| {"GEM/web_nlg_en": {"PALM_prompt": {"bleu": 0.22386799285100242, "bleu_stderr": 0.025018167341179967, "rouge1_fmeasure": 0.08717467473249238, "rouge1_fmeasure_stderr": 0.001988496293821803, "rouge1_precision": 0.06270503422215706, "rouge1_precision_stderr": 0.0018889830987665244, "rouge1_recall": 0.22196309199959086, "rouge1_recall_stderr": 0.003977028632566687, "rouge2_fmeasure": 0.03760470124518723, "rouge2_fmeasure_stderr": 0.0011212849650132507, "rouge2_precision": 0.02636193213072692, "rouge2_precision_stderr": 0.0009948761975072144, "rouge2_recall": 0.10182548952971911, "rouge2_recall_stderr": 0.0026075444055286934, "rougeL_fmeasure": 0.08288446430861876, "rougeL_fmeasure_stderr": 0.0017917823158372869, "rougeL_precision": 0.058872164432613124, "rougeL_precision_stderr": 0.0016543717782211067, "rougeL_recall": 0.2150079269966024, "rougeL_recall_stderr": 0.0038312866185628972, "rougeLsum_fmeasure": 0.08313479823551378, "rougeLsum_fmeasure_stderr": 0.0018229722576069702, "rougeLsum_precision": 0.059266742576785554, "rougeLsum_precision_stderr": 0.001700146105139763, "rougeLsum_recall": 0.2146878788305741, "rougeLsum_recall_stderr": 0.003813273422443642}}, "GEM/wiki_lingua_en": {"tldr_en": {"bleu": 0.09489512058813623, "bleu_stderr": 0.015019543669611902, "rouge1_fmeasure": 0.03692896653093653, "rouge1_fmeasure_stderr": 0.001444978729387553, "rouge1_precision": 0.04847824168899397, "rouge1_precision_stderr": 0.0021527306994951743, "rouge1_recall": 0.04290155774449955, "rouge1_recall_stderr": 0.0017685252209751602, "rouge2_fmeasure": 0.006267683793955542, "rouge2_fmeasure_stderr": 0.0005005058667584872, "rouge2_precision": 0.00916634461711251, "rouge2_precision_stderr": 0.0008793312023838661, "rouge2_recall": 0.007207669889606505, "rouge2_recall_stderr": 0.0006015119954053042, "rougeL_fmeasure": 0.03090192793357971, "rougeL_fmeasure_stderr": 0.001194549842708322, "rougeL_precision": 0.04072462596685456, "rougeL_precision_stderr": 0.001826606480591984, "rougeL_recall": 0.03615887229029135, "rougeL_recall_stderr": 0.0014729717928229518, "rougeLsum_fmeasure": 0.03442247041414027, "rougeLsum_fmeasure_stderr": 0.0013400879274452296, "rougeLsum_precision": 0.04542034910903916, "rougeLsum_precision_stderr": 0.0020204702947843995, "rougeLsum_recall": 0.039970284683949656, "rougeLsum_recall_stderr": 0.0016443164447444867}}, "e2e_nlg_cleaned": {"generate_text_restaurant": {"bleu": 8.942155482913693, "bleu_stderr": 0.16097618995677943, "rouge1_fmeasure": 0.36393958053094144, "rouge1_fmeasure_stderr": 0.0022056875684752482, "rouge1_precision": 0.43622486474795197, "rouge1_precision_stderr": 0.003180231455917317, "rouge1_recall": 0.34794080588594495, "rouge1_recall_stderr": 0.0025302437862891095, "rouge2_fmeasure": 0.15830475389068993, "rouge2_fmeasure_stderr": 0.0017490360106332174, "rouge2_precision": 0.19328105202965348, "rouge2_precision_stderr": 0.0023520595209739854, "rouge2_recall": 0.1512965958463667, "rouge2_recall_stderr": 0.0018449526665716308, "rougeL_fmeasure": 0.28058628929067725, "rougeL_fmeasure_stderr": 0.001866861403319837, "rougeL_precision": 0.3379579590729962, "rougeL_precision_stderr": 0.002768090228521333, "rougeL_recall": 0.26863807145078394, "rougeL_recall_stderr": 0.00211887791687035, "rougeLsum_fmeasure": 0.30998668589677814, "rougeLsum_fmeasure_stderr": 0.002129216424796756, "rougeLsum_precision": 0.3722310719989836, "rougeLsum_precision_stderr": 0.003015809692521337, "rougeLsum_recall": 0.29631987882427524, "rougeLsum_recall_stderr": 0.0023825505361464985}}, "gem_xsum": {"article_DOC_summary": {"bleu": 0.1945677197809648, "bleu_stderr": 0.04427282782106186, "rouge1_fmeasure": 0.03937861378098916, "rouge1_fmeasure_stderr": 0.002315856820827257, "rouge1_precision": 0.037913585028776065, "rouge1_precision_stderr": 0.0023001502602127523, "rouge1_recall": 0.04985852283454599, "rouge1_recall_stderr": 0.003059874154622636, "rouge2_fmeasure": 0.005653435053950428, "rouge2_fmeasure_stderr": 0.0006134888531248025, "rouge2_precision": 0.0049564518309591745, "rouge2_precision_stderr": 0.0005552167801086178, "rouge2_recall": 0.00808101754829496, "rouge2_recall_stderr": 0.0009432130706742604, "rougeL_fmeasure": 0.031970816594020374, "rougeL_fmeasure_stderr": 0.0018597075082346828, "rougeL_precision": 0.03066492611348946, "rougeL_precision_stderr": 0.0018517687252350952, "rougeL_recall": 0.0409686857380869, "rougeL_recall_stderr": 0.0025238815188420474, "rougeLsum_fmeasure": 0.03145276305797317, "rougeLsum_fmeasure_stderr": 0.0018465561902809033, "rougeLsum_precision": 0.030346836341775464, "rougeLsum_precision_stderr": 0.0018562425966080272, "rougeLsum_recall": 0.04007296257687896, "rougeLsum_recall_stderr": 0.00249432492023191}}} |