingface.co/lmqg/mt5-small-dequad-qg/raw/main/eval/metric.first.sentence.paragraph_answer.question.lmqg_qg_dequad.default.json)
107
 
108
  | | Score | Type | Dataset |
109
  |:-----------|--------:|:--------|:-----------------------------------------------------------------|
 
117
  | ROUGE_L | 10.08 | default | [lmqg/qg_dequad](https://huggingface.co/datasets/lmqg/qg_dequad) |
118
 
119
 
120
+ - ***Metric (Question & Answer Generation)***: QAG metrics are computed with *the gold answer* and generated question on it for this model, as the model cannot provide an answer. [raw metric file](https://huggingface.co/lmqg/mt5-small-dequad-qg/raw/main/eval/metric.first.answer.paragraph.questions_answers.lmqg_qg_dequad.default.json)
121
 
122
  | | Score | Type | Dataset |
123
  |:--------------------------------|--------:|:--------|:-----------------------------------------------------------------|
 
149
  - gradient_accumulation_steps: 4
150
  - label_smoothing: 0.15
151
 
152
+ The full configuration can be found at [fine-tuning config file](https://huggingface.co/lmqg/mt5-small-dequad-qg/raw/main/trainer_config.json).
153
 
154
  ## Citation
155
  ```