Skip to content

(demo) FactCC & Frank & QAGS results on pairwise MNLI model metrics (sample results using df[:10]) #23

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
lihebi wants to merge 1 commit into
base: turx
Choose a base branch
from
Open

(demo) FactCC & Frank & QAGS results on pairwise MNLI model metrics (sample results using df[:10]) #23

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
398 changes: 398 additions & 0 deletions results/sample/factcc_summary.json
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,398 @@
{
"('pearsonr', 'human', 'new', 'bertscore-sentence-cos-mpnet', 'P')": {
"0": 0.5815545229,
"average": 0.5815545229
},
"('pearsonr', 'human', 'new', 'bertscore-sentence-cos-mpnet', 'R')": {
"0": -0.0600319914,
"average": -0.0600319914
},
"('pearsonr', 'human', 'new', 'bertscore-sentence-cos-mpnet', 'F')": {
"0": 0.0277402752,
"average": 0.0277402752
},
"('pearsonr', 'human', 'new', 'bertscore-sentence-cos-roberta', 'P')": {
"0": 0.7169653488,
"average": 0.7169653488
},
"('pearsonr', 'human', 'new', 'bertscore-sentence-cos-roberta', 'R')": {
"0": -0.0528466412,
"average": -0.0528466412
},
"('pearsonr', 'human', 'new', 'bertscore-sentence-cos-roberta', 'F')": {
"0": 0.0967947792,
"average": 0.0967947792
},
"('pearsonr', 'human', 'new', 'bertscore-sentence-mnli-roberta-not_neutral', 'P')": {
"0": 0.3208156661,
"average": 0.3208156661
},
"('pearsonr', 'human', 'new', 'bertscore-sentence-mnli-roberta-not_neutral', 'R')": {
"0": -0.5156587126,
"average": -0.5156587126
},
"('pearsonr', 'human', 'new', 'bertscore-sentence-mnli-roberta-not_neutral', 'F')": {
"0": -0.470599931,
"average": -0.470599931
},
"('pearsonr', 'human', 'new', 'bertscore-sentence-mnli-roberta-entail_only', 'P')": {
"0": 0.6595192702,
"average": 0.6595192702
},
"('pearsonr', 'human', 'new', 'bertscore-sentence-mnli-roberta-entail_only', 'R')": {
"0": 0.0757447464,
"average": 0.0757447464
},
"('pearsonr', 'human', 'new', 'bertscore-sentence-mnli-roberta-entail_only', 'F')": {
"0": 0.1639806392,
"average": 0.1639806392
},
"('pearsonr', 'human', 'new', 'bertscore-sentence-mnli-roberta-entail_contradict', 'P')": {
"0": 0.6717421438,
"average": 0.6717421438
},
"('pearsonr', 'human', 'new', 'bertscore-sentence-mnli-roberta-entail_contradict', 'R')": {
"0": 0.3588681114,
"average": 0.3588681114
},
"('pearsonr', 'human', 'new', 'bertscore-sentence-mnli-roberta-entail_contradict', 'F')": {
"0": -0.2877454493,
"average": -0.2877454493
},
"('pearsonr', 'human', 'new', 'bertscore-sentence-mnli-bart-not_neutral', 'P')": {
"0": -0.2861778665,
"average": -0.2861778665
},
"('pearsonr', 'human', 'new', 'bertscore-sentence-mnli-bart-not_neutral', 'R')": {
"0": -0.6681691136,
"average": -0.6681691136
},
"('pearsonr', 'human', 'new', 'bertscore-sentence-mnli-bart-not_neutral', 'F')": {
"0": -0.6737821313,
"average": -0.6737821313
},
"('pearsonr', 'human', 'new', 'bertscore-sentence-mnli-bart-entail_only', 'P')": {
"0": 0.6666898215,
"average": 0.6666898215
},
"('pearsonr', 'human', 'new', 'bertscore-sentence-mnli-bart-entail_only', 'R')": {
"0": 0.3804341873,
"average": 0.3804341873
},
"('pearsonr', 'human', 'new', 'bertscore-sentence-mnli-bart-entail_only', 'F')": {
"0": 0.4086553414,
"average": 0.4086553414
},
"('pearsonr', 'human', 'new', 'bertscore-sentence-mnli-bart-entail_contradict', 'P')": {
"0": 0.6806158226,
"average": 0.6806158226
},
"('pearsonr', 'human', 'new', 'bertscore-sentence-mnli-bart-entail_contradict', 'R')": {
"0": 0.6709422745,
"average": 0.6709422745
},
"('pearsonr', 'human', 'new', 'bertscore-sentence-mnli-bart-entail_contradict', 'F')": {
"0": 0.3458599955,
"average": 0.3458599955
},
"('pearsonr', 'human', 'new', 'bertscore-sentence-mnli-deberta-not_neutral', 'P')": {
"0": 0.2855930523,
"average": 0.2855930523
},
"('pearsonr', 'human', 'new', 'bertscore-sentence-mnli-deberta-not_neutral', 'R')": {
"0": -0.5795375818,
"average": -0.5795375818
},
"('pearsonr', 'human', 'new', 'bertscore-sentence-mnli-deberta-not_neutral', 'F')": {
"0": -0.5553977183,
"average": -0.5553977183
},
"('pearsonr', 'human', 'new', 'bertscore-sentence-mnli-deberta-entail_only', 'P')": {
"0": 0.5867073853,
"average": 0.5867073853
},
"('pearsonr', 'human', 'new', 'bertscore-sentence-mnli-deberta-entail_only', 'R')": {
"0": 0.262299699,
"average": 0.262299699
},
"('pearsonr', 'human', 'new', 'bertscore-sentence-mnli-deberta-entail_only', 'F')": {
"0": 0.2984548025,
"average": 0.2984548025
},
"('pearsonr', 'human', 'new', 'bertscore-sentence-mnli-deberta-entail_contradict', 'P')": {
"0": 0.591284334,
"average": 0.591284334
},
"('pearsonr', 'human', 'new', 'bertscore-sentence-mnli-deberta-entail_contradict', 'R')": {
"0": 0.5146585507,
"average": 0.5146585507
},
"('pearsonr', 'human', 'new', 'bertscore-sentence-mnli-deberta-entail_contradict', 'F')": {
"0": -0.2794090753,
"average": -0.2794090753
},
"('kendalltau', 'human', 'new', 'bertscore-sentence-cos-mpnet', 'P')": {
"0": 0.4868644956,
"average": 0.4868644956
},
"('kendalltau', 'human', 'new', 'bertscore-sentence-cos-mpnet', 'R')": {
"0": -0.1217161239,
"average": -0.1217161239
},
"('kendalltau', 'human', 'new', 'bertscore-sentence-cos-mpnet', 'F')": {
"0": 0.0,
"average": 0.0
},
"('kendalltau', 'human', 'new', 'bertscore-sentence-cos-roberta', 'P')": {
"0": 0.7302967433,
"average": 0.7302967433
},
"('kendalltau', 'human', 'new', 'bertscore-sentence-cos-roberta', 'R')": {
"0": -0.0608580619,
"average": -0.0608580619
},
"('kendalltau', 'human', 'new', 'bertscore-sentence-cos-roberta', 'F')": {
"0": 0.2434322478,
"average": 0.2434322478
},
"('kendalltau', 'human', 'new', 'bertscore-sentence-mnli-roberta-not_neutral', 'P')": {
"0": -0.1217161239,
"average": -0.1217161239
},
"('kendalltau', 'human', 'new', 'bertscore-sentence-mnli-roberta-not_neutral', 'R')": {
"0": -0.3042903097,
"average": -0.3042903097
},
"('kendalltau', 'human', 'new', 'bertscore-sentence-mnli-roberta-not_neutral', 'F')": {
"0": -0.3042903097,
"average": -0.3042903097
},
"('kendalltau', 'human', 'new', 'bertscore-sentence-mnli-roberta-entail_only', 'P')": {
"0": 0.4868644956,
"average": 0.4868644956
},
"('kendalltau', 'human', 'new', 'bertscore-sentence-mnli-roberta-entail_only', 'R')": {
"0": 0.1825741858,
"average": 0.1825741858
},
"('kendalltau', 'human', 'new', 'bertscore-sentence-mnli-roberta-entail_only', 'F')": {
"0": 0.1825741858,
"average": 0.1825741858
},
"('kendalltau', 'human', 'new', 'bertscore-sentence-mnli-roberta-entail_contradict', 'P')": {
"0": 0.5477225575,
"average": 0.5477225575
},
"('kendalltau', 'human', 'new', 'bertscore-sentence-mnli-roberta-entail_contradict', 'R')": {
"0": 0.2434322478,
"average": 0.2434322478
},
"('kendalltau', 'human', 'new', 'bertscore-sentence-mnli-roberta-entail_contradict', 'F')": {
"0": -0.3042903097,
"average": -0.3042903097
},
"('kendalltau', 'human', 'new', 'bertscore-sentence-mnli-bart-not_neutral', 'P')": {
"0": -0.4868644956,
"average": -0.4868644956
},
"('kendalltau', 'human', 'new', 'bertscore-sentence-mnli-bart-not_neutral', 'R')": {
"0": -0.5477225575,
"average": -0.5477225575
},
"('kendalltau', 'human', 'new', 'bertscore-sentence-mnli-bart-not_neutral', 'F')": {
"0": -0.5477225575,
"average": -0.5477225575
},
"('kendalltau', 'human', 'new', 'bertscore-sentence-mnli-bart-entail_only', 'P')": {
"0": 0.6085806195,
"average": 0.6085806195
},
"('kendalltau', 'human', 'new', 'bertscore-sentence-mnli-bart-entail_only', 'R')": {
"0": 0.4260064336,
"average": 0.4260064336
},
"('kendalltau', 'human', 'new', 'bertscore-sentence-mnli-bart-entail_only', 'F')": {
"0": 0.4868644956,
"average": 0.4868644956
},
"('kendalltau', 'human', 'new', 'bertscore-sentence-mnli-bart-entail_contradict', 'P')": {
"0": 0.6085806195,
"average": 0.6085806195
},
"('kendalltau', 'human', 'new', 'bertscore-sentence-mnli-bart-entail_contradict', 'R')": {
"0": 0.5477225575,
"average": 0.5477225575
},
"('kendalltau', 'human', 'new', 'bertscore-sentence-mnli-bart-entail_contradict', 'F')": {
"0": 0.1825741858,
"average": 0.1825741858
},
"('kendalltau', 'human', 'new', 'bertscore-sentence-mnli-deberta-not_neutral', 'P')": {
"0": -0.3651483717,
"average": -0.3651483717
},
"('kendalltau', 'human', 'new', 'bertscore-sentence-mnli-deberta-not_neutral', 'R')": {
"0": -0.3651483717,
"average": -0.3651483717
},
"('kendalltau', 'human', 'new', 'bertscore-sentence-mnli-deberta-not_neutral', 'F')": {
"0": -0.3042903097,
"average": -0.3042903097
},
"('kendalltau', 'human', 'new', 'bertscore-sentence-mnli-deberta-entail_only', 'P')": {
"0": 0.5477225575,
"average": 0.5477225575
},
"('kendalltau', 'human', 'new', 'bertscore-sentence-mnli-deberta-entail_only', 'R')": {
"0": 0.3042903097,
"average": 0.3042903097
},
"('kendalltau', 'human', 'new', 'bertscore-sentence-mnli-deberta-entail_only', 'F')": {
"0": 0.3042903097,
"average": 0.3042903097
},
"('kendalltau', 'human', 'new', 'bertscore-sentence-mnli-deberta-entail_contradict', 'P')": {
"0": 0.5477225575,
"average": 0.5477225575
},
"('kendalltau', 'human', 'new', 'bertscore-sentence-mnli-deberta-entail_contradict', 'R')": {
"0": 0.3651483717,
"average": 0.3651483717
},
"('kendalltau', 'human', 'new', 'bertscore-sentence-mnli-deberta-entail_contradict', 'F')": {
"0": -0.0608580619,
"average": -0.0608580619
},
"('spearmanr', 'human', 'new', 'bertscore-sentence-cos-mpnet', 'P')": {
"0": 0.5685352436,
"average": 0.5685352436
},
"('spearmanr', 'human', 'new', 'bertscore-sentence-cos-mpnet', 'R')": {
"0": -0.1421338109,
"average": -0.1421338109
},
"('spearmanr', 'human', 'new', 'bertscore-sentence-cos-mpnet', 'F')": {
"0": 0.0,
"average": 0.0
},
"('spearmanr', 'human', 'new', 'bertscore-sentence-cos-roberta', 'P')": {
"0": 0.8528028654,
"average": 0.8528028654
},
"('spearmanr', 'human', 'new', 'bertscore-sentence-cos-roberta', 'R')": {
"0": -0.0710669055,
"average": -0.0710669055
},
"('spearmanr', 'human', 'new', 'bertscore-sentence-cos-roberta', 'F')": {
"0": 0.2842676218,
"average": 0.2842676218
},
"('spearmanr', 'human', 'new', 'bertscore-sentence-mnli-roberta-not_neutral', 'P')": {
"0": -0.1421338109,
"average": -0.1421338109
},
"('spearmanr', 'human', 'new', 'bertscore-sentence-mnli-roberta-not_neutral', 'R')": {
"0": -0.3553345273,
"average": -0.3553345273
},
"('spearmanr', 'human', 'new', 'bertscore-sentence-mnli-roberta-not_neutral', 'F')": {
"0": -0.3553345273,
"average": -0.3553345273
},
"('spearmanr', 'human', 'new', 'bertscore-sentence-mnli-roberta-entail_only', 'P')": {
"0": 0.5685352436,
"average": 0.5685352436
},
"('spearmanr', 'human', 'new', 'bertscore-sentence-mnli-roberta-entail_only', 'R')": {
"0": 0.2132007164,
"average": 0.2132007164
},
"('spearmanr', 'human', 'new', 'bertscore-sentence-mnli-roberta-entail_only', 'F')": {
"0": 0.2132007164,
"average": 0.2132007164
},
"('spearmanr', 'human', 'new', 'bertscore-sentence-mnli-roberta-entail_contradict', 'P')": {
"0": 0.6396021491,
"average": 0.6396021491
},
"('spearmanr', 'human', 'new', 'bertscore-sentence-mnli-roberta-entail_contradict', 'R')": {
"0": 0.2842676218,
"average": 0.2842676218
},
"('spearmanr', 'human', 'new', 'bertscore-sentence-mnli-roberta-entail_contradict', 'F')": {
"0": -0.3553345273,
"average": -0.3553345273
},
"('spearmanr', 'human', 'new', 'bertscore-sentence-mnli-bart-not_neutral', 'P')": {
"0": -0.5685352436,
"average": -0.5685352436
},
"('spearmanr', 'human', 'new', 'bertscore-sentence-mnli-bart-not_neutral', 'R')": {
"0": -0.6396021491,
"average": -0.6396021491
},
"('spearmanr', 'human', 'new', 'bertscore-sentence-mnli-bart-not_neutral', 'F')": {
"0": -0.6396021491,
"average": -0.6396021491
},
"('spearmanr', 'human', 'new', 'bertscore-sentence-mnli-bart-entail_only', 'P')": {
"0": 0.7106690545,
"average": 0.7106690545
},
"('spearmanr', 'human', 'new', 'bertscore-sentence-mnli-bart-entail_only', 'R')": {
"0": 0.4974683382,
"average": 0.4974683382
},
"('spearmanr', 'human', 'new', 'bertscore-sentence-mnli-bart-entail_only', 'F')": {
"0": 0.5685352436,
"average": 0.5685352436
},
"('spearmanr', 'human', 'new', 'bertscore-sentence-mnli-bart-entail_contradict', 'P')": {
"0": 0.7106690545,
"average": 0.7106690545
},
"('spearmanr', 'human', 'new', 'bertscore-sentence-mnli-bart-entail_contradict', 'R')": {
"0": 0.6396021491,
"average": 0.6396021491
},
"('spearmanr', 'human', 'new', 'bertscore-sentence-mnli-bart-entail_contradict', 'F')": {
"0": 0.2132007164,
"average": 0.2132007164
},
"('spearmanr', 'human', 'new', 'bertscore-sentence-mnli-deberta-not_neutral', 'P')": {
"0": -0.4264014327,
"average": -0.4264014327
},
"('spearmanr', 'human', 'new', 'bertscore-sentence-mnli-deberta-not_neutral', 'R')": {
"0": -0.4264014327,
"average": -0.4264014327
},
"('spearmanr', 'human', 'new', 'bertscore-sentence-mnli-deberta-not_neutral', 'F')": {
"0": -0.3553345273,
"average": -0.3553345273
},
"('spearmanr', 'human', 'new', 'bertscore-sentence-mnli-deberta-entail_only', 'P')": {
"0": 0.6396021491,
"average": 0.6396021491
},
"('spearmanr', 'human', 'new', 'bertscore-sentence-mnli-deberta-entail_only', 'R')": {
"0": 0.3553345273,
"average": 0.3553345273
},
"('spearmanr', 'human', 'new', 'bertscore-sentence-mnli-deberta-entail_only', 'F')": {
"0": 0.3553345273,
"average": 0.3553345273
},
"('spearmanr', 'human', 'new', 'bertscore-sentence-mnli-deberta-entail_contradict', 'P')": {
"0": 0.6396021491,
"average": 0.6396021491
},
"('spearmanr', 'human', 'new', 'bertscore-sentence-mnli-deberta-entail_contradict', 'R')": {
"0": 0.4264014327,
"average": 0.4264014327
},
"('spearmanr', 'human', 'new', 'bertscore-sentence-mnli-deberta-entail_contradict', 'F')": {
"0": -0.0710669055,
"average": -0.0710669055
}
}
Loading