Muennighoff's picture
Add
29393c3
raw
history blame contribute delete
No virus
28 kB
{"GEM/web_nlg_en": {"0": {"PALM_prompt": {"bleu": 0.40286648385376755, "bleu_stderr": 0.05212845034450995, "rouge1_fmeasure": 0.10639343053245706, "rouge1_fmeasure_stderr": 0.0021073511307359532, "rouge1_precision": 0.06996098838307302, "rouge1_precision_stderr": 0.0015898449832407893, "rouge1_recall": 0.29442884741673947, "rouge1_recall_stderr": 0.004657771756760718, "rouge2_fmeasure": 0.05033305845129639, "rouge2_fmeasure_stderr": 0.0013249908270922567, "rouge2_precision": 0.03294981919147428, "rouge2_precision_stderr": 0.0009663398363788032, "rouge2_recall": 0.14246175839945485, "rouge2_recall_stderr": 0.0031909835354524702, "rougeL_fmeasure": 0.10235134870489063, "rougeL_fmeasure_stderr": 0.0019273341529169933, "rougeL_precision": 0.06695896997261808, "rougeL_precision_stderr": 0.0014202002477843082, "rougeL_recall": 0.28646151455290875, "rougeL_recall_stderr": 0.004529876020974902, "rougeLsum_fmeasure": 0.10161495575656154, "rougeLsum_fmeasure_stderr": 0.0019693633168815267, "rougeLsum_precision": 0.0667289062013898, "rougeLsum_precision_stderr": 0.001476878097104591, "rougeLsum_recall": 0.2816381384137136, "rougeLsum_recall_stderr": 0.00440124224176318}}, "1": {"PALM_prompt": {"bleu": 0.5379028926508614, "bleu_stderr": 0.03687531363084996, "rouge1_fmeasure": 0.11471205984296223, "rouge1_fmeasure_stderr": 0.0018805014434852309, "rouge1_precision": 0.07309631370592509, "rouge1_precision_stderr": 0.0013732592923049792, "rouge1_recall": 0.37028400918910054, "rouge1_recall_stderr": 0.005457409473033004, "rouge2_fmeasure": 0.0530528813586448, "rouge2_fmeasure_stderr": 0.001199555498269871, "rouge2_precision": 0.03377367444978376, "rouge2_precision_stderr": 0.0008548764812808871, "rouge2_recall": 0.17908798528025902, "rouge2_recall_stderr": 0.0037028704616034083, "rougeL_fmeasure": 0.10809733095164265, "rougeL_fmeasure_stderr": 0.0016925101881231047, "rougeL_precision": 0.0688117484703189, "rougeL_precision_stderr": 0.001222213532774839, "rougeL_recall": 0.3480091072970109, "rougeL_recall_stderr": 0.004950245404519997, "rougeLsum_fmeasure": 0.10846385734949525, "rougeLsum_fmeasure_stderr": 0.0017609033136198704, "rougeLsum_precision": 0.0692047577374815, "rougeLsum_precision_stderr": 0.0012923071491164684, "rougeLsum_recall": 0.34853415419811595, "rougeLsum_recall_stderr": 0.004966041933763933}}, "2": {"PALM_prompt": {"bleu": 0.5942366626957291, "bleu_stderr": 0.025627212989091184, "rouge1_fmeasure": 0.11889915113239362, "rouge1_fmeasure_stderr": 0.0017198201554726746, "rouge1_precision": 0.07493247583805844, "rouge1_precision_stderr": 0.0012395113463601354, "rouge1_recall": 0.4039521622707045, "rouge1_recall_stderr": 0.005434274713783703, "rouge2_fmeasure": 0.054647342094887884, "rouge2_fmeasure_stderr": 0.0010921234226901342, "rouge2_precision": 0.034282050377834015, "rouge2_precision_stderr": 0.0007600503732258525, "rouge2_recall": 0.1991669602854511, "rouge2_recall_stderr": 0.003931080841294317, "rougeL_fmeasure": 0.10982111537163444, "rougeL_fmeasure_stderr": 0.0015404704299286365, "rougeL_precision": 0.06925387716093144, "rougeL_precision_stderr": 0.001112414391402196, "rougeL_recall": 0.3720868248461876, "rougeL_recall_stderr": 0.004894890409864309, "rougeLsum_fmeasure": 0.11238895371903196, "rougeLsum_fmeasure_stderr": 0.0016119226692343728, "rougeLsum_precision": 0.07089026453871902, "rougeLsum_precision_stderr": 0.0011645544140396038, "rougeLsum_recall": 0.38071119224279054, "rougeLsum_recall_stderr": 0.00501969435495313}}, "3": {"PALM_prompt": {"bleu": 0.6679262074421776, "bleu_stderr": 0.03333067116771941, "rouge1_fmeasure": 0.12006524308183385, "rouge1_fmeasure_stderr": 0.0016814614065816674, "rouge1_precision": 0.07536480662831223, "rouge1_precision_stderr": 0.0011983446313843626, "rouge1_recall": 0.4126495888007212, "rouge1_recall_stderr": 0.005516411154661876, "rouge2_fmeasure": 0.054975410913038446, "rouge2_fmeasure_stderr": 0.001083918785034363, "rouge2_precision": 0.03435429282776522, "rouge2_precision_stderr": 0.0007469545646988583, "rouge2_recall": 0.2021206807513725, "rouge2_recall_stderr": 0.003937737161421917, "rougeL_fmeasure": 0.11006804581376863, "rougeL_fmeasure_stderr": 0.001493830571926201, "rougeL_precision": 0.06923780115211091, "rougeL_precision_stderr": 0.001077323853164496, "rougeL_recall": 0.37665280691221614, "rougeL_recall_stderr": 0.004882350067942863, "rougeLsum_fmeasure": 0.1129753647300024, "rougeLsum_fmeasure_stderr": 0.001577915948877365, "rougeLsum_precision": 0.07103697236204776, "rougeLsum_precision_stderr": 0.0011338290169387135, "rougeLsum_recall": 0.38640310742292994, "rougeLsum_recall_stderr": 0.005040562618951275}}, "4": {"PALM_prompt": {"bleu": 0.6769067627224955, "bleu_stderr": 0.0461104671558504, "rouge1_fmeasure": 0.12273630978790588, "rouge1_fmeasure_stderr": 0.001663341770893685, "rouge1_precision": 0.07698161606160427, "rouge1_precision_stderr": 0.0011812041716973312, "rouge1_recall": 0.4169767197057726, "rouge1_recall_stderr": 0.005368256764036794, "rouge2_fmeasure": 0.05676722017594987, "rouge2_fmeasure_stderr": 0.0010551520395745532, "rouge2_precision": 0.03535772650403365, "rouge2_precision_stderr": 0.0007212057820482756, "rouge2_recall": 0.20970750904696342, "rouge2_recall_stderr": 0.0039457537348272925, "rougeL_fmeasure": 0.1122867012912741, "rougeL_fmeasure_stderr": 0.0014682525659690917, "rougeL_precision": 0.07053008542469329, "rougeL_precision_stderr": 0.001056451040385872, "rougeL_recall": 0.38052456768133897, "rougeL_recall_stderr": 0.004711823160775788, "rougeLsum_fmeasure": 0.11624170216768001, "rougeLsum_fmeasure_stderr": 0.0015625017951151554, "rougeLsum_precision": 0.07296806904648159, "rougeLsum_precision_stderr": 0.0011161127148090057, "rougeLsum_recall": 0.39425404712648704, "rougeLsum_recall_stderr": 0.004952931195655136}}, "5": {"PALM_prompt": {"bleu": 0.7298388215986955, "bleu_stderr": 0.03410846938230183, "rouge1_fmeasure": 0.12306547329071646, "rouge1_fmeasure_stderr": 0.0016005194094492465, "rouge1_precision": 0.07695562502104737, "rouge1_precision_stderr": 0.001146538309303851, "rouge1_recall": 0.42572244510998153, "rouge1_recall_stderr": 0.005292556910488358, "rouge2_fmeasure": 0.05651438979578568, "rouge2_fmeasure_stderr": 0.001041479745584778, "rouge2_precision": 0.035072722310952494, "rouge2_precision_stderr": 0.0007144692727423962, "rouge2_recall": 0.21311707552350648, "rouge2_recall_stderr": 0.003973886927101672, "rougeL_fmeasure": 0.11208456880715004, "rougeL_fmeasure_stderr": 0.0014454570151403556, "rougeL_precision": 0.07024401142170024, "rougeL_precision_stderr": 0.001051262962385294, "rougeL_recall": 0.3855636673236153, "rougeL_recall_stderr": 0.004614982713566353, "rougeLsum_fmeasure": 0.11597908604907735, "rougeLsum_fmeasure_stderr": 0.001497182042775692, "rougeLsum_precision": 0.07259500178551292, "rougeLsum_precision_stderr": 0.0010804144644452327, "rougeLsum_recall": 0.39997726550161855, "rougeLsum_recall_stderr": 0.0048313269402151205}}}, "GEM/wiki_lingua_en": {"0": {"tldr_en": {"bleu": 1.7892535258267361, "bleu_stderr": 0.07376152555399827, "rouge1_fmeasure": 0.18718732854154974, "rouge1_fmeasure_stderr": 0.0018924487998349612, "rouge1_precision": 0.15969051276064813, "rouge1_precision_stderr": 0.001942883143586728, "rouge1_recall": 0.27343051217750347, "rouge1_recall_stderr": 0.0027587854784945757, "rouge2_fmeasure": 0.04075668205435305, "rouge2_fmeasure_stderr": 0.0009022201823907085, "rouge2_precision": 0.03457636027289612, "rouge2_precision_stderr": 0.0008049732049233189, "rouge2_recall": 0.061281361460635966, "rouge2_recall_stderr": 0.0014971431420006567, "rougeL_fmeasure": 0.1452400681084372, "rougeL_fmeasure_stderr": 0.0013211415113596292, "rougeL_precision": 0.12243858898167204, "rougeL_precision_stderr": 0.0013264585867582177, "rougeL_recall": 0.21719592340715815, "rougeL_recall_stderr": 0.002198877203255072, "rougeLsum_fmeasure": 0.1717276627498721, "rougeLsum_fmeasure_stderr": 0.0017249210773351896, "rougeLsum_precision": 0.14631477056240805, "rougeLsum_precision_stderr": 0.0017693856980057917, "rougeLsum_recall": 0.25167431554385267, "rougeLsum_recall_stderr": 0.0025519675545699265}}, "1": {"tldr_en": {"bleu": 2.7313763312803463, "bleu_stderr": 0.06431841398930878, "rouge1_fmeasure": 0.2179019106488729, "rouge1_fmeasure_stderr": 0.001914589747533169, "rouge1_precision": 0.19337653863894458, "rouge1_precision_stderr": 0.0022789610297058423, "rouge1_recall": 0.31342249510279335, "rouge1_recall_stderr": 0.0027451555547873163, "rouge2_fmeasure": 0.05309884853711394, "rouge2_fmeasure_stderr": 0.0010362274557463985, "rouge2_precision": 0.04767366659499796, "rouge2_precision_stderr": 0.0010966119115502326, "rouge2_recall": 0.07815815946901311, "rouge2_recall_stderr": 0.0016866799115371686, "rougeL_fmeasure": 0.1573437634028076, "rougeL_fmeasure_stderr": 0.0013081487267953859, "rougeL_precision": 0.13876745029470247, "rougeL_precision_stderr": 0.0016193053665115018, "rougeL_recall": 0.23180330032633759, "rougeL_recall_stderr": 0.0021871697423696415, "rougeLsum_fmeasure": 0.20404526770912643, "rougeLsum_fmeasure_stderr": 0.0017913673119406505, "rougeLsum_precision": 0.18110312506761292, "rougeLsum_precision_stderr": 0.002148924896412393, "rougeLsum_recall": 0.2939865838321714, "rougeLsum_recall_stderr": 0.0026003070024099395}}, "2": {"tldr_en": {"bleu": 3.2706626686468483, "bleu_stderr": 0.05895243674760552, "rouge1_fmeasure": 0.22655355604347935, "rouge1_fmeasure_stderr": 0.0019575369428529144, "rouge1_precision": 0.2378942905907137, "rouge1_precision_stderr": 0.0031497210011433496, "rouge1_recall": 0.30323691861478563, "rouge1_recall_stderr": 0.002907309508940713, "rouge2_fmeasure": 0.05930210668592541, "rouge2_fmeasure_stderr": 0.0011620048939953744, "rouge2_precision": 0.06661871177427002, "rouge2_precision_stderr": 0.0018856657162201126, "rouge2_recall": 0.0803263511266704, "rouge2_recall_stderr": 0.0017407744409257712, "rougeL_fmeasure": 0.16378420244346403, "rougeL_fmeasure_stderr": 0.0014079706838807605, "rougeL_precision": 0.17510717603427448, "rougeL_precision_stderr": 0.002585888506583138, "rougeL_recall": 0.22190182805565306, "rougeL_recall_stderr": 0.0022886872280766754, "rougeLsum_fmeasure": 0.21397004830277258, "rougeLsum_fmeasure_stderr": 0.001847756158136501, "rougeLsum_precision": 0.22473899823994106, "rougeLsum_precision_stderr": 0.0030077620086430773, "rougeLsum_recall": 0.28698298853858273, "rougeLsum_recall_stderr": 0.0027715872137367885}}, "3": {"tldr_en": {"bleu": 3.625995619755928, "bleu_stderr": 0.08151204101758054, "rouge1_fmeasure": 0.18879655923916508, "rouge1_fmeasure_stderr": 0.002417829019868095, "rouge1_precision": 0.22797269883915738, "rouge1_precision_stderr": 0.0038340085779668192, "rouge1_recall": 0.23645930801545356, "rouge1_recall_stderr": 0.003376410271713712, "rouge2_fmeasure": 0.0517180012203842, "rouge2_fmeasure_stderr": 0.0012108106278924731, "rouge2_precision": 0.06756596682222428, "rouge2_precision_stderr": 0.0021738332098718894, "rouge2_recall": 0.06552475514042137, "rouge2_recall_stderr": 0.0016796922078675188, "rougeL_fmeasure": 0.13925720702220254, "rougeL_fmeasure_stderr": 0.0018062024998216275, "rougeL_precision": 0.17257640354449272, "rougeL_precision_stderr": 0.0031587073849980592, "rougeL_recall": 0.1755452238104328, "rougeL_recall_stderr": 0.0026310211489849133, "rougeLsum_fmeasure": 0.17894024147930437, "rougeLsum_fmeasure_stderr": 0.002304299372894341, "rougeLsum_precision": 0.21606433484698467, "rougeLsum_precision_stderr": 0.00365906632460656, "rougeLsum_recall": 0.22396544472382549, "rougeLsum_recall_stderr": 0.003215244567646662}}, "4": {"tldr_en": {"bleu": 0.32276000238250857, "bleu_stderr": 0.04122539509538276, "rouge1_fmeasure": 0.05877235025374831, "rouge1_fmeasure_stderr": 0.0020757714328794993, "rouge1_precision": 0.07359995764515682, "rouge1_precision_stderr": 0.002967980885850916, "rouge1_recall": 0.07437337044894303, "rouge1_recall_stderr": 0.002771566352869776, "rouge2_fmeasure": 0.01647080810209277, "rouge2_fmeasure_stderr": 0.0008494024468294314, "rouge2_precision": 0.022811544918519226, "rouge2_precision_stderr": 0.0014875286720145739, "rouge2_recall": 0.021443597362593173, "rouge2_recall_stderr": 0.0012035793544498154, "rougeL_fmeasure": 0.044744539055611814, "rougeL_fmeasure_stderr": 0.0015882377996984806, "rougeL_precision": 0.05769488309593311, "rougeL_precision_stderr": 0.00243974941628649, "rougeL_recall": 0.05662359971916526, "rougeL_recall_stderr": 0.0021434534763578057, "rougeLsum_fmeasure": 0.055593054042710664, "rougeLsum_fmeasure_stderr": 0.0019668083119517665, "rougeLsum_precision": 0.06995076302877311, "rougeLsum_precision_stderr": 0.0028399207563645236, "rougeLsum_recall": 0.07020001543089976, "rougeLsum_recall_stderr": 0.002619552306226126}}, "5": {"tldr_en": {"bleu": 1.3484611407865652e-09, "bleu_stderr": 8.443352035948435e-09, "rouge1_fmeasure": 0.009114612973823273, "rouge1_fmeasure_stderr": 0.0009223542254736345, "rouge1_precision": 0.01239315444106573, "rouge1_precision_stderr": 0.0014363410021848279, "rouge1_recall": 0.011383300045857872, "rouge1_recall_stderr": 0.0012173762561540143, "rouge2_fmeasure": 0.00278038991283995, "rouge2_fmeasure_stderr": 0.00038473075637041824, "rouge2_precision": 0.0045302531996229065, "rouge2_precision_stderr": 0.0008330565796211205, "rouge2_recall": 0.003576470172001708, "rouge2_recall_stderr": 0.0005588651622667037, "rougeL_fmeasure": 0.007155949619192927, "rougeL_fmeasure_stderr": 0.0007211501481932415, "rougeL_precision": 0.01001834697102603, "rougeL_precision_stderr": 0.0012120937969546158, "rougeL_recall": 0.008985972581881612, "rougeL_recall_stderr": 0.0009837080918219663, "rougeLsum_fmeasure": 0.008540877676789025, "rougeLsum_fmeasure_stderr": 0.0008635134486980147, "rougeLsum_precision": 0.011636645385352324, "rougeLsum_precision_stderr": 0.001366681246596602, "rougeLsum_recall": 0.010738557235201493, "rougeLsum_recall_stderr": 0.001155987282700236}}}, "e2e_nlg_cleaned": {"0": {"generate_text_restaurant": {"bleu": 2.693401837200285, "bleu_stderr": 0.08763868635746681, "rouge1_fmeasure": 0.16611297494282404, "rouge1_fmeasure_stderr": 0.00159680296784645, "rouge1_precision": 0.16579904997386866, "rouge1_precision_stderr": 0.002186020056914844, "rouge1_recall": 0.22642045526757837, "rouge1_recall_stderr": 0.0023687905832833014, "rouge2_fmeasure": 0.041429203797191096, "rouge2_fmeasure_stderr": 0.0010121278902232196, "rouge2_precision": 0.03388945696322452, "rouge2_precision_stderr": 0.0008651029489382238, "rouge2_recall": 0.060593946509437495, "rouge2_recall_stderr": 0.0014889438447109118, "rougeL_fmeasure": 0.15663336526066807, "rougeL_fmeasure_stderr": 0.0013865257867417336, "rougeL_precision": 0.15530426027054353, "rougeL_precision_stderr": 0.0019863912296353655, "rougeL_recall": 0.21503755577893796, "rougeL_recall_stderr": 0.00211789398504925, "rougeLsum_fmeasure": 0.1428371423325733, "rougeLsum_fmeasure_stderr": 0.0014402421725265263, "rougeLsum_precision": 0.1450920759219515, "rougeLsum_precision_stderr": 0.002087614148443835, "rougeLsum_recall": 0.1931878795136461, "rougeLsum_recall_stderr": 0.0020747007413996115}}, "1": {"generate_text_restaurant": {"bleu": 10.811542079735363, "bleu_stderr": 0.15162454275554624, "rouge1_fmeasure": 0.42854660449035686, "rouge1_fmeasure_stderr": 0.0022746952803792044, "rouge1_precision": 0.5137013573524062, "rouge1_precision_stderr": 0.00319258683563529, "rouge1_recall": 0.40636878171094676, "rouge1_recall_stderr": 0.002882672968645596, "rouge2_fmeasure": 0.1928054727426135, "rouge2_fmeasure_stderr": 0.0019038284121157692, "rouge2_precision": 0.23534073778557085, "rouge2_precision_stderr": 0.0025715857623083557, "rouge2_recall": 0.18258609223833502, "rouge2_recall_stderr": 0.002046539791218941, "rougeL_fmeasure": 0.3113788779508062, "rougeL_fmeasure_stderr": 0.0019774235562405734, "rougeL_precision": 0.3762979694307179, "rougeL_precision_stderr": 0.0028693975057274054, "rougeL_recall": 0.2944414188627779, "rougeL_recall_stderr": 0.002337120458337281, "rougeLsum_fmeasure": 0.3498432663788988, "rougeLsum_fmeasure_stderr": 0.0022315022947435688, "rougeLsum_precision": 0.4205624013999805, "rougeLsum_precision_stderr": 0.003079312427902136, "rougeLsum_recall": 0.3313519491919322, "rougeLsum_recall_stderr": 0.002639246783373194}}, "2": {"generate_text_restaurant": {"bleu": 12.803942144601116, "bleu_stderr": 0.21618040146131992, "rouge1_fmeasure": 0.4611513176254791, "rouge1_fmeasure_stderr": 0.002199995367365474, "rouge1_precision": 0.5538907219965342, "rouge1_precision_stderr": 0.0032612294164257216, "rouge1_recall": 0.4350995198760696, "rouge1_recall_stderr": 0.002856610829509688, "rouge2_fmeasure": 0.2229687549240271, "rouge2_fmeasure_stderr": 0.0019710523597241715, "rouge2_precision": 0.2729320100739506, "rouge2_precision_stderr": 0.0027234503513028584, "rouge2_recall": 0.2101696343227206, "rouge2_recall_stderr": 0.002150285923735445, "rougeL_fmeasure": 0.3416818930898736, "rougeL_fmeasure_stderr": 0.0020246870873676555, "rougeL_precision": 0.4133741500218145, "rougeL_precision_stderr": 0.003020936241100034, "rougeL_recall": 0.32145908492422065, "rougeL_recall_stderr": 0.0023969661475136306, "rougeLsum_fmeasure": 0.38257616765715247, "rougeLsum_fmeasure_stderr": 0.0022246263334132453, "rougeLsum_precision": 0.4611079827648602, "rougeLsum_precision_stderr": 0.0032149008542871746, "rougeLsum_recall": 0.36026749805953084, "rougeLsum_recall_stderr": 0.002648080757717859}}, "3": {"generate_text_restaurant": {"bleu": 13.549419526938319, "bleu_stderr": 0.1855065278827089, "rouge1_fmeasure": 0.47156037863176303, "rouge1_fmeasure_stderr": 0.0021582661393463962, "rouge1_precision": 0.5622765325560521, "rouge1_precision_stderr": 0.0032287138496162934, "rouge1_recall": 0.44435519723608424, "rouge1_recall_stderr": 0.002801797047585696, "rouge2_fmeasure": 0.23320849920258752, "rouge2_fmeasure_stderr": 0.002003019136182861, "rouge2_precision": 0.2824005913951133, "rouge2_precision_stderr": 0.002719274951851043, "rouge2_recall": 0.21987553093336418, "rouge2_recall_stderr": 0.002184214297734334, "rougeL_fmeasure": 0.35119690753799093, "rougeL_fmeasure_stderr": 0.002078338911409397, "rougeL_precision": 0.42050656145422816, "rougeL_precision_stderr": 0.0030059607815769765, "rougeL_recall": 0.330473027799321, "rougeL_recall_stderr": 0.0024402629244160393, "rougeLsum_fmeasure": 0.394476669084247, "rougeLsum_fmeasure_stderr": 0.0022641630943918186, "rougeLsum_precision": 0.4706616514354793, "rougeLsum_precision_stderr": 0.003192105043156649, "rougeLsum_recall": 0.37155323262077417, "rougeLsum_recall_stderr": 0.0026779306873817056}}, "4": {"generate_text_restaurant": {"bleu": 13.824091400241928, "bleu_stderr": 0.13104091370071627, "rouge1_fmeasure": 0.4729227008920987, "rouge1_fmeasure_stderr": 0.002173390089402513, "rouge1_precision": 0.559655152378256, "rouge1_precision_stderr": 0.00321686393289185, "rouge1_recall": 0.4463184732215886, "rouge1_recall_stderr": 0.002756272749754986, "rouge2_fmeasure": 0.23586940604720674, "rouge2_fmeasure_stderr": 0.0020025387806477473, "rouge2_precision": 0.2840232577174272, "rouge2_precision_stderr": 0.00271181738495325, "rouge2_recall": 0.2222491185021198, "rouge2_recall_stderr": 0.0021623586075651146, "rougeL_fmeasure": 0.35202027805933056, "rougeL_fmeasure_stderr": 0.002092564908854137, "rougeL_precision": 0.4180629283082632, "rougeL_precision_stderr": 0.0029877481411599237, "rougeL_recall": 0.33196107712218637, "rougeL_recall_stderr": 0.0024311143031782462, "rougeLsum_fmeasure": 0.39613612180447344, "rougeLsum_fmeasure_stderr": 0.002266152079884005, "rougeLsum_precision": 0.4688463943976415, "rougeLsum_precision_stderr": 0.0031530760765321546, "rougeLsum_recall": 0.37409621129154014, "rougeLsum_recall_stderr": 0.0026785522822089635}}, "5": {"generate_text_restaurant": {"bleu": 14.200380998337229, "bleu_stderr": 0.19329384114815742, "rouge1_fmeasure": 0.47679187260022104, "rouge1_fmeasure_stderr": 0.002154333673818338, "rouge1_precision": 0.5598013517043776, "rouge1_precision_stderr": 0.0031952209265306724, "rouge1_recall": 0.4515552018520872, "rouge1_recall_stderr": 0.0027541134409545752, "rouge2_fmeasure": 0.23981788779086907, "rouge2_fmeasure_stderr": 0.0020141420899880426, "rouge2_precision": 0.2868996527085169, "rouge2_precision_stderr": 0.0027439839572370225, "rouge2_recall": 0.22658843899426176, "rouge2_recall_stderr": 0.002166189730967118, "rougeL_fmeasure": 0.3553964547201032, "rougeL_fmeasure_stderr": 0.0020748384854769424, "rougeL_precision": 0.4188961211054761, "rougeL_precision_stderr": 0.0029753067970391253, "rougeL_recall": 0.33630944752712066, "rougeL_recall_stderr": 0.002420426022345789, "rougeLsum_fmeasure": 0.40177021275924996, "rougeLsum_fmeasure_stderr": 0.0022697719817145177, "rougeLsum_precision": 0.47218722229605625, "rougeLsum_precision_stderr": 0.003172746693556059, "rougeLsum_recall": 0.3804288121576126, "rougeLsum_recall_stderr": 0.0026714741710499577}}}, "gem_xsum": {"0": {"article_DOC_summary": {"bleu": 2.0960641205542827, "bleu_stderr": 0.06798641040244616, "rouge1_fmeasure": 0.20476726427909248, "rouge1_fmeasure_stderr": 0.002649474133903418, "rouge1_precision": 0.15842344794238317, "rouge1_precision_stderr": 0.002372031267709981, "rouge1_recall": 0.3284952182299337, "rouge1_recall_stderr": 0.0044298556614964756, "rouge2_fmeasure": 0.046916069305408335, "rouge2_fmeasure_stderr": 0.0017197355481914094, "rouge2_precision": 0.03540871760128505, "rouge2_precision_stderr": 0.0014181321683695847, "rouge2_recall": 0.07816166775968982, "rouge2_recall_stderr": 0.0028237456627397046, "rougeL_fmeasure": 0.15749123183599076, "rougeL_fmeasure_stderr": 0.002073944694954327, "rougeL_precision": 0.12176908432033119, "rougeL_precision_stderr": 0.0018710373562779625, "rougeL_recall": 0.2541701545006927, "rougeL_recall_stderr": 0.003551902432183393, "rougeLsum_fmeasure": 0.16236856321055648, "rougeLsum_fmeasure_stderr": 0.002283002778052774, "rougeLsum_precision": 0.12532539040842194, "rougeLsum_precision_stderr": 0.0019917639332936807, "rougeLsum_recall": 0.26232198349291647, "rougeLsum_recall_stderr": 0.003932145235326188}}, "1": {"article_DOC_summary": {"bleu": 1.4696760073708208, "bleu_stderr": 0.06265270441243473, "rouge1_fmeasure": 0.17891974543666367, "rouge1_fmeasure_stderr": 0.0024706510302881872, "rouge1_precision": 0.1271937006393597, "rouge1_precision_stderr": 0.0018275474060210689, "rouge1_recall": 0.3135496885733734, "rouge1_recall_stderr": 0.004242917655669163, "rouge2_fmeasure": 0.03736288266942292, "rouge2_fmeasure_stderr": 0.0014220403164735326, "rouge2_precision": 0.026267000271180424, "rouge2_precision_stderr": 0.0010006504874047221, "rouge2_recall": 0.06722812716641016, "rouge2_recall_stderr": 0.002624780376748357, "rougeL_fmeasure": 0.14017165769151607, "rougeL_fmeasure_stderr": 0.0018633298526103481, "rougeL_precision": 0.09950647531372532, "rougeL_precision_stderr": 0.001366245247346246, "rougeL_recall": 0.24678392130953006, "rougeL_recall_stderr": 0.0033174561386390567, "rougeLsum_fmeasure": 0.1428074680374857, "rougeLsum_fmeasure_stderr": 0.002053207964484963, "rougeLsum_precision": 0.1012924090593187, "rougeLsum_precision_stderr": 0.0014963465244654786, "rougeLsum_recall": 0.2518765845772237, "rougeLsum_recall_stderr": 0.0036614448966502135}}, "2": {"article_DOC_summary": {"bleu": 1.5439003664247115, "bleu_stderr": 0.10851669022401786, "rouge1_fmeasure": 0.18113319848969633, "rouge1_fmeasure_stderr": 0.0024823291925392898, "rouge1_precision": 0.12914677410683195, "rouge1_precision_stderr": 0.001846681090538485, "rouge1_recall": 0.31563927705067746, "rouge1_recall_stderr": 0.004211671574972399, "rouge2_fmeasure": 0.039942143589958415, "rouge2_fmeasure_stderr": 0.0014636503235895269, "rouge2_precision": 0.028246308499238097, "rouge2_precision_stderr": 0.001039777781254331, "rouge2_recall": 0.07096061694974337, "rouge2_recall_stderr": 0.0026636364744364984, "rougeL_fmeasure": 0.1456603788587842, "rougeL_fmeasure_stderr": 0.0019174980062219666, "rougeL_precision": 0.10371573983765109, "rougeL_precision_stderr": 0.0014182980426936482, "rougeL_recall": 0.2550751527972976, "rougeL_recall_stderr": 0.00337783485571472, "rougeLsum_fmeasure": 0.14257911934085393, "rougeLsum_fmeasure_stderr": 0.0020437479521562105, "rougeLsum_precision": 0.10139018090786547, "rougeLsum_precision_stderr": 0.0014984047207110595, "rougeLsum_recall": 0.25022303799687573, "rougeLsum_recall_stderr": 0.0035989374972674425}}, "3": {"article_DOC_summary": {"bleu": 1.6145690136458937, "bleu_stderr": 0.08805787248504932, "rouge1_fmeasure": 0.17680602744097074, "rouge1_fmeasure_stderr": 0.002631980246229425, "rouge1_precision": 0.1296338781704996, "rouge1_precision_stderr": 0.0021646982503126387, "rouge1_recall": 0.3021070098062078, "rouge1_recall_stderr": 0.004505088335872746, "rouge2_fmeasure": 0.03904911931370361, "rouge2_fmeasure_stderr": 0.0014830525218956757, "rouge2_precision": 0.028309377178479218, "rouge2_precision_stderr": 0.0011164748559469404, "rouge2_recall": 0.06851024845447631, "rouge2_recall_stderr": 0.0026775539108549653, "rougeL_fmeasure": 0.14303319341608928, "rougeL_fmeasure_stderr": 0.0021220160049417853, "rougeL_precision": 0.10464417400111554, "rougeL_precision_stderr": 0.0017426786877401284, "rougeL_recall": 0.2455380323796214, "rougeL_recall_stderr": 0.003722345532650257, "rougeLsum_fmeasure": 0.13901962932381862, "rougeLsum_fmeasure_stderr": 0.002140626268901333, "rougeLsum_precision": 0.10170185371430301, "rougeLsum_precision_stderr": 0.001760814642264659, "rougeLsum_recall": 0.23909447163984915, "rougeLsum_recall_stderr": 0.0037550549904903216}}, "4": {"article_DOC_summary": {"bleu": 0.8494731376465096, "bleu_stderr": 0.15759913012237653, "rouge1_fmeasure": 0.049265793004777556, "rouge1_fmeasure_stderr": 0.0027540940646298335, "rouge1_precision": 0.044098357705247684, "rouge1_precision_stderr": 0.002947936975335653, "rouge1_recall": 0.07606084813555343, "rouge1_recall_stderr": 0.004337933086452851, "rouge2_fmeasure": 0.010722887449732417, "rouge2_fmeasure_stderr": 0.0009552037220813737, "rouge2_precision": 0.010194511397550707, "rouge2_precision_stderr": 0.0014805264810943113, "rouge2_recall": 0.01713730518568552, "rouge2_recall_stderr": 0.0015368918618672114, "rougeL_fmeasure": 0.039633473182401346, "rougeL_fmeasure_stderr": 0.0022076800838754865, "rougeL_precision": 0.036289652305464506, "rougeL_precision_stderr": 0.002595205368225138, "rougeL_recall": 0.06125010427741984, "rougeL_recall_stderr": 0.0035011808908862285, "rougeLsum_fmeasure": 0.039426934015668255, "rougeLsum_fmeasure_stderr": 0.002220814881451182, "rougeLsum_precision": 0.036220881484227876, "rougeLsum_precision_stderr": 0.0026089772559001233, "rougeLsum_recall": 0.06097365769946667, "rougeLsum_recall_stderr": 0.0035434576624889095}}, "5": {"article_DOC_summary": {"bleu": 4.572852757384441e-37, "bleu_stderr": 8.34242498549966e-32, "rouge1_fmeasure": 0.003121651270370141, "rouge1_fmeasure_stderr": 0.000904884711931905, "rouge1_precision": 0.0034796910548998868, "rouge1_precision_stderr": 0.0010310566863858106, "rouge1_recall": 0.003032491272466143, "rouge1_recall_stderr": 0.0008992364877230313, "rouge2_fmeasure": 0.0005993250623691804, "rouge2_fmeasure_stderr": 0.0002662375423658333, "rouge2_precision": 0.0006845648493817196, "rouge2_precision_stderr": 0.00029577448238137655, "rouge2_recall": 0.0005517517074120848, "rouge2_recall_stderr": 0.000253583231847424, "rougeL_fmeasure": 0.0023439628096121445, "rougeL_fmeasure_stderr": 0.0007012918571879311, "rougeL_precision": 0.002635557548227681, "rougeL_precision_stderr": 0.0008071763549733777, "rougeL_recall": 0.0022333458685090783, "rougeL_recall_stderr": 0.0006677775933364694, "rougeLsum_fmeasure": 0.002638144025655543, "rougeLsum_fmeasure_stderr": 0.0007785517533749153, "rougeLsum_precision": 0.002932835738490274, "rougeLsum_precision_stderr": 0.000884369578355545, "rougeLsum_recall": 0.0025885022906791634, "rougeLsum_recall_stderr": 0.0007930485746239223}}}}