File size: 27,970 Bytes
b0240cf
1
{"GEM/web_nlg_en": {"0": {"PALM_prompt": {"bleu": 0.3544571642681627, "bleu_stderr": 0.03407992444539609, "rouge1_fmeasure": 0.10020082045945918, "rouge1_fmeasure_stderr": 0.0019981291727618295, "rouge1_precision": 0.06761582940505043, "rouge1_precision_stderr": 0.001698628240993464, "rouge1_recall": 0.2835900568928793, "rouge1_recall_stderr": 0.0051423530685150995, "rouge2_fmeasure": 0.04533088635900367, "rouge2_fmeasure_stderr": 0.0011446673324507026, "rouge2_precision": 0.0298169184397825, "rouge2_precision_stderr": 0.0008893184105046417, "rouge2_recall": 0.1320847016852513, "rouge2_recall_stderr": 0.0030629028842595533, "rougeL_fmeasure": 0.09624293276078504, "rougeL_fmeasure_stderr": 0.001854737899845049, "rougeL_precision": 0.06475622065447084, "rougeL_precision_stderr": 0.001561020298095879, "rougeL_recall": 0.2752132257530675, "rougeL_recall_stderr": 0.004995344363048776, "rougeLsum_fmeasure": 0.09482991624917897, "rougeLsum_fmeasure_stderr": 0.00186076215487636, "rougeLsum_precision": 0.0640147635918145, "rougeLsum_precision_stderr": 0.001575258619523322, "rougeLsum_recall": 0.2681983425978889, "rougeLsum_recall_stderr": 0.004751089970308051}}, "1": {"PALM_prompt": {"bleu": 0.47989295807569715, "bleu_stderr": 0.0475397437178309, "rouge1_fmeasure": 0.14346476228827978, "rouge1_fmeasure_stderr": 0.0034815952103301458, "rouge1_precision": 0.11534724394991629, "rouge1_precision_stderr": 0.003827393590577779, "rouge1_recall": 0.3024780747165944, "rouge1_recall_stderr": 0.004967827146790581, "rouge2_fmeasure": 0.0707256674518147, "rouge2_fmeasure_stderr": 0.0022771008751978987, "rouge2_precision": 0.057998177860908384, "rouge2_precision_stderr": 0.0025743686817686295, "rouge2_recall": 0.15177356518097615, "rouge2_recall_stderr": 0.0034257177589283546, "rougeL_fmeasure": 0.13060275535305266, "rougeL_fmeasure_stderr": 0.0029918940675236053, "rougeL_precision": 0.10379078272811205, "rougeL_precision_stderr": 0.003315527005477984, "rougeL_recall": 0.28296523055686296, "rougeL_recall_stderr": 0.0045634431352543385, "rougeLsum_fmeasure": 0.13337871311137614, "rougeLsum_fmeasure_stderr": 0.0030768430402653476, "rougeLsum_precision": 0.10645036357421774, "rougeLsum_precision_stderr": 0.0034217554292272586, "rougeLsum_recall": 0.2866781623820036, "rougeLsum_recall_stderr": 0.0046215646233925805}}, "2": {"PALM_prompt": {"bleu": 0.666861601918144, "bleu_stderr": 0.026299047658385755, "rouge1_fmeasure": 0.17667190508199623, "rouge1_fmeasure_stderr": 0.00419053891681268, "rouge1_precision": 0.1547430839815294, "rouge1_precision_stderr": 0.004933321468949893, "rouge1_recall": 0.33478841436451773, "rouge1_recall_stderr": 0.005044795305603361, "rouge2_fmeasure": 0.09269395791934168, "rouge2_fmeasure_stderr": 0.002904096045529738, "rouge2_precision": 0.0836753208680069, "rouge2_precision_stderr": 0.0033827146122726165, "rouge2_recall": 0.17569109460452212, "rouge2_recall_stderr": 0.00376890003216499, "rougeL_fmeasure": 0.15988566101529644, "rougeL_fmeasure_stderr": 0.003641617023536087, "rougeL_precision": 0.13806190021996617, "rougeL_precision_stderr": 0.004291374157153462, "rougeL_recall": 0.31163920071713547, "rougeL_recall_stderr": 0.004598513995424206, "rougeLsum_fmeasure": 0.16376462584391532, "rougeLsum_fmeasure_stderr": 0.003764157053925168, "rougeLsum_precision": 0.14223938842195769, "rougeLsum_precision_stderr": 0.004446164564752725, "rougeLsum_recall": 0.31614503537746547, "rougeLsum_recall_stderr": 0.004685139330564806}}, "3": {"PALM_prompt": {"bleu": 0.7918596286549058, "bleu_stderr": 0.0505082941574267, "rouge1_fmeasure": 0.19582351163910977, "rouge1_fmeasure_stderr": 0.004516582135357114, "rouge1_precision": 0.17771262032081198, "rouge1_precision_stderr": 0.0054951572240111435, "rouge1_recall": 0.35311914964743174, "rouge1_recall_stderr": 0.005025197259419015, "rouge2_fmeasure": 0.10613152749319005, "rouge2_fmeasure_stderr": 0.0031819607620739436, "rouge2_precision": 0.10055990834825583, "rouge2_precision_stderr": 0.003908838679331289, "rouge2_recall": 0.18896553373557853, "rouge2_recall_stderr": 0.0038495013649217655, "rougeL_fmeasure": 0.1766613912727054, "rougeL_fmeasure_stderr": 0.003927425134752762, "rougeL_precision": 0.15835690076776687, "rougeL_precision_stderr": 0.004829192255619531, "rougeL_recall": 0.3282078865520143, "rougeL_recall_stderr": 0.004628481258729149, "rougeLsum_fmeasure": 0.18105604842604275, "rougeLsum_fmeasure_stderr": 0.004055025613896272, "rougeLsum_precision": 0.1631952722315149, "rougeLsum_precision_stderr": 0.005000959403714751, "rougeLsum_recall": 0.3330222709351221, "rougeLsum_recall_stderr": 0.00468575613523257}}, "4": {"PALM_prompt": {"bleu": 0.8540878153236116, "bleu_stderr": 0.04264209433083351, "rouge1_fmeasure": 0.19985774352152183, "rouge1_fmeasure_stderr": 0.004398277620735298, "rouge1_precision": 0.1824057188502487, "rouge1_precision_stderr": 0.005459901706601115, "rouge1_recall": 0.3648014741857513, "rouge1_recall_stderr": 0.004987141844898954, "rouge2_fmeasure": 0.10765686386731786, "rouge2_fmeasure_stderr": 0.0030775323292218954, "rouge2_precision": 0.10170190198280457, "rouge2_precision_stderr": 0.003802778312321268, "rouge2_recall": 0.1969832896256075, "rouge2_recall_stderr": 0.003898300177769583, "rougeL_fmeasure": 0.1790692812610404, "rougeL_fmeasure_stderr": 0.0037636080036965234, "rougeL_precision": 0.16138211318666076, "rougeL_precision_stderr": 0.004748850648521006, "rougeL_recall": 0.3387426515169364, "rougeL_recall_stderr": 0.004593853553959088, "rougeLsum_fmeasure": 0.18423836334787674, "rougeLsum_fmeasure_stderr": 0.003922969546378721, "rougeLsum_precision": 0.1672573483266801, "rougeLsum_precision_stderr": 0.0049642924071582155, "rougeLsum_recall": 0.34429093880762246, "rougeLsum_recall_stderr": 0.0046537632402660605}}, "5": {"PALM_prompt": {"bleu": 0.912001768808622, "bleu_stderr": 0.043254031735108306, "rouge1_fmeasure": 0.2092111019883349, "rouge1_fmeasure_stderr": 0.00460529861669814, "rouge1_precision": 0.19859783075889126, "rouge1_precision_stderr": 0.005919289804309579, "rouge1_recall": 0.36844512002888075, "rouge1_recall_stderr": 0.00505018826168294, "rouge2_fmeasure": 0.11687710078916223, "rouge2_fmeasure_stderr": 0.003314632884900664, "rouge2_precision": 0.11681205435376238, "rouge2_precision_stderr": 0.004339261455429453, "rouge2_recall": 0.20339458742529712, "rouge2_recall_stderr": 0.004013105858687102, "rougeL_fmeasure": 0.18815490160354775, "rougeL_fmeasure_stderr": 0.0039766285759192405, "rougeL_precision": 0.17708492516954327, "rougeL_precision_stderr": 0.005248751409406995, "rougeL_recall": 0.3425914027687954, "rougeL_recall_stderr": 0.004629793741986903, "rougeLsum_fmeasure": 0.19256627879558108, "rougeLsum_fmeasure_stderr": 0.004111657382117099, "rougeLsum_precision": 0.18241276096737613, "rougeLsum_precision_stderr": 0.0054404594348748435, "rougeLsum_recall": 0.3465669085097831, "rougeLsum_recall_stderr": 0.004652250039019875}}}, "GEM/wiki_lingua_en": {"0": {"tldr_en": {"bleu": 2.1294656115380315, "bleu_stderr": 0.08608373097383684, "rouge1_fmeasure": 0.1681539808990386, "rouge1_fmeasure_stderr": 0.0022516781432784135, "rouge1_precision": 0.15239310002995923, "rouge1_precision_stderr": 0.002438796263618738, "rouge1_recall": 0.23281616338419592, "rouge1_recall_stderr": 0.003153441505325274, "rouge2_fmeasure": 0.03664384349201909, "rouge2_fmeasure_stderr": 0.0009444852473193031, "rouge2_precision": 0.032362606343306115, "rouge2_precision_stderr": 0.0008736804306871456, "rouge2_recall": 0.05277290954431128, "rouge2_recall_stderr": 0.0015535207326358358, "rougeL_fmeasure": 0.13117374932151898, "rougeL_fmeasure_stderr": 0.0016522658265504455, "rougeL_precision": 0.11810199150971258, "rougeL_precision_stderr": 0.0018590591408895979, "rougeL_recall": 0.18586688913934518, "rougeL_recall_stderr": 0.002536111883086673, "rougeLsum_fmeasure": 0.15416461307042828, "rougeLsum_fmeasure_stderr": 0.0020767003871997682, "rougeLsum_precision": 0.13989462081303852, "rougeLsum_precision_stderr": 0.0022791670344911403, "rougeLsum_recall": 0.21404920648714998, "rougeLsum_recall_stderr": 0.0029316839033584957}}, "1": {"tldr_en": {"bleu": 3.6252694677393182, "bleu_stderr": 0.11516306057568679, "rouge1_fmeasure": 0.2114035653216517, "rouge1_fmeasure_stderr": 0.0023246773063628615, "rouge1_precision": 0.2751823879663153, "rouge1_precision_stderr": 0.003881996275772322, "rouge1_recall": 0.2346682268668015, "rouge1_recall_stderr": 0.0030480805010752515, "rouge2_fmeasure": 0.057131255472237095, "rouge2_fmeasure_stderr": 0.0014085125325758205, "rouge2_precision": 0.07953360723989537, "rouge2_precision_stderr": 0.0023704352619084283, "rouge2_recall": 0.062365192117877284, "rouge2_recall_stderr": 0.0016572329309161098, "rougeL_fmeasure": 0.16173018381687715, "rougeL_fmeasure_stderr": 0.0017896383598985555, "rougeL_precision": 0.2144299891910755, "rougeL_precision_stderr": 0.0032459302277197937, "rougeL_recall": 0.17984636106508087, "rougeL_recall_stderr": 0.002382783710665373, "rougeLsum_fmeasure": 0.1991087226604085, "rougeLsum_fmeasure_stderr": 0.002183402133872785, "rougeLsum_precision": 0.2602893534943804, "rougeLsum_precision_stderr": 0.0037273296754777798, "rougeLsum_recall": 0.22087932595278062, "rougeLsum_recall_stderr": 0.002865409410302555}}, "2": {"tldr_en": {"bleu": 4.294396830160884, "bleu_stderr": 0.10510562701376282, "rouge1_fmeasure": 0.2415919978553291, "rouge1_fmeasure_stderr": 0.002275465997227811, "rouge1_precision": 0.3427708550618383, "rouge1_precision_stderr": 0.0039616432661503925, "rouge1_recall": 0.24353092504463666, "rouge1_recall_stderr": 0.0028368108328522975, "rouge2_fmeasure": 0.07316494206446221, "rouge2_fmeasure_stderr": 0.0014908416636519638, "rouge2_precision": 0.10981242271190325, "rouge2_precision_stderr": 0.002600254579986533, "rouge2_recall": 0.07299604533557322, "rouge2_recall_stderr": 0.0016818837531280511, "rougeL_fmeasure": 0.18830499327024094, "rougeL_fmeasure_stderr": 0.0018262223394083703, "rougeL_precision": 0.27052380671481613, "rougeL_precision_stderr": 0.003342423060950019, "rougeL_recall": 0.18975380555144886, "rougeL_recall_stderr": 0.002272746335013426, "rougeLsum_fmeasure": 0.22838437822057972, "rougeLsum_fmeasure_stderr": 0.0021677295739195527, "rougeLsum_precision": 0.3252291175905201, "rougeLsum_precision_stderr": 0.003832831712454371, "rougeLsum_recall": 0.2296884650140397, "rougeLsum_recall_stderr": 0.00267247029974853}}, "3": {"tldr_en": {"bleu": 2.9094995439916813, "bleu_stderr": 0.1020505721496997, "rouge1_fmeasure": 0.20299844928550523, "rouge1_fmeasure_stderr": 0.002687864968532052, "rouge1_precision": 0.3073965000868567, "rouge1_precision_stderr": 0.004532668529568856, "rouge1_recall": 0.19614307988052224, "rouge1_recall_stderr": 0.003080191271460992, "rouge2_fmeasure": 0.061844393074462746, "rouge2_fmeasure_stderr": 0.0014810001971562478, "rouge2_precision": 0.10017130648615265, "rouge2_precision_stderr": 0.002776734778018214, "rouge2_recall": 0.059152151232302004, "rouge2_recall_stderr": 0.0016020020538619843, "rougeL_fmeasure": 0.16011928521487392, "rougeL_fmeasure_stderr": 0.0021479359283275963, "rougeL_precision": 0.24589394056510158, "rougeL_precision_stderr": 0.0038062820175439435, "rougeL_recall": 0.15441816724846275, "rougeL_recall_stderr": 0.0024515259341510915, "rougeLsum_fmeasure": 0.19201708263502876, "rougeLsum_fmeasure_stderr": 0.002552311917295444, "rougeLsum_precision": 0.2921779950267841, "rougeLsum_precision_stderr": 0.004374364347847452, "rougeLsum_recall": 0.18494595132044844, "rougeLsum_recall_stderr": 0.002894976936245908}}, "4": {"tldr_en": {"bleu": 0.0372391578969955, "bleu_stderr": 0.006245634047152133, "rouge1_fmeasure": 0.06515084313802752, "rouge1_fmeasure_stderr": 0.0023301601298560937, "rouge1_precision": 0.1006627719845332, "rouge1_precision_stderr": 0.00368234304942406, "rouge1_recall": 0.06278686240158242, "rouge1_recall_stderr": 0.002429866089129886, "rouge2_fmeasure": 0.019499194268273016, "rouge2_fmeasure_stderr": 0.0010427160072790155, "rouge2_precision": 0.0324786744467653, "rouge2_precision_stderr": 0.0019107387952160683, "rouge2_recall": 0.018895906029094554, "rouge2_recall_stderr": 0.0011271396066362587, "rougeL_fmeasure": 0.0523000871859911, "rougeL_fmeasure_stderr": 0.0018885969396611308, "rougeL_precision": 0.0823028370721046, "rougeL_precision_stderr": 0.0031051929375046153, "rougeL_recall": 0.05042051526784097, "rougeL_recall_stderr": 0.0019878366229883104, "rougeLsum_fmeasure": 0.06128900015472603, "rougeLsum_fmeasure_stderr": 0.002200644241627669, "rougeLsum_precision": 0.0954288017222706, "rougeLsum_precision_stderr": 0.0035264644632323466, "rougeLsum_recall": 0.05883979010675358, "rougeLsum_recall_stderr": 0.002281234737704665}}, "5": {"tldr_en": {"bleu": 5.89885644425285e-18, "bleu_stderr": 2.573727805263297e-15, "rouge1_fmeasure": 0.009841170717213035, "rouge1_fmeasure_stderr": 0.0009774207438938338, "rouge1_precision": 0.016979177640177374, "rouge1_precision_stderr": 0.0017468463524776949, "rouge1_recall": 0.00933120437657692, "rouge1_recall_stderr": 0.0010188132703681308, "rouge2_fmeasure": 0.0030060031859358545, "rouge2_fmeasure_stderr": 0.0004356120556552399, "rouge2_precision": 0.00576381210470867, "rouge2_precision_stderr": 0.0009504290775495337, "rouge2_recall": 0.0028734319831093366, "rouge2_recall_stderr": 0.0005018903996908588, "rougeL_fmeasure": 0.008154099496089815, "rougeL_fmeasure_stderr": 0.0008271752653321118, "rougeL_precision": 0.0144844872691487, "rougeL_precision_stderr": 0.00156210488273622, "rougeL_recall": 0.00773643445858647, "rougeL_recall_stderr": 0.0008732235538470538, "rougeLsum_fmeasure": 0.009454743941186122, "rougeLsum_fmeasure_stderr": 0.0009383005713490151, "rougeLsum_precision": 0.01642901756992128, "rougeLsum_precision_stderr": 0.0016976705166155568, "rougeLsum_recall": 0.00896493050335643, "rougeLsum_recall_stderr": 0.0009870511987772768}}}, "e2e_nlg_cleaned": {"0": {"generate_text_restaurant": {"bleu": 6.333542682337677, "bleu_stderr": 0.10726439979644425, "rouge1_fmeasure": 0.2920852729385422, "rouge1_fmeasure_stderr": 0.002585917559501568, "rouge1_precision": 0.29450049619552965, "rouge1_precision_stderr": 0.003103286443917978, "rouge1_recall": 0.3531232647714125, "rouge1_recall_stderr": 0.0034741713736329807, "rouge2_fmeasure": 0.11366020920928965, "rouge2_fmeasure_stderr": 0.0016797755141133139, "rouge2_precision": 0.10697543573411866, "rouge2_precision_stderr": 0.0017227291388967737, "rouge2_recall": 0.14277215373452296, "rouge2_recall_stderr": 0.002226911641687255, "rougeL_fmeasure": 0.23998550760843057, "rougeL_fmeasure_stderr": 0.001884083170727271, "rougeL_precision": 0.24140263089446137, "rougeL_precision_stderr": 0.0024270505962341814, "rougeL_recall": 0.2922338485900498, "rougeL_recall_stderr": 0.0026699862026011607, "rougeLsum_fmeasure": 0.2615141040307818, "rougeLsum_fmeasure_stderr": 0.002531253935486819, "rougeLsum_precision": 0.26084716441716366, "rougeLsum_precision_stderr": 0.0028038576941327303, "rougeLsum_recall": 0.31762402755219166, "rougeLsum_recall_stderr": 0.0033985728561216327}}, "1": {"generate_text_restaurant": {"bleu": 11.806297456970103, "bleu_stderr": 0.14551133253272594, "rouge1_fmeasure": 0.4697116660037698, "rouge1_fmeasure_stderr": 0.0023603969460476203, "rouge1_precision": 0.5669733154538599, "rouge1_precision_stderr": 0.003166104003686594, "rouge1_recall": 0.44018022577601473, "rouge1_recall_stderr": 0.0030630676874763485, "rouge2_fmeasure": 0.21840708978516402, "rouge2_fmeasure_stderr": 0.0020602369546148685, "rouge2_precision": 0.26656594919484183, "rouge2_precision_stderr": 0.0026339804527222587, "rouge2_recall": 0.20480027468494613, "rouge2_recall_stderr": 0.0022153423750415576, "rougeL_fmeasure": 0.33677921954756435, "rougeL_fmeasure_stderr": 0.0020664076993835057, "rougeL_precision": 0.40943221799438445, "rougeL_precision_stderr": 0.0028646547374588187, "rougeL_recall": 0.31460122768740206, "rougeL_recall_stderr": 0.002459245774729076, "rougeLsum_fmeasure": 0.380038908785806, "rougeLsum_fmeasure_stderr": 0.00234012651128036, "rougeLsum_precision": 0.45952493691536156, "rougeLsum_precision_stderr": 0.003085366813391384, "rougeLsum_recall": 0.35573040920519855, "rougeLsum_recall_stderr": 0.0027873440001945633}}, "2": {"generate_text_restaurant": {"bleu": 14.008929768185011, "bleu_stderr": 0.22440533336667637, "rouge1_fmeasure": 0.4993958738165169, "rouge1_fmeasure_stderr": 0.002296786336619267, "rouge1_precision": 0.597056411617577, "rouge1_precision_stderr": 0.0031639255878135267, "rouge1_recall": 0.4669271432097342, "rouge1_recall_stderr": 0.0029680675695804874, "rouge2_fmeasure": 0.24661876395459947, "rouge2_fmeasure_stderr": 0.0021262352052310984, "rouge2_precision": 0.29845711503191086, "rouge2_precision_stderr": 0.002761178182657989, "rouge2_recall": 0.23063537341826645, "rouge2_recall_stderr": 0.0022864554379483197, "rougeL_fmeasure": 0.36623753572761475, "rougeL_fmeasure_stderr": 0.002138032094317196, "rougeL_precision": 0.4403342175867495, "rougeL_precision_stderr": 0.0029750295481156285, "rougeL_recall": 0.34158773617015814, "rougeL_recall_stderr": 0.002503496159612652, "rougeLsum_fmeasure": 0.4135155622957521, "rougeLsum_fmeasure_stderr": 0.0023712145913602815, "rougeLsum_precision": 0.4951601294309332, "rougeLsum_precision_stderr": 0.0031807126472612607, "rougeLsum_recall": 0.38625888194917374, "rougeLsum_recall_stderr": 0.002796003413056854}}, "3": {"generate_text_restaurant": {"bleu": 15.105211182371182, "bleu_stderr": 0.18451933366555634, "rouge1_fmeasure": 0.5090805906068294, "rouge1_fmeasure_stderr": 0.0023041964520437996, "rouge1_precision": 0.6051917320726051, "rouge1_precision_stderr": 0.003186903545451817, "rouge1_recall": 0.4753181139650836, "rouge1_recall_stderr": 0.0029509453548170993, "rouge2_fmeasure": 0.2590847138395995, "rouge2_fmeasure_stderr": 0.002198161898886385, "rouge2_precision": 0.31111017436171656, "rouge2_precision_stderr": 0.00280736353534738, "rouge2_recall": 0.24213349104334048, "rouge2_recall_stderr": 0.0023696571519957635, "rougeL_fmeasure": 0.376176843640381, "rougeL_fmeasure_stderr": 0.0021978084264396066, "rougeL_precision": 0.449516766264704, "rougeL_precision_stderr": 0.0030507269243126643, "rougeL_recall": 0.35056364105111965, "rougeL_recall_stderr": 0.0025410208161535013, "rougeLsum_fmeasure": 0.42660489724977463, "rougeLsum_fmeasure_stderr": 0.002422704060549194, "rougeLsum_precision": 0.5074249964876819, "rougeLsum_precision_stderr": 0.003227079004477513, "rougeLsum_recall": 0.39822024067404677, "rougeLsum_recall_stderr": 0.0028309325845659074}}, "4": {"generate_text_restaurant": {"bleu": 15.474611986847089, "bleu_stderr": 0.14973216958042582, "rouge1_fmeasure": 0.5131026297255403, "rouge1_fmeasure_stderr": 0.0023318809968242366, "rouge1_precision": 0.6085558629612119, "rouge1_precision_stderr": 0.0032072518394225774, "rouge1_recall": 0.47700323449919174, "rouge1_recall_stderr": 0.002886159999148568, "rouge2_fmeasure": 0.26342970509252306, "rouge2_fmeasure_stderr": 0.0022326066051085933, "rouge2_precision": 0.3159128148862684, "rouge2_precision_stderr": 0.002852006737172459, "rouge2_recall": 0.24477002962445538, "rouge2_recall_stderr": 0.0023552807653690055, "rougeL_fmeasure": 0.380814583402722, "rougeL_fmeasure_stderr": 0.0022426618892846866, "rougeL_precision": 0.45306373160845365, "rougeL_precision_stderr": 0.003027837117034534, "rougeL_recall": 0.3537262109331126, "rougeL_recall_stderr": 0.0025437784350140404, "rougeLsum_fmeasure": 0.4326211658968149, "rougeLsum_fmeasure_stderr": 0.002460044931103608, "rougeLsum_precision": 0.5130870759871387, "rougeLsum_precision_stderr": 0.0032394064012829364, "rougeLsum_recall": 0.40218523134077677, "rougeLsum_recall_stderr": 0.0028079212152934013}}, "5": {"generate_text_restaurant": {"bleu": 15.682367116615334, "bleu_stderr": 0.25213559215306164, "rouge1_fmeasure": 0.5145966431967747, "rouge1_fmeasure_stderr": 0.0022816662119259, "rouge1_precision": 0.6058475533177261, "rouge1_precision_stderr": 0.0031740863555628556, "rouge1_recall": 0.4800148399689924, "rouge1_recall_stderr": 0.002825932845056274, "rouge2_fmeasure": 0.265260656307001, "rouge2_fmeasure_stderr": 0.002214043917610533, "rouge2_precision": 0.31623066797668453, "rouge2_precision_stderr": 0.0028462039844017895, "rouge2_recall": 0.24702364656456957, "rouge2_recall_stderr": 0.0023166256664731376, "rougeL_fmeasure": 0.3813026321038327, "rougeL_fmeasure_stderr": 0.0022157680630405245, "rougeL_precision": 0.4504141035870135, "rougeL_precision_stderr": 0.0030013926360521865, "rougeL_recall": 0.3552692730806331, "rougeL_recall_stderr": 0.0025020557665565548, "rougeLsum_fmeasure": 0.43506423120687865, "rougeLsum_fmeasure_stderr": 0.002423656341895589, "rougeLsum_precision": 0.512482274282817, "rougeLsum_precision_stderr": 0.0032133729386090016, "rougeLsum_recall": 0.4057631051784554, "rougeLsum_recall_stderr": 0.0027687632042124708}}}, "gem_xsum": {"0": {"article_DOC_summary": {"bleu": 2.018881442853279, "bleu_stderr": 0.1198347060919623, "rouge1_fmeasure": 0.2153075569633584, "rouge1_fmeasure_stderr": 0.0027773199670098106, "rouge1_precision": 0.1569943914968631, "rouge1_precision_stderr": 0.0021655546132824436, "rouge1_recall": 0.36095324775264914, "rouge1_recall_stderr": 0.004668719577415661, "rouge2_fmeasure": 0.05104998297888022, "rouge2_fmeasure_stderr": 0.0015800598536466126, "rouge2_precision": 0.03708686838166038, "rouge2_precision_stderr": 0.0012602221441622482, "rouge2_recall": 0.08846965963220199, "rouge2_recall_stderr": 0.00283080199253979, "rougeL_fmeasure": 0.15509756403131228, "rougeL_fmeasure_stderr": 0.0020293672794457597, "rougeL_precision": 0.11303186631574795, "rougeL_precision_stderr": 0.0016203168039502166, "rougeL_recall": 0.26188641959340075, "rougeL_recall_stderr": 0.003589938071974499, "rougeLsum_fmeasure": 0.1703530812291028, "rougeLsum_fmeasure_stderr": 0.0023104790446865997, "rougeLsum_precision": 0.12408813760298806, "rougeLsum_precision_stderr": 0.0018120535311226468, "rougeLsum_recall": 0.2872247357242771, "rougeLsum_recall_stderr": 0.004029862587537261}}, "1": {"article_DOC_summary": {"bleu": 1.8858887147145498, "bleu_stderr": 0.14401168622655466, "rouge1_fmeasure": 0.20505806920550534, "rouge1_fmeasure_stderr": 0.0032842375202117528, "rouge1_precision": 0.20579494303326157, "rouge1_precision_stderr": 0.004051163060208727, "rouge1_recall": 0.24161408729335127, "rouge1_recall_stderr": 0.0038629846635870923, "rouge2_fmeasure": 0.041503622574202585, "rouge2_fmeasure_stderr": 0.0019316323685802709, "rouge2_precision": 0.04302422220208535, "rouge2_precision_stderr": 0.0022086413426371967, "rouge2_recall": 0.04740997367205154, "rouge2_recall_stderr": 0.00213449836929217, "rougeL_fmeasure": 0.15474973660621036, "rougeL_fmeasure_stderr": 0.0024910059328029795, "rougeL_precision": 0.155249768985157, "rougeL_precision_stderr": 0.0031065288103969873, "rougeL_recall": 0.18302318903854045, "rougeL_recall_stderr": 0.0029523933556650545, "rougeLsum_fmeasure": 0.1576172218419311, "rougeLsum_fmeasure_stderr": 0.0025371395589236932, "rougeLsum_precision": 0.15741153110570363, "rougeLsum_precision_stderr": 0.0031082667915430405, "rougeLsum_recall": 0.18784045795172838, "rougeLsum_recall_stderr": 0.003159463678885708}}, "2": {"article_DOC_summary": {"bleu": 2.2458789198162017, "bleu_stderr": 0.1742473110428736, "rouge1_fmeasure": 0.22078072361061904, "rouge1_fmeasure_stderr": 0.003334382844575592, "rouge1_precision": 0.22569787787241932, "rouge1_precision_stderr": 0.004125302870311216, "rouge1_recall": 0.24825517453863355, "rouge1_recall_stderr": 0.0037122286921001967, "rouge2_fmeasure": 0.04934524005211476, "rouge2_fmeasure_stderr": 0.002100138042584609, "rouge2_precision": 0.05192675145501797, "rouge2_precision_stderr": 0.0023645411876905063, "rouge2_recall": 0.05351390792594154, "rouge2_recall_stderr": 0.002216269112397534, "rougeL_fmeasure": 0.16774207141216832, "rougeL_fmeasure_stderr": 0.002691419016293324, "rougeL_precision": 0.17160827341192383, "rougeL_precision_stderr": 0.0033267002849613177, "rougeL_recall": 0.1887814116454046, "rougeL_recall_stderr": 0.002953788514567365, "rougeLsum_fmeasure": 0.17009783088315292, "rougeLsum_fmeasure_stderr": 0.002696769898546311, "rougeLsum_precision": 0.17340733922548357, "rougeLsum_precision_stderr": 0.003311231497456564, "rougeLsum_recall": 0.19262857796948832, "rougeLsum_recall_stderr": 0.003071618374246459}}, "3": {"article_DOC_summary": {"bleu": 2.409483529873289, "bleu_stderr": 0.18624352036745506, "rouge1_fmeasure": 0.21169375438699195, "rouge1_fmeasure_stderr": 0.0036769584663103264, "rouge1_precision": 0.22042725300280533, "rouge1_precision_stderr": 0.004337361685140243, "rouge1_recall": 0.2304513543151878, "rouge1_recall_stderr": 0.0039858349476740084, "rouge2_fmeasure": 0.047001131672013766, "rouge2_fmeasure_stderr": 0.002098938383869797, "rouge2_precision": 0.0493940240244741, "rouge2_precision_stderr": 0.0023545425488460964, "rouge2_recall": 0.050316504605654816, "rouge2_recall_stderr": 0.002169331811953602, "rougeL_fmeasure": 0.1606547287936503, "rougeL_fmeasure_stderr": 0.0029102503972058716, "rougeL_precision": 0.1678584231793303, "rougeL_precision_stderr": 0.0035036978381175823, "rougeL_recall": 0.1752875336790613, "rougeL_recall_stderr": 0.003140466954264108, "rougeLsum_fmeasure": 0.1629790699497271, "rougeLsum_fmeasure_stderr": 0.0029227535963180563, "rougeLsum_precision": 0.1698133729917698, "rougeLsum_precision_stderr": 0.0034978460193711204, "rougeLsum_recall": 0.1786035650942303, "rougeLsum_recall_stderr": 0.0032260778602228465}}, "4": {"article_DOC_summary": {"bleu": 0.18746323959602532, "bleu_stderr": 0.054417035919397665, "rouge1_fmeasure": 0.05852312292259964, "rouge1_fmeasure_stderr": 0.003411745135977311, "rouge1_precision": 0.07074969836542556, "rouge1_precision_stderr": 0.004374846930886093, "rouge1_recall": 0.05935148359227344, "rouge1_recall_stderr": 0.0035290460576690463, "rouge2_fmeasure": 0.014128424244693396, "rouge2_fmeasure_stderr": 0.001372131743832138, "rouge2_precision": 0.017451535244963366, "rouge2_precision_stderr": 0.0018970209619056206, "rouge2_recall": 0.013916749485762063, "rouge2_recall_stderr": 0.0013341269055275502, "rougeL_fmeasure": 0.04473715844771224, "rougeL_fmeasure_stderr": 0.002669461412700664, "rougeL_precision": 0.05499178642750529, "rougeL_precision_stderr": 0.003534909374730744, "rougeL_recall": 0.04518795012564015, "rougeL_recall_stderr": 0.0027283021035140226, "rougeLsum_fmeasure": 0.045274962805013225, "rougeLsum_fmeasure_stderr": 0.002694404061113344, "rougeLsum_precision": 0.05547251868043394, "rougeLsum_precision_stderr": 0.0035488908061919494, "rougeLsum_recall": 0.045982840052559225, "rougeLsum_recall_stderr": 0.002791306716270555}}, "5": {"article_DOC_summary": {"bleu": 8.822788855803002e-48, "bleu_stderr": 1.2895291827584802e-40, "rouge1_fmeasure": 0.0023248125380148903, "rouge1_fmeasure_stderr": 0.0007115633852660155, "rouge1_precision": 0.0034544238838444107, "rouge1_precision_stderr": 0.0010758816471093306, "rouge1_recall": 0.001915294823020827, "rouge1_recall_stderr": 0.0005795152691274384, "rouge2_fmeasure": 0.0003328471473444539, "rouge2_fmeasure_stderr": 0.00015760010881621698, "rouge2_precision": 0.0006244865012900529, "rouge2_precision_stderr": 0.00030583312965056826, "rouge2_recall": 0.0002459647270968026, "rouge2_recall_stderr": 0.00011885497758694596, "rougeL_fmeasure": 0.0018202630319951564, "rougeL_fmeasure_stderr": 0.0005323287142674903, "rougeL_precision": 0.002672449885242423, "rougeL_precision_stderr": 0.000805779683887303, "rougeL_recall": 0.0015212204792498286, "rougeL_recall_stderr": 0.0004379233657056629, "rougeLsum_fmeasure": 0.001866621568919731, "rougeLsum_fmeasure_stderr": 0.000538219309246783, "rougeLsum_precision": 0.0027228988813074017, "rougeLsum_precision_stderr": 0.0008103635709126659, "rougeLsum_recall": 0.00156410212590506, "rougeLsum_recall_stderr": 0.0004440546710373052}}}}