asahi417 commited on
Commit
8f20073
1 Parent(s): 62c914d
eval/metric.first.answer.paragraph.questions_answers.lmqg_qg_dequad.default.json CHANGED
@@ -1 +1 @@
1
- {"test": {"QAAlignedF1Score (BERTScore)": 0.0, "QAAlignedRecall (BERTScore)": 0.0, "QAAlignedPrecision (BERTScore)": 0.0, "QAAlignedF1Score (MoverScore)": 0.0, "QAAlignedRecall (MoverScore)": 0.0, "QAAlignedPrecision (MoverScore)": 0.0, "Bleu_1": 0.0, "Bleu_2": 0.0, "Bleu_3": 0.0, "Bleu_4": 0.0, "METEOR": 0.0, "ROUGE_L": 0.006427099173143384, "BERTScore": 0.0, "MoverScore": 0.4288402864228588}, "validation": {"QAAlignedF1Score (BERTScore)": 0.0, "QAAlignedRecall (BERTScore)": 0.0, "QAAlignedPrecision (BERTScore)": 0.0, "QAAlignedF1Score (MoverScore)": 0.0, "QAAlignedRecall (MoverScore)": 0.0, "QAAlignedPrecision (MoverScore)": 0.0, "Bleu_1": 0.0, "Bleu_2": 0.0, "Bleu_3": 0.0, "Bleu_4": 0.0, "METEOR": 0.0, "ROUGE_L": 0.011010381923259495, "BERTScore": 0.0, "MoverScore": 0.4333211602082045}}
 
1
+ {"test": {"QAAlignedF1Score (BERTScore)": 0.795605568009872, "QAAlignedRecall (BERTScore)": 0.8075998148232812, "QAAlignedPrecision (BERTScore)": 0.7846723900916923, "QAAlignedF1Score (MoverScore)": 0.5376816845488548, "QAAlignedRecall (MoverScore)": 0.5405917740395045, "QAAlignedPrecision (MoverScore)": 0.5352697941570417, "Bleu_1": 0.15683947137863452, "Bleu_2": 0.07635587146515127, "Bleu_3": 0.025120524978800494, "Bleu_4": 0.010260866052853968, "METEOR": 0.2030218544810605, "ROUGE_L": 0.17180510675539695, "BERTScore": 0.7254355045562052, "MoverScore": 0.5271236825073656}, "validation": {"QAAlignedF1Score (BERTScore)": 0.7967546168259902, "QAAlignedRecall (BERTScore)": 0.8270277058905917, "QAAlignedPrecision (BERTScore)": 0.7694226515000434, "QAAlignedF1Score (MoverScore)": 0.5360733712204881, "QAAlignedRecall (MoverScore)": 0.5502707318749572, "QAAlignedPrecision (MoverScore)": 0.5233552340239792, "Bleu_1": 0.07875842839293742, "Bleu_2": 0.031605160165092544, "Bleu_3": 0.009243073915583868, "Bleu_4": 0.0035192885317932242, "METEOR": 0.1668857916854053, "ROUGE_L": 0.11396162357596337, "BERTScore": 0.6715921184154061, "MoverScore": 0.5099549477437207}}
eval/metric.first.answer.paragraph_sentence.answer.lmqg_qg_dequad.default.json CHANGED
@@ -1 +1 @@
1
- {"validation": {"Bleu_1": 0.2512808570097713, "Bleu_2": 0.17200666979618856, "Bleu_3": 0.11601037389714632, "Bleu_4": 0.07833093186130648, "METEOR": 0.27241316698312057, "ROUGE_L": 0.2442186146594222, "BERTScore": 0.7912570112089063, "MoverScore": 0.6111877039173896, "AnswerF1Score": 47.97914329982987, "AnswerExactMatch": 13.203266787658801}, "test": {"Bleu_1": 0.19504937685970955, "Bleu_2": 0.13013436077051674, "Bleu_3": 0.08631932690075304, "Bleu_4": 0.056732079759815104, "METEOR": 0.2266378098231599, "ROUGE_L": 0.18189892033201369, "BERTScore": 0.7504787875336009, "MoverScore": 0.5779213304061341, "AnswerF1Score": 38.08332842395432, "AnswerExactMatch": 9.936479128856623}}
 
1
+ {"validation": {"Bleu_1": 0.2512808570097713, "Bleu_2": 0.17200666979618856, "Bleu_3": 0.11601037389714632, "Bleu_4": 0.07833093186130648, "METEOR": 0.27241316698312057, "ROUGE_L": 0.2442186146594222, "BERTScore": 0.7912570143730367, "MoverScore": 0.6111882206411756, "AnswerF1Score": 47.97914329982987, "AnswerExactMatch": 13.203266787658801}, "test": {"Bleu_1": 0.19504937685970955, "Bleu_2": 0.13013436077051674, "Bleu_3": 0.08631932690075304, "Bleu_4": 0.056732079759815104, "METEOR": 0.2266378098231599, "ROUGE_L": 0.18189892033201369, "BERTScore": 0.7504787909952136, "MoverScore": 0.5779229264497275, "AnswerF1Score": 38.08332842395432, "AnswerExactMatch": 9.936479128856623}}
eval/metric.first.sentence.paragraph_answer.question.lmqg_qg_dequad.default.json CHANGED
@@ -1 +1 @@
1
- {"validation": {"Bleu_1": 0.12215287779377382, "Bleu_2": 0.052578262597836246, "Bleu_3": 0.024112443205915976, "Bleu_4": 0.008702732064885895, "METEOR": 0.13773817064587052, "ROUGE_L": 0.11946680276213367, "BERTScore": 0.8194934565045169, "MoverScore": 0.5624235228037266}, "test": {"Bleu_1": 0.1043083900226701, "Bleu_2": 0.04316105757713112, "Bleu_3": 0.018803586872870995, "Bleu_4": 0.00756511319481653, "METEOR": 0.12323987544014788, "ROUGE_L": 0.10459936850793287, "BERTScore": 0.804436454869849, "MoverScore": 0.5509798112903916}}
 
1
+ {"validation": {"Bleu_1": 0.12215287779377382, "Bleu_2": 0.052578262597836246, "Bleu_3": 0.024112443205915976, "Bleu_4": 0.008702732064885895, "METEOR": 0.13773817064587052, "ROUGE_L": 0.11946680276213367, "BERTScore": 0.8194934573532738, "MoverScore": 0.5624235643235452}, "test": {"Bleu_1": 0.1043083900226701, "Bleu_2": 0.04316105757713112, "Bleu_3": 0.018803586872870995, "Bleu_4": 0.00756511319481653, "METEOR": 0.12323987544014788, "ROUGE_L": 0.10459936850793287, "BERTScore": 0.8044364544754894, "MoverScore": 0.5509801046228046}}
eval/samples.test.hyp.paragraph.questions_answers.lmqg_qg_dequad.default.txt CHANGED
The diff for this file is too large to render. See raw diff
 
eval/samples.validation.hyp.paragraph.questions_answers.lmqg_qg_dequad.default.txt CHANGED
The diff for this file is too large to render. See raw diff