#################### QQP ####################
edlp ## bertscore: 0.883934789143006, bleurt: -1.0660817216336727, isacrebleu: 86.84269198749647, wer: 0.9038260201107988, ppl: 481.8243823768139
edlps ## bertscore: 0.8954033228536447, bleurt: -0.8566851574248324, isacrebleu: 83.50441490737703, wer: 0.813841164000211, ppl: 520.9291055495421
UPSA ## bertscore: 0.8964296319862207, bleurt: -0.7286781624391675, isacrebleu: 65.7488936153203, wer: 0.49634162421840955, ppl: 722.832566802303
CGMH_10 ## bertscore: 0.8953981555461884, bleurt: -0.9596808960235367, isacrebleu: 50.31770656012276, wer: 0.28913473993753563, ppl: 743.2987425424417
CGMH_50 ## bertscore: 0.8925640134394169, bleurt: -0.8423082187398027, isacrebleu: 65.3503942369682, wer: 0.455073698796752, ppl: 490.6097778250535
M2M ## bertscore: 0.9385456494828065, bleurt: 0.03628914601681754, isacrebleu: 43.53868754625173, wer: 0.23594101619832725, ppl: 286.63750045496624
M2M_base ## bertscore: 0.9363275157193343, bleurt: -0.0019026256321308514, isacrebleu: 46.0395560712631, wer: 0.2544308763367002, ppl: 351.6738987718582
ours ## bertscore: 0.9383506693502267, bleurt: 0.08253093624711037, isacrebleu: 69.42145179433659, wer: 0.4481315032260948, ppl: 125.90523350303968
ours_v2 ## bertscore: 0.9397474018553893, bleurt: 0.08754429378298421, isacrebleu: 68.96323643919528, wer: 0.4409846606133981, ppl: 126.43364125383695
ours_v3 ## bertscore: 0.9396903170526028, bleurt: 0.08710836742023627, isacrebleu: 69.08430590381987, wer: 0.4423207140044516, ppl: 126.28680368502934
input ## bertscore: 0.9466241271356741, bleurt: 0.12398522536295156, isacrebleu: 0.009999999999943228, wer: 0.0, ppl: 204.72871816275915
reference ## bertscore: 0.9999999934395154, bleurt: 1.0008384853959083, isacrebleu: 72.00245358346925, wer: 0.6314160820102561, ppl: 225.93165502940815
overlap ## overlap_v3: 0, overlap_M2M: 2524
#################### medical ####################
UPSA ## bertscore: 0.8407951116640111, bleurt: -1.3505762425199972, isacrebleu: 89.41771591822639, wer: 0.7489985712058038, ppl: 463.16344598334604
CGMH_10 ## bertscore: 0.8478259603808246, bleurt: -1.3554517505348238, isacrebleu: 76.10954663501259, wer: 0.5001721736328983, ppl: 771.93388996725
CGMH_50 ## bertscore: 0.8381163870568663, bleurt: -1.4054179029671225, isacrebleu: 88.94955332093778, wer: 0.6941013468894065, ppl: 801.6978537761007
M2M_base ## bertscore: 0.8968618114007114, bleurt: -0.5609206023071147, isacrebleu: 35.68755426988565, wer: 0.21979948038172847, ppl: 225.00605261544857
M2M ## bertscore: 0.8971238802346032, bleurt: -0.5461594664340159, isacrebleu: 36.33321152534402, wer: 0.23628443457087409, ppl: 217.8753259319646
ours_medical ## bertscore: 0.8949195785237736, bleurt: -0.48627981603551373, isacrebleu: 72.91729026668439, wer: 0.5570893959603272, ppl: 134.7138967895758
input ## bertscore: 0.9019202751124625, bleurt: -0.5231785194195435, isacrebleu: -4.263256414560601e-14, wer: 0.0, ppl: 191.72098987997362
reference ## bertscore: 0.9999999799362318, bleurt: 0.9359067646380798, isacrebleu: 88.63216108823346, wer: 1.2748491576159033, ppl: 128.38050682213049
overlap ## overlap_v3: 0, overlap_M2M: 56

#################### medical ####################
UPSA ## bertscore: 0, bleurt: -1.3505761845848887, isacrebleu: 89.41771591822639, wer: 0, ppl: 476.06887248150633
CGMH_50 ## bertscore: 0, bleurt: -1.4054178372123267, isacrebleu: 88.94955332093778, wer: 0, ppl: 818.3068276715717
M2M ## bertscore: 0, bleurt: -0.5609204446153808, isacrebleu: 35.68755426988565, wer: 0, ppl: 296.6715879646812
ours_medical ## bertscore: 0, bleurt: -0.5082177095252072, isacrebleu: 68.73528031049582, wer: 0, ppl: 158.75916129209864
input ## bertscore: 0, bleurt: -0.5231783451766675, isacrebleu: -4.263256414560601e-14, wer: 0, ppl: 249.10667843768604
reference ## bertscore: 0, bleurt: 0.9359068207032099, isacrebleu: 88.63216108823346, wer: 0, ppl: 171.7860055069911
#################### QQP ####################
edlp ## bertscore: 0, bleurt: -1.0660811604705949, isacrebleu: 86.84269198749647, wer: 0, ppl: 585.3841777984143
edlps ## bertscore: 0, bleurt: -0.856684603581205, isacrebleu: 83.50441490737703, wer: 0, ppl: 597.0244169775168
UPSA ## bertscore: 0, bleurt: -0.7286776233027379, isacrebleu: 65.7488936153203, wer: 0, ppl: 392.83325559840205
CGMH_50 ## bertscore: 0, bleurt: -0.8423076925708601, isacrebleu: 65.3503942369682, wer: 0, ppl: 556.1629477054914
M2M ## bertscore: 0, bleurt: 0.03628928903813163, isacrebleu: 43.53868754625173, wer: 0, ppl: 346.17039420688945
ours ## bertscore: 0, bleurt: 0.08253149654194712, isacrebleu: 69.42145179433659, wer: 0, ppl: 171.61447043709754
input ## bertscore: 0, bleurt: 0.1239857500050217, isacrebleu: 0.009999999999943228, wer: 0, ppl: 270.7808294111252
reference ## bertscore: 0, bleurt: 1.0008386475026607, isacrebleu: 72.00245358346925, wer: 0, ppl: 278.1628854610443
overlap ## overlap_ours: 0, overlap_M2M: 2524
