init
Browse files- eval/metric.first.answer.paragraph.questions_answers.lmqg_qg_jaquad.default.json +1 -0
- eval/metric.first.answer.paragraph_sentence.answer.lmqg_qg_jaquad.default.json +1 -1
- eval/metric.first.sentence.paragraph_answer.question.lmqg_qg_jaquad.default.json +1 -1
- eval/samples.validation.hyp.paragraph.questions_answers.lmqg_qg_jaquad.default.txt +0 -0
eval/metric.first.answer.paragraph.questions_answers.lmqg_qg_jaquad.default.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"test": {"QAAlignedF1Score (BERTScore)": 0.8035098723803743, "QAAlignedRecall (BERTScore)": 0.8378749715759669, "QAAlignedPrecision (BERTScore)": 0.7728178741807085, "QAAlignedF1Score (MoverScore)": 0.5623463256430944, "QAAlignedRecall (MoverScore)": 0.5881454405770354, "QAAlignedPrecision (MoverScore)": 0.5401739069684022}, "validation": {"QAAlignedF1Score (BERTScore)": 0.813409552842049, "QAAlignedRecall (BERTScore)": 0.8308434153273754, "QAAlignedPrecision (BERTScore)": 0.7975233646341368, "QAAlignedF1Score (MoverScore)": 0.5698790455257939, "QAAlignedRecall (MoverScore)": 0.5819119554714534, "QAAlignedPrecision (MoverScore)": 0.5593087503926527}}
|
eval/metric.first.answer.paragraph_sentence.answer.lmqg_qg_jaquad.default.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"validation": {"Bleu_1": 0.
|
|
|
1 |
+
{"validation": {"Bleu_1": 0.3605256831476592, "Bleu_2": 0.3339294539634141, "Bleu_3": 0.30661656260169173, "Bleu_4": 0.2835733236966017, "METEOR": 0.27782717743915303, "ROUGE_L": 0.3850244880094073, "BERTScore": 0.7882174059472492, "MoverScore": 0.6654066499366282, "AnswerF1Score": 31.454683929931456, "AnswerExactMatch": 31.454683929931456}, "test": {"Bleu_1": 0.34665062174084665, "Bleu_2": 0.31786047211885404, "Bleu_3": 0.29280193680100863, "Bleu_4": 0.27348837838775075, "METEOR": 0.2618209929989591, "ROUGE_L": 0.3680624036980424, "BERTScore": 0.7816285902502331, "MoverScore": 0.6584344462398951, "AnswerF1Score": 30.21071337903021, "AnswerExactMatch": 30.21071337903021}}
|
eval/metric.first.sentence.paragraph_answer.question.lmqg_qg_jaquad.default.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"validation": {"Bleu_1": 0.
|
|
|
1 |
+
{"validation": {"Bleu_1": 0.5507062279336253, "Bleu_2": 0.42232371591766943, "Bleu_3": 0.3398500478384735, "Bleu_4": 0.28093163829109097, "METEOR": 0.2741246139352359, "ROUGE_L": 0.49021077431250365, "BERTScore": 0.8024911547532048, "MoverScore": 0.5803509731504769}, "test": {"Bleu_1": 0.5585811236269425, "Bleu_2": 0.437494660650837, "Bleu_3": 0.35877137505222195, "Bleu_4": 0.3011775332002, "METEOR": 0.2882634531494165, "ROUGE_L": 0.5080335061386184, "BERTScore": 0.8100855520616319, "MoverScore": 0.5884824768439435}}
|
eval/samples.validation.hyp.paragraph.questions_answers.lmqg_qg_jaquad.default.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|