Skip to content
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

Jump to bottom

(WIP) Factcc full results #24

Open
wants to merge 5 commits into
base: turx
Choose a base branch
from
Open

(WIP) Factcc full results #24

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
f3e3614
add qags full results
lihebi Jan 14, 2023
b884b64
add frank summary level
lihebi Jan 14, 2023
dadd26a
add qags-xsum results
lihebi Jan 14, 2023
427b85b
add frank-xsum results
lihebi Jan 14, 2023
4a670e2
add factcc results
lihebi Jan 14, 2023
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/factcc-id0_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": 0.0464916151,
"average": 0.0464916151
},
"('pearsonr', 'human', 'new', 'bertscore-sentence-cos-mpnet', 'R')": {
"0": -0.0638095802,
"average": -0.0638095802
},
"('pearsonr', 'human', 'new', 'bertscore-sentence-cos-mpnet', 'F')": {
"0": -0.0494382556,
"average": -0.0494382556
},
"('pearsonr', 'human', 'new', 'bertscore-sentence-cos-roberta', 'P')": {
"0": 0.0545306925,
"average": 0.0545306925
},
"('pearsonr', 'human', 'new', 'bertscore-sentence-cos-roberta', 'R')": {
"0": -0.0588050578,
"average": -0.0588050578
},
"('pearsonr', 'human', 'new', 'bertscore-sentence-cos-roberta', 'F')": {
"0": -0.0410990233,
"average": -0.0410990233
},
"('pearsonr', 'human', 'new', 'bertscore-sentence-mnli-roberta-not_neutral', 'P')": {
"0": 0.0763387457,
"average": 0.0763387457
},
"('pearsonr', 'human', 'new', 'bertscore-sentence-mnli-roberta-not_neutral', 'R')": {
"0": -0.1391934072,
"average": -0.1391934072
},
"('pearsonr', 'human', 'new', 'bertscore-sentence-mnli-roberta-not_neutral', 'F')": {
"0": -0.1373480309,
"average": -0.1373480309
},
"('pearsonr', 'human', 'new', 'bertscore-sentence-mnli-roberta-entail_only', 'P')": {
"0": 0.5545457454,
"average": 0.5545457454
},
"('pearsonr', 'human', 'new', 'bertscore-sentence-mnli-roberta-entail_only', 'R')": {
"0": 0.2708304936,
"average": 0.2708304936
},
"('pearsonr', 'human', 'new', 'bertscore-sentence-mnli-roberta-entail_only', 'F')": {
"0": 0.3323295943,
"average": 0.3323295943
},
"('pearsonr', 'human', 'new', 'bertscore-sentence-mnli-roberta-entail_contradict', 'P')": {
"0": 0.5550462428,
"average": 0.5550462428
},
"('pearsonr', 'human', 'new', 'bertscore-sentence-mnli-roberta-entail_contradict', 'R')": {
"0": 0.3288420023,
"average": 0.3288420023
},
"('pearsonr', 'human', 'new', 'bertscore-sentence-mnli-roberta-entail_contradict', 'F')": {
"0": -0.0216828609,
"average": -0.0216828609
},
"('pearsonr', 'human', 'new', 'bertscore-sentence-mnli-bart-not_neutral', 'P')": {
"0": 0.0991536999,
"average": 0.0991536999
},
"('pearsonr', 'human', 'new', 'bertscore-sentence-mnli-bart-not_neutral', 'R')": {
"0": -0.088461976,
"average": -0.088461976
},
"('pearsonr', 'human', 'new', 'bertscore-sentence-mnli-bart-not_neutral', 'F')": {
"0": -0.0879244745,
"average": -0.0879244745
},
"('pearsonr', 'human', 'new', 'bertscore-sentence-mnli-bart-entail_only', 'P')": {
"0": 0.6072476088,
"average": 0.6072476088
},
"('pearsonr', 'human', 'new', 'bertscore-sentence-mnli-bart-entail_only', 'R')": {
"0": 0.3342730657,
"average": 0.3342730657
},
"('pearsonr', 'human', 'new', 'bertscore-sentence-mnli-bart-entail_only', 'F')": {
"0": 0.3908544479,
"average": 0.3908544479
},
"('pearsonr', 'human', 'new', 'bertscore-sentence-mnli-bart-entail_contradict', 'P')": {
"0": 0.5912649355,
"average": 0.5912649355
},
"('pearsonr', 'human', 'new', 'bertscore-sentence-mnli-bart-entail_contradict', 'R')": {
"0": 0.2491778988,
"average": 0.2491778988
},
"('pearsonr', 'human', 'new', 'bertscore-sentence-mnli-bart-entail_contradict', 'F')": {
"0": -0.0338613947,
"average": -0.0338613947
},
"('pearsonr', 'human', 'new', 'bertscore-sentence-mnli-deberta-not_neutral', 'P')": {
"0": 0.2809733169,
"average": 0.2809733169
},
"('pearsonr', 'human', 'new', 'bertscore-sentence-mnli-deberta-not_neutral', 'R')": {
"0": -0.0948472374,
"average": -0.0948472374
},
"('pearsonr', 'human', 'new', 'bertscore-sentence-mnli-deberta-not_neutral', 'F')": {
"0": -0.0845110103,
"average": -0.0845110103
},
"('pearsonr', 'human', 'new', 'bertscore-sentence-mnli-deberta-entail_only', 'P')": {
"0": 0.6277175716,
"average": 0.6277175716
},
"('pearsonr', 'human', 'new', 'bertscore-sentence-mnli-deberta-entail_only', 'R')": {
"0": 0.2991939824,
"average": 0.2991939824
},
"('pearsonr', 'human', 'new', 'bertscore-sentence-mnli-deberta-entail_only', 'F')": {
"0": 0.3628689547,
"average": 0.3628689547
},
"('pearsonr', 'human', 'new', 'bertscore-sentence-mnli-deberta-entail_contradict', 'P')": {
"0": 0.6331495255,
"average": 0.6331495255
},
"('pearsonr', 'human', 'new', 'bertscore-sentence-mnli-deberta-entail_contradict', 'R')": {
"0": 0.2960637702,
"average": 0.2960637702
},
"('pearsonr', 'human', 'new', 'bertscore-sentence-mnli-deberta-entail_contradict', 'F')": {
"0": -0.0126112964,
"average": -0.0126112964
},
"('kendalltau', 'human', 'new', 'bertscore-sentence-cos-mpnet', 'P')": {
"0": 0.1342348608,
"average": 0.1342348608
},
"('kendalltau', 'human', 'new', 'bertscore-sentence-cos-mpnet', 'R')": {
"0": -0.0439182742,
"average": -0.0439182742
},
"('kendalltau', 'human', 'new', 'bertscore-sentence-cos-mpnet', 'F')": {
"0": -0.019484924,
"average": -0.019484924
},
"('kendalltau', 'human', 'new', 'bertscore-sentence-cos-roberta', 'P')": {
"0": 0.1402615512,
"average": 0.1402615512
},
"('kendalltau', 'human', 'new', 'bertscore-sentence-cos-roberta', 'R')": {
"0": -0.037080971,
"average": -0.037080971
},
"('kendalltau', 'human', 'new', 'bertscore-sentence-cos-roberta', 'F')": {
"0": -0.0084705157,
"average": -0.0084705157
},
"('kendalltau', 'human', 'new', 'bertscore-sentence-mnli-roberta-not_neutral', 'P')": {
"0": 0.017239943,
"average": 0.017239943
},
"('kendalltau', 'human', 'new', 'bertscore-sentence-mnli-roberta-not_neutral', 'R')": {
"0": -0.0992111907,
"average": -0.0992111907
},
"('kendalltau', 'human', 'new', 'bertscore-sentence-mnli-roberta-not_neutral', 'F')": {
"0": -0.1012174034,
"average": -0.1012174034
},
"('kendalltau', 'human', 'new', 'bertscore-sentence-mnli-roberta-entail_only', 'P')": {
"0": 0.461573943,
"average": 0.461573943
},
"('kendalltau', 'human', 'new', 'bertscore-sentence-mnli-roberta-entail_only', 'R')": {
"0": 0.2870596826,
"average": 0.2870596826
},
"('kendalltau', 'human', 'new', 'bertscore-sentence-mnli-roberta-entail_only', 'F')": {
"0": 0.3135004791,
"average": 0.3135004791
},
"('kendalltau', 'human', 'new', 'bertscore-sentence-mnli-roberta-entail_contradict', 'P')": {
"0": 0.4639049497,
"average": 0.4639049497
},
"('kendalltau', 'human', 'new', 'bertscore-sentence-mnli-roberta-entail_contradict', 'R')": {
"0": 0.2813405561,
"average": 0.2813405561
},
"('kendalltau', 'human', 'new', 'bertscore-sentence-mnli-roberta-entail_contradict', 'F')": {
"0": 0.0219606802,
"average": 0.0219606802
},
"('kendalltau', 'human', 'new', 'bertscore-sentence-mnli-bart-not_neutral', 'P')": {
"0": -0.0899415757,
"average": -0.0899415757
},
"('kendalltau', 'human', 'new', 'bertscore-sentence-mnli-bart-not_neutral', 'R')": {
"0": -0.0667842805,
"average": -0.0667842805
},
"('kendalltau', 'human', 'new', 'bertscore-sentence-mnli-bart-not_neutral', 'F')": {
"0": -0.066294152,
"average": -0.066294152
},
"('kendalltau', 'human', 'new', 'bertscore-sentence-mnli-bart-entail_only', 'P')": {
"0": 0.4807517609,
"average": 0.4807517609
},
"('kendalltau', 'human', 'new', 'bertscore-sentence-mnli-bart-entail_only', 'R')": {
"0": 0.39273847,
"average": 0.39273847
},
"('kendalltau', 'human', 'new', 'bertscore-sentence-mnli-bart-entail_only', 'F')": {
"0": 0.4020840535,
"average": 0.4020840535
},
"('kendalltau', 'human', 'new', 'bertscore-sentence-mnli-bart-entail_contradict', 'P')": {
"0": 0.4720057603,
"average": 0.4720057603
},
"('kendalltau', 'human', 'new', 'bertscore-sentence-mnli-bart-entail_contradict', 'R')": {
"0": 0.2300073658,
"average": 0.2300073658
},
"('kendalltau', 'human', 'new', 'bertscore-sentence-mnli-bart-entail_contradict', 'F')": {
"0": -0.0464055564,
"average": -0.0464055564
},
"('kendalltau', 'human', 'new', 'bertscore-sentence-mnli-deberta-not_neutral', 'P')": {
"0": 0.2368221115,
"average": 0.2368221115
},
"('kendalltau', 'human', 'new', 'bertscore-sentence-mnli-deberta-not_neutral', 'R')": {
"0": -0.0756286195,
"average": -0.0756286195
},
"('kendalltau', 'human', 'new', 'bertscore-sentence-mnli-deberta-not_neutral', 'F')": {
"0": -0.0661004472,
"average": -0.0661004472
},
"('kendalltau', 'human', 'new', 'bertscore-sentence-mnli-deberta-entail_only', 'P')": {
"0": 0.5335440163,
"average": 0.5335440163
},
"('kendalltau', 'human', 'new', 'bertscore-sentence-mnli-deberta-entail_only', 'R')": {
"0": 0.3735207391,
"average": 0.3735207391
},
"('kendalltau', 'human', 'new', 'bertscore-sentence-mnli-deberta-entail_only', 'F')": {
"0": 0.3848367174,
"average": 0.3848367174
},
"('kendalltau', 'human', 'new', 'bertscore-sentence-mnli-deberta-entail_contradict', 'P')": {
"0": 0.5337396595,
"average": 0.5337396595
},
"('kendalltau', 'human', 'new', 'bertscore-sentence-mnli-deberta-entail_contradict', 'R')": {
"0": 0.2695206574,
"average": 0.2695206574
},
"('kendalltau', 'human', 'new', 'bertscore-sentence-mnli-deberta-entail_contradict', 'F')": {
"0": -0.0032238146,
"average": -0.0032238146
},
"('spearmanr', 'human', 'new', 'bertscore-sentence-cos-mpnet', 'P')": {
"0": 0.1642671062,
"average": 0.1642671062
},
"('spearmanr', 'human', 'new', 'bertscore-sentence-cos-mpnet', 'R')": {
"0": -0.0537835503,
"average": -0.0537835503
},
"('spearmanr', 'human', 'new', 'bertscore-sentence-cos-mpnet', 'F')": {
"0": -0.0238617852,
"average": -0.0238617852
},
"('spearmanr', 'human', 'new', 'bertscore-sentence-cos-roberta', 'P')": {
"0": 0.1716590494,
"average": 0.1716590494
},
"('spearmanr', 'human', 'new', 'bertscore-sentence-cos-roberta', 'R')": {
"0": -0.045410397,
"average": -0.045410397
},
"('spearmanr', 'human', 'new', 'bertscore-sentence-cos-roberta', 'F')": {
"0": -0.0103732315,
"average": -0.0103732315
},
"('spearmanr', 'human', 'new', 'bertscore-sentence-mnli-roberta-not_neutral', 'P')": {
"0": 0.021112497,
"average": 0.021112497
},
"('spearmanr', 'human', 'new', 'bertscore-sentence-mnli-roberta-not_neutral', 'R')": {
"0": -0.121496811,
"average": -0.121496811
},
"('spearmanr', 'human', 'new', 'bertscore-sentence-mnli-roberta-not_neutral', 'F')": {
"0": -0.1239536754,
"average": -0.1239536754
},
"('spearmanr', 'human', 'new', 'bertscore-sentence-mnli-roberta-entail_only', 'P')": {
"0": 0.5652555334,
"average": 0.5652555334
},
"('spearmanr', 'human', 'new', 'bertscore-sentence-mnli-roberta-entail_only', 'R')": {
"0": 0.3515413509,
"average": 0.3515413509
},
"('spearmanr', 'human', 'new', 'bertscore-sentence-mnli-roberta-entail_only', 'F')": {
"0": 0.3839214929,
"average": 0.3839214929
},
"('spearmanr', 'human', 'new', 'bertscore-sentence-mnli-roberta-entail_contradict', 'P')": {
"0": 0.5681109499,
"average": 0.5681109499
},
"('spearmanr', 'human', 'new', 'bertscore-sentence-mnli-roberta-entail_contradict', 'R')": {
"0": 0.3445375478,
"average": 0.3445375478
},
"('spearmanr', 'human', 'new', 'bertscore-sentence-mnli-roberta-entail_contradict', 'F')": {
"0": 0.0268936658,
"average": 0.0268936658
},
"('spearmanr', 'human', 'new', 'bertscore-sentence-mnli-bart-not_neutral', 'P')": {
"0": -0.110144968,
"average": -0.110144968
},
"('spearmanr', 'human', 'new', 'bertscore-sentence-mnli-bart-not_neutral', 'R')": {
"0": -0.0817859058,
"average": -0.0817859058
},
"('spearmanr', 'human', 'new', 'bertscore-sentence-mnli-bart-not_neutral', 'F')": {
"0": -0.0811856807,
"average": -0.0811856807
},
"('spearmanr', 'human', 'new', 'bertscore-sentence-mnli-bart-entail_only', 'P')": {
"0": 0.5887417041,
"average": 0.5887417041
},
"('spearmanr', 'human', 'new', 'bertscore-sentence-mnli-bart-entail_only', 'R')": {
"0": 0.4809585624,
"average": 0.4809585624
},
"('spearmanr', 'human', 'new', 'bertscore-sentence-mnli-bart-entail_only', 'F')": {
"0": 0.4924034264,
"average": 0.4924034264
},
"('spearmanr', 'human', 'new', 'bertscore-sentence-mnli-bart-entail_contradict', 'P')": {
"0": 0.5780314286,
"average": 0.5780314286
},
"('spearmanr', 'human', 'new', 'bertscore-sentence-mnli-bart-entail_contradict', 'R')": {
"0": 0.2816734811,
"average": 0.2816734811
},
"('spearmanr', 'human', 'new', 'bertscore-sentence-mnli-bart-entail_contradict', 'F')": {
"0": -0.0568295479,
"average": -0.0568295479
},
"('spearmanr', 'human', 'new', 'bertscore-sentence-mnli-deberta-not_neutral', 'P')": {
"0": 0.2900189046,
"average": 0.2900189046
},
"('spearmanr', 'human', 'new', 'bertscore-sentence-mnli-deberta-not_neutral', 'R')": {
"0": -0.0926169319,
"average": -0.0926169319
},
"('spearmanr', 'human', 'new', 'bertscore-sentence-mnli-deberta-not_neutral', 'F')": {
"0": -0.0809484645,
"average": -0.0809484645
},
"('spearmanr', 'human', 'new', 'bertscore-sentence-mnli-deberta-entail_only', 'P')": {
"0": 0.6533918256,
"average": 0.6533918256
},
"('spearmanr', 'human', 'new', 'bertscore-sentence-mnli-deberta-entail_only', 'R')": {
"0": 0.4574239893,
"average": 0.4574239893
},
"('spearmanr', 'human', 'new', 'bertscore-sentence-mnli-deberta-entail_only', 'F')": {
"0": 0.4712818542,
"average": 0.4712818542
},
"('spearmanr', 'human', 'new', 'bertscore-sentence-mnli-deberta-entail_contradict', 'P')": {
"0": 0.6536323183,
"average": 0.6536323183
},
"('spearmanr', 'human', 'new', 'bertscore-sentence-mnli-deberta-entail_contradict', 'R')": {
"0": 0.3300625678,
"average": 0.3300625678
},
"('spearmanr', 'human', 'new', 'bertscore-sentence-mnli-deberta-entail_contradict', 'F')": {
"0": -0.0039479739,
"average": -0.0039479739
}
}
Loading