asahi417 commited on
Commit
2e2a3ea
1 Parent(s): d73a8f0

model update

Browse files
Files changed (1) hide show
  1. README.md +53 -0
README.md CHANGED
@@ -79,6 +79,39 @@ model-index:
79
  - name: QAAlignedPrecision-MoverScore (Question & Answer Generation (with Gold Answer)) [Gold Answer]
80
  type: qa_aligned_precision_moverscore_question_answer_generation_with_gold_answer_gold_answer
81
  value: 86.01
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
82
  ---
83
 
84
  # Model Card of `lmqg/mt5-base-koquad-qg`
@@ -152,6 +185,26 @@ output = pipe("1990년 영화 《 <hl> 남부군 <hl> 》에서 단역으로 영
152
  | ROUGE_L | 48.7 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
153
 
154
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
155
 
156
  ## Training hyperparameters
157
 
 
79
  - name: QAAlignedPrecision-MoverScore (Question & Answer Generation (with Gold Answer)) [Gold Answer]
80
  type: qa_aligned_precision_moverscore_question_answer_generation_with_gold_answer_gold_answer
81
  value: 86.01
82
+ - name: BLEU4 (Question & Answer Generation)
83
+ type: bleu4_question_answer_generation
84
+ value: 0.65
85
+ - name: ROUGE-L (Question & Answer Generation)
86
+ type: rouge_l_question_answer_generation
87
+ value: 11.32
88
+ - name: METEOR (Question & Answer Generation)
89
+ type: meteor_question_answer_generation
90
+ value: 17.42
91
+ - name: BERTScore (Question & Answer Generation)
92
+ type: bertscore_question_answer_generation
93
+ value: 61.72
94
+ - name: MoverScore (Question & Answer Generation)
95
+ type: moverscore_question_answer_generation
96
+ value: 61.82
97
+ - name: QAAlignedF1Score-BERTScore (Question & Answer Generation) [Gold Answer]
98
+ type: qa_aligned_f1_score_bertscore_question_answer_generation_gold_answer
99
+ value: 77.26
100
+ - name: QAAlignedRecall-BERTScore (Question & Answer Generation) [Gold Answer]
101
+ type: qa_aligned_recall_bertscore_question_answer_generation_gold_answer
102
+ value: 78.25
103
+ - name: QAAlignedPrecision-BERTScore (Question & Answer Generation) [Gold Answer]
104
+ type: qa_aligned_precision_bertscore_question_answer_generation_gold_answer
105
+ value: 76.37
106
+ - name: QAAlignedF1Score-MoverScore (Question & Answer Generation) [Gold Answer]
107
+ type: qa_aligned_f1_score_moverscore_question_answer_generation_gold_answer
108
+ value: 77.51
109
+ - name: QAAlignedRecall-MoverScore (Question & Answer Generation) [Gold Answer]
110
+ type: qa_aligned_recall_moverscore_question_answer_generation_gold_answer
111
+ value: 78.95
112
+ - name: QAAlignedPrecision-MoverScore (Question & Answer Generation) [Gold Answer]
113
+ type: qa_aligned_precision_moverscore_question_answer_generation_gold_answer
114
+ value: 76.26
115
  ---
116
 
117
  # Model Card of `lmqg/mt5-base-koquad-qg`
 
185
  | ROUGE_L | 48.7 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
186
 
187
 
188
+ - ***Metric (Question & Answer Generation, Pipeline Approach)***: Each question is generated on the answer generated by [`lmqg/mt5-base-koquad-ae`](https://huggingface.co/lmqg/mt5-base-koquad-ae). [raw metric file](https://huggingface.co/lmqg/mt5-base-koquad-qg/raw/main/eval_pipeline/metric.first.answer.paragraph.questions_answers.lmqg_qg_koquad.default.lmqg_mt5-base-koquad-ae.json)
189
+
190
+ | | Score | Type | Dataset |
191
+ |:--------------------------------|--------:|:--------|:-----------------------------------------------------------------|
192
+ | BERTScore | 61.72 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
193
+ | Bleu_1 | 6.83 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
194
+ | Bleu_2 | 3.13 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
195
+ | Bleu_3 | 1.38 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
196
+ | Bleu_4 | 0.65 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
197
+ | METEOR | 17.42 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
198
+ | MoverScore | 61.82 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
199
+ | QAAlignedF1Score (BERTScore) | 77.26 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
200
+ | QAAlignedF1Score (MoverScore) | 77.51 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
201
+ | QAAlignedPrecision (BERTScore) | 76.37 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
202
+ | QAAlignedPrecision (MoverScore) | 76.26 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
203
+ | QAAlignedRecall (BERTScore) | 78.25 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
204
+ | QAAlignedRecall (MoverScore) | 78.95 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
205
+ | ROUGE_L | 11.32 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
206
+
207
+
208
 
209
  ## Training hyperparameters
210