model update
Browse files
README.md
CHANGED
@@ -51,23 +51,38 @@ model-index:
|
|
51 |
- name: MoverScore (Question Generation)
|
52 |
type: moverscore_question_generation
|
53 |
value: 82.54
|
54 |
-
- name:
|
55 |
-
type:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
56 |
value: 80.36
|
57 |
-
- name: QAAlignedRecall-BERTScore (Question & Answer Generation)
|
58 |
-
type:
|
59 |
value: 83.72
|
60 |
-
- name: QAAlignedPrecision-BERTScore (Question & Answer Generation)
|
61 |
-
type:
|
62 |
value: 77.34
|
63 |
-
- name: QAAlignedF1Score-MoverScore (Question & Answer Generation)
|
64 |
-
type:
|
65 |
value: 82.55
|
66 |
-
- name: QAAlignedRecall-MoverScore (Question & Answer Generation)
|
67 |
-
type:
|
68 |
value: 86.69
|
69 |
-
- name: QAAlignedPrecision-MoverScore (Question & Answer Generation)
|
70 |
-
type:
|
71 |
value: 78.93
|
72 |
- name: BLEU4 (Answer Extraction)
|
73 |
type: bleu4_answer_extraction
|
@@ -152,12 +167,20 @@ question = pipe("extract answers: 또한 스피어스는 많은 새로운 여성
|
|
152 |
|
153 |
| | Score | Type | Dataset |
|
154 |
|:--------------------------------|--------:|:--------|:-----------------------------------------------------------------|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
155 |
| QAAlignedF1Score (BERTScore) | 80.36 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
|
156 |
| QAAlignedF1Score (MoverScore) | 82.55 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
|
157 |
| QAAlignedPrecision (BERTScore) | 77.34 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
|
158 |
| QAAlignedPrecision (MoverScore) | 78.93 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
|
159 |
| QAAlignedRecall (BERTScore) | 83.72 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
|
160 |
| QAAlignedRecall (MoverScore) | 86.69 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
|
|
|
161 |
|
162 |
|
163 |
- ***Metric (Answer Extraction)***: [raw metric file](https://huggingface.co/lmqg/mt5-small-koquad-qg-ae/raw/main/eval/metric.first.answer.paragraph_sentence.answer.lmqg_qg_koquad.default.json)
|
|
|
51 |
- name: MoverScore (Question Generation)
|
52 |
type: moverscore_question_generation
|
53 |
value: 82.54
|
54 |
+
- name: BLEU4 (Question & Answer Generation (with Gold Answer))
|
55 |
+
type: bleu4_question_answer_generation_with_gold_answer
|
56 |
+
value: 1.01
|
57 |
+
- name: ROUGE-L (Question & Answer Generation (with Gold Answer))
|
58 |
+
type: rouge_l_question_answer_generation_with_gold_answer
|
59 |
+
value: 13.22
|
60 |
+
- name: METEOR (Question & Answer Generation (with Gold Answer))
|
61 |
+
type: meteor_question_answer_generation_with_gold_answer
|
62 |
+
value: 23.79
|
63 |
+
- name: BERTScore (Question & Answer Generation (with Gold Answer))
|
64 |
+
type: bertscore_question_answer_generation_with_gold_answer
|
65 |
+
value: 68.11
|
66 |
+
- name: MoverScore (Question & Answer Generation (with Gold Answer))
|
67 |
+
type: moverscore_question_answer_generation_with_gold_answer
|
68 |
+
value: 62.67
|
69 |
+
- name: QAAlignedF1Score-BERTScore (Question & Answer Generation (with Gold Answer))
|
70 |
+
type: qa_aligned_f1_score_bertscore_question_answer_generation_with_gold_answer
|
71 |
value: 80.36
|
72 |
+
- name: QAAlignedRecall-BERTScore (Question & Answer Generation (with Gold Answer))
|
73 |
+
type: qa_aligned_recall_bertscore_question_answer_generation_with_gold_answer
|
74 |
value: 83.72
|
75 |
+
- name: QAAlignedPrecision-BERTScore (Question & Answer Generation (with Gold Answer))
|
76 |
+
type: qa_aligned_precision_bertscore_question_answer_generation_with_gold_answer
|
77 |
value: 77.34
|
78 |
+
- name: QAAlignedF1Score-MoverScore (Question & Answer Generation (with Gold Answer))
|
79 |
+
type: qa_aligned_f1_score_moverscore_question_answer_generation_with_gold_answer
|
80 |
value: 82.55
|
81 |
+
- name: QAAlignedRecall-MoverScore (Question & Answer Generation (with Gold Answer))
|
82 |
+
type: qa_aligned_recall_moverscore_question_answer_generation_with_gold_answer
|
83 |
value: 86.69
|
84 |
+
- name: QAAlignedPrecision-MoverScore (Question & Answer Generation (with Gold Answer))
|
85 |
+
type: qa_aligned_precision_moverscore_question_answer_generation_with_gold_answer
|
86 |
value: 78.93
|
87 |
- name: BLEU4 (Answer Extraction)
|
88 |
type: bleu4_answer_extraction
|
|
|
167 |
|
168 |
| | Score | Type | Dataset |
|
169 |
|:--------------------------------|--------:|:--------|:-----------------------------------------------------------------|
|
170 |
+
| BERTScore | 68.11 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
|
171 |
+
| Bleu_1 | 8.34 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
|
172 |
+
| Bleu_2 | 4.4 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
|
173 |
+
| Bleu_3 | 2.1 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
|
174 |
+
| Bleu_4 | 1.01 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
|
175 |
+
| METEOR | 23.79 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
|
176 |
+
| MoverScore | 62.67 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
|
177 |
| QAAlignedF1Score (BERTScore) | 80.36 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
|
178 |
| QAAlignedF1Score (MoverScore) | 82.55 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
|
179 |
| QAAlignedPrecision (BERTScore) | 77.34 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
|
180 |
| QAAlignedPrecision (MoverScore) | 78.93 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
|
181 |
| QAAlignedRecall (BERTScore) | 83.72 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
|
182 |
| QAAlignedRecall (MoverScore) | 86.69 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
|
183 |
+
| ROUGE_L | 13.22 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
|
184 |
|
185 |
|
186 |
- ***Metric (Answer Extraction)***: [raw metric file](https://huggingface.co/lmqg/mt5-small-koquad-qg-ae/raw/main/eval/metric.first.answer.paragraph_sentence.answer.lmqg_qg_koquad.default.json)
|