diff options
Diffstat (limited to 'fine_tune/bert/tutorials')
| -rw-r--r-- | fine_tune/bert/tutorials/03_bert_input_embedding.py | 4 | ||||
| -rw-r--r-- | fine_tune/bert/tutorials/04_subword_wordpiece_tokenizer.ipynb | 6115 |
2 files changed, 6116 insertions, 3 deletions
diff --git a/fine_tune/bert/tutorials/03_bert_input_embedding.py b/fine_tune/bert/tutorials/03_bert_input_embedding.py index 7a58db3..95da9ef 100644 --- a/fine_tune/bert/tutorials/03_bert_input_embedding.py +++ b/fine_tune/bert/tutorials/03_bert_input_embedding.py @@ -17,6 +17,4 @@ model_input = tokenizer(test_sent, return_tensors='pt') model.eval() with torch.no_grad(): - output = model(**model_input) - -nn.MultiheadAttention
\ No newline at end of file + output = model(**model_input)
\ No newline at end of file diff --git a/fine_tune/bert/tutorials/04_subword_wordpiece_tokenizer.ipynb b/fine_tune/bert/tutorials/04_subword_wordpiece_tokenizer.ipynb new file mode 100644 index 0000000..b86f5a7 --- /dev/null +++ b/fine_tune/bert/tutorials/04_subword_wordpiece_tokenizer.ipynb @@ -0,0 +1,6115 @@ +{ + "cells": [ + { + "cell_type": "code", + "execution_count": 29, + "metadata": { + "ExecuteTime": { + "end_time": "2022-07-09T02:48:50.247468Z", + "start_time": "2022-07-09T02:48:50.244431Z" + } + }, + "outputs": [], + "source": [ + "s1 = 'albums sold 124443286539 copies'\n", + "s2 = 'technically perfect, melodically correct'\n", + "s3 = 'featuring a previously unheard track'\n", + "s4 = 'bestselling music artist'\n", + "s5 = 's1 d1 o1 and o2'\n", + "s6 = 'asbofwheohwbeif'" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "ExecuteTime": { + "end_time": "2022-07-09T02:28:16.211451Z", + "start_time": "2022-07-09T02:28:16.209738Z" + } + }, + "source": [ + "### 0. 实例化 tokenizer" + ] + }, + { + "cell_type": "code", + "execution_count": 1, + "metadata": { + "ExecuteTime": { + "end_time": "2022-07-09T02:42:32.975723Z", + "start_time": "2022-07-09T02:42:25.656501Z" + } + }, + "outputs": [], + "source": [ + "from transformers import BertTokenizer" + ] + }, + { + "cell_type": "code", + "execution_count": 2, + "metadata": { + "ExecuteTime": { + "end_time": "2022-07-09T02:42:42.052968Z", + "start_time": "2022-07-09T02:42:34.071473Z" + } + }, + "outputs": [], + "source": [ + "model_name = 'bert-base-uncased'\n", + "tokenizer = BertTokenizer.from_pretrained(model_name)" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### 1. vocab" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "- tokenizer.vocab vs. tokenizer.ids_to_tokens\n", + "- len(tokenizer.vocab) == 30522" + ] + }, + { + "cell_type": "code", + "execution_count": 7, + "metadata": { + "ExecuteTime": { + "end_time": "2022-07-09T02:43:53.672683Z", + "start_time": "2022-07-09T02:43:53.670232Z" + } + }, + "outputs": [], + "source": [ + "# tokenizer.vocab\n", + "# tokenizer.ids_to_tokens" + ] + }, + { + "cell_type": "code", + "execution_count": 5, + "metadata": { + "ExecuteTime": { + "end_time": "2022-07-09T02:43:27.055307Z", + "start_time": "2022-07-09T02:43:27.050585Z" + } + }, + "outputs": [ + { + "data": { + "text/plain": [ + "30522" + ] + }, + "execution_count": 5, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "len(tokenizer.vocab)" + ] + }, + { + "cell_type": "code", + "execution_count": 6, + "metadata": { + "ExecuteTime": { + "end_time": "2022-07-09T02:43:35.493500Z", + "start_time": "2022-07-09T02:43:35.489465Z" + }, + "scrolled": true + }, + "outputs": [ + { + "data": { + "text/plain": [ + "100" + ] + }, + "execution_count": 6, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "tokenizer.vocab['[UNK]']" + ] + }, + { + "cell_type": "code", + "execution_count": 25, + "metadata": { + "ExecuteTime": { + "end_time": "2022-07-09T02:48:01.375569Z", + "start_time": "2022-07-09T02:48:01.371231Z" + } + }, + "outputs": [ + { + "data": { + "text/plain": [ + "['best', '##sell', '##ing']" + ] + }, + "execution_count": 25, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "tokenizer.tokenize('bestselling')" + ] + }, + { + "cell_type": "code", + "execution_count": 35, + "metadata": { + "ExecuteTime": { + "end_time": "2022-07-09T02:51:31.053715Z", + "start_time": "2022-07-09T02:51:30.100811Z" + } + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "##s\n", + "##a\n", + "##e\n", + "##i\n", + "##ing\n", + "##n\n", + "##o\n", + "##d\n", + "##ed\n", + "##r\n", + "##y\n", + "##t\n", + "##er\n", + "##ly\n", + "##l\n", + "##m\n", + "##u\n", + "##es\n", + "##h\n", + "##on\n", + "##k\n", + "##us\n", + "##c\n", + "##g\n", + "##an\n", + "##p\n", + "##en\n", + "##in\n", + "##man\n", + "##al\n", + "##ia\n", + "##2\n", + "##z\n", + "##is\n", + "##1\n", + "##b\n", + "##3\n", + "##ra\n", + "##na\n", + "##ers\n", + "##f\n", + "##4\n", + "##le\n", + "##6\n", + "##7\n", + "##ic\n", + "##x\n", + "##v\n", + "##te\n", + "##8\n", + "##5\n", + "##ne\n", + "##ie\n", + "##ton\n", + "##9\n", + "##0\n", + "##ta\n", + "##th\n", + "##la\n", + "##ness\n", + "##ch\n", + "##um\n", + "##da\n", + "##ry\n", + "##w\n", + "##ma\n", + "##rs\n", + "##el\n", + "##re\n", + "##os\n", + "##ar\n", + "##ka\n", + "##ist\n", + "##ian\n", + "##or\n", + "##ism\n", + "##ling\n", + "##ity\n", + "##as\n", + "##ley\n", + "##ted\n", + "##ng\n", + "##ville\n", + "##able\n", + "##ri\n", + "##ies\n", + "##land\n", + "##ur\n", + "##ya\n", + "##ine\n", + "##de\n", + "##ki\n", + "##ts\n", + "##ro\n", + "##less\n", + "##ey\n", + "##ion\n", + "##ha\n", + "##am\n", + "##ter\n", + "##ge\n", + "##ll\n", + "##se\n", + "##st\n", + "##ation\n", + "##nt\n", + "##son\n", + "##et\n", + "##ce\n", + "##to\n", + "##ting\n", + "##ble\n", + "##ke\n", + "##ni\n", + "##j\n", + "##tion\n", + "##ham\n", + "##ive\n", + "##do\n", + "##ca\n", + "##men\n", + "##ized\n", + "##ous\n", + "##va\n", + "##id\n", + "##co\n", + "##ck\n", + "##ns\n", + "##no\n", + "##ga\n", + "##li\n", + "##ment\n", + "##ba\n", + "##ner\n", + "##ko\n", + "##ate\n", + "##io\n", + "##wood\n", + "##led\n", + "##ty\n", + "##ve\n", + "##sa\n", + "##by\n", + "##ier\n", + "##ti\n", + "##field\n", + "##ford\n", + "##ja\n", + "##ler\n", + "##ally\n", + "##ina\n", + "##ization\n", + "##ful\n", + "##go\n", + "##il\n", + "##at\n", + "##hi\n", + "##berg\n", + "##der\n", + "##sh\n", + "##rd\n", + "##lin\n", + "##lo\n", + "##ot\n", + "##za\n", + "##q\n", + "##me\n", + "##ius\n", + "##line\n", + "##den\n", + "##it\n", + "##wa\n", + "##ad\n", + "##ite\n", + "##que\n", + "##ard\n", + "##les\n", + "##ff\n", + "##tor\n", + "##age\n", + "##di\n", + "##ir\n", + "##mi\n", + "##est\n", + "##ria\n", + "##ze\n", + "##well\n", + "##ated\n", + "##ee\n", + "##ah\n", + "##ji\n", + "##ov\n", + "##pa\n", + "##ish\n", + "##ps\n", + "##tes\n", + "##lla\n", + "##way\n", + "##house\n", + "##tic\n", + "##ger\n", + "##un\n", + "##ant\n", + "##burg\n", + "##ura\n", + "##town\n", + "##ding\n", + "##tte\n", + "##ping\n", + "##ize\n", + "##ay\n", + "##ging\n", + "##ol\n", + "##ss\n", + "##ent\n", + "##tt\n", + "##be\n", + "##ky\n", + "##ak\n", + "##ial\n", + "##han\n", + "##per\n", + "##nd\n", + "##ls\n", + "##ai\n", + "##au\n", + "##ny\n", + "##ring\n", + "##ut\n", + "##bury\n", + "##kin\n", + "##ron\n", + "##head\n", + "##ow\n", + "##ium\n", + "##mer\n", + "##pe\n", + "##sen\n", + "##ong\n", + "##ised\n", + "##bo\n", + "##ds\n", + "##ists\n", + "##ries\n", + "##dy\n", + "##ana\n", + "##worth\n", + "##ide\n", + "##ea\n", + "##ms\n", + "##nes\n", + "##don\n", + "##ku\n", + "##gan\n", + "##mo\n", + "##pur\n", + "##ul\n", + "##si\n", + "##rt\n", + "##ell\n", + "##om\n", + "##he\n", + "##ure\n", + "##ara\n", + "##che\n", + "##ney\n", + "##zed\n", + "##chi\n", + "##ik\n", + "##ker\n", + "##ski\n", + "##ini\n", + "##ran\n", + "##tone\n", + "##ica\n", + "##jo\n", + "##ise\n", + "##ung\n", + "##ning\n", + "##red\n", + "##ux\n", + "##gh\n", + "##hip\n", + "##gs\n", + "##dale\n", + "##bi\n", + "##one\n", + "##ons\n", + "##ary\n", + "##ang\n", + "##ue\n", + "##cy\n", + "##ors\n", + "##ped\n", + "##ber\n", + "##and\n", + "##ore\n", + "##ks\n", + "##im\n", + "##ded\n", + "##vi\n", + "##ino\n", + "##tz\n", + "##tan\n", + "##lan\n", + "##mann\n", + "##tus\n", + "##zi\n", + "##out\n", + "##ating\n", + "##gi\n", + "##gate\n", + "##sky\n", + "##water\n", + "##her\n", + "##nce\n", + "##bs\n", + "##ek\n", + "##tta\n", + "##back\n", + "##more\n", + "##ged\n", + "##tive\n", + "##izing\n", + "##ola\n", + "##yn\n", + "##res\n", + "##idae\n", + "##cing\n", + "##ens\n", + "##ii\n", + "##des\n", + "##cs\n", + "##shi\n", + "##sis\n", + "##work\n", + "##ft\n", + "##nia\n", + "##van\n", + "##lle\n", + "##ster\n", + "##board\n", + "##up\n", + "##zer\n", + "##gy\n", + "##ver\n", + "##ac\n", + "##ious\n", + "##bly\n", + "##ied\n", + "##su\n", + "##vin\n", + "##bridge\n", + "##ld\n", + "##port\n", + "##ram\n", + "##ities\n", + "##ving\n", + "##je\n", + "##logy\n", + "##sm\n", + "##tra\n", + "##so\n", + "##sy\n", + "##ora\n", + "##ten\n", + "##istic\n", + "##ics\n", + "##ok\n", + "##ming\n", + "##ett\n", + "##ily\n", + "##ita\n", + "##tors\n", + "##ct\n", + "##ice\n", + "##lia\n", + "##em\n", + "##isation\n", + "##ance\n", + "##rin\n", + "##ye\n", + "##kar\n", + "##ened\n", + "##ae\n", + "##ua\n", + "##sk\n", + "##ano\n", + "##vo\n", + "##zing\n", + "##ach\n", + "##ev\n", + "##ology\n", + "##ud\n", + "##ata\n", + "##ick\n", + "##ho\n", + "##ese\n", + "##ru\n", + "##rum\n", + "##rn\n", + "##king\n", + "##gar\n", + "##zo\n", + "##ered\n", + "##lis\n", + "##dae\n", + "##rian\n", + "##po\n", + "##lli\n", + "##ci\n", + "##era\n", + "##gen\n", + "##tti\n", + "##sed\n", + "##ris\n", + "##ves\n", + "##ans\n", + "##uk\n", + "##oy\n", + "##hu\n", + "##fa\n", + "##ible\n", + "##ich\n", + "##yan\n", + "##tory\n", + "##ians\n", + "##ula\n", + "##ins\n", + "##ani\n", + "##sson\n", + "##lt\n", + "##hill\n", + "##ova\n", + "##ston\n", + "##ao\n", + "##light\n", + "##ou\n", + "##net\n", + "##llo\n", + "##ved\n", + "##wick\n", + "##ned\n", + "##nan\n", + "##ane\n", + "##off\n", + "##dra\n", + "##ys\n", + "##ric\n", + "##time\n", + "##hn\n", + "##ery\n", + "##tis\n", + "##hl\n", + "##pers\n", + "##ros\n", + "##op\n", + "##side\n", + "##ties\n", + "##rie\n", + "##sha\n", + "##mm\n", + "##ball\n", + "##ren\n", + "##lus\n", + "##cia\n", + "##ening\n", + "##ique\n", + "##ei\n", + "##shire\n", + "##ock\n", + "##ire\n", + "##gon\n", + "##wan\n", + "##cher\n", + "##ical\n", + "##let\n", + "##cha\n", + "##fer\n", + "##ken\n", + "##fish\n", + "##ction\n", + "##ika\n", + "##tar\n", + "##med\n", + "##ette\n", + "##mus\n", + "##ites\n", + "##tin\n", + "##lu\n", + "##ix\n", + "##ward\n", + "##dar\n", + "##nts\n", + "##yo\n", + "##py\n", + "##ched\n", + "##bach\n", + "##down\n", + "##fully\n", + "##mic\n", + "##od\n", + "##kov\n", + "##ivity\n", + "##°\n", + "##sing\n", + "##ters\n", + "##len\n", + "##ified\n", + "##lon\n", + "##oon\n", + "##mes\n", + "##over\n", + "##dan\n", + "##mar\n", + "##ington\n", + "##ona\n", + "##ere\n", + "##cus\n", + "##ab\n", + "##lock\n", + "##ira\n", + "##hs\n", + "##vic\n", + "##ala\n", + "##tre\n", + "##ular\n", + "##ral\n", + "##rus\n", + "##ias\n", + "##sey\n", + "##fe\n", + "##wn\n", + "##ess\n", + "##ew\n", + "##dor\n", + "##ering\n", + "##sley\n", + "##ig\n", + "##ability\n", + "##lar\n", + "##burn\n", + "##rk\n", + "##my\n", + "##nie\n", + "##ser\n", + "##heim\n", + "##ware\n", + "##ama\n", + "##ative\n", + "##pin\n", + "##hr\n", + "##all\n", + "##ain\n", + "##ked\n", + "##feld\n", + "##ration\n", + "##ven\n", + "##our\n", + "##ments\n", + "##har\n", + "##ras\n", + "##ena\n", + "##ban\n", + "##pi\n", + "##mon\n", + "##₂\n", + "##ably\n", + "##bar\n", + "##nik\n", + "##low\n", + "##bed\n", + "##bus\n", + "##bert\n", + "##ress\n", + "##tha\n", + "##ska\n", + "##ches\n", + "##point\n", + "##jan\n", + "##ella\n", + "##bin\n", + "##art\n", + "##ada\n", + "##ges\n", + "##ching\n", + "##ets\n", + "##ph\n", + "##ome\n", + "##sia\n", + "##lay\n", + "##ari\n", + "##ag\n", + "##ions\n", + "##yl\n", + "##ates\n", + "##las\n", + "##ida\n", + "##tu\n", + "##ax\n", + "##non\n", + "##we\n", + "##ord\n", + "##bility\n", + "##use\n", + "##du\n", + "##bu\n", + "##maker\n", + "##ses\n", + "##view\n", + "##mate\n", + "##ec\n", + "##ill\n", + "##stein\n", + "##rat\n", + "##ings\n", + "##ides\n", + "##ene\n", + "##und\n", + "##og\n", + "##lands\n", + "##book\n", + "##chen\n", + "##ologist\n", + "##con\n", + "##bel\n", + "##ack\n", + "##master\n", + "##nic\n", + "##iya\n", + "##din\n", + "##mp\n", + "##ert\n", + "##hon\n", + "##lie\n", + "##ify\n", + "##box\n", + "##eo\n", + "##ual\n", + "##san\n", + "##osa\n", + "##itz\n", + "##ator\n", + "##hal\n", + "##fi\n", + "##das\n", + "##00\n", + "##ulated\n", + "##oe\n", + "##uous\n", + "##ith\n", + "##nda\n", + "##nk\n", + "##ugh\n", + "##nis\n", + "##aki\n", + "##ath\n", + "##bird\n", + "##com\n", + "##ien\n", + "##hood\n", + "##bad\n", + "##war\n", + "##ification\n", + "##dia\n", + "##via\n", + "##xi\n", + "##els\n", + "##zar\n", + "##mal\n", + "##ceae\n", + "##hed\n", + "##gue\n", + "##tal\n", + "##nell\n", + "##zy\n", + "##cker\n", + "##ju\n", + "##kan\n", + "##ovic\n", + "##wi\n", + "##sta\n", + "##tv\n", + "##lly\n", + "##stone\n", + "##ose\n", + "##urs\n", + "##cies\n", + "##del\n", + "##rated\n", + "##iel\n", + "##zation\n", + "##tto\n", + "##tions\n", + "##tle\n", + "##cal\n", + "##bank\n", + "##dal\n", + "##ule\n", + "##oid\n", + "##works\n", + "##nation\n", + "##wing\n", + "##ap\n", + "##ws\n", + "##mas\n", + "##can\n", + "##sville\n", + "##ez\n", + "##gle\n", + "##ising\n", + "##sco\n", + "##ado\n", + "##illa\n", + "##pp\n", + "##ncy\n", + "##ridge\n", + "##ray\n", + "##ale\n", + "##ile\n", + "##cc\n", + "##rio\n", + "##uri\n", + "##away\n", + "##ulation\n", + "##tie\n", + "##nna\n", + "##una\n", + "##dom\n", + "##oo\n", + "##ima\n", + "##tein\n", + "##ces\n", + "##oma\n", + "##wall\n", + "##mont\n", + "##lyn\n", + "##ade\n", + "##ship\n", + "##yne\n", + "##kes\n", + "##shan\n", + "##orn\n", + "##gal\n", + "##sburg\n", + "##brook\n", + "##bling\n", + "##iro\n", + "##pm\n", + "##pan\n", + "##zu\n", + "##berry\n", + "##horn\n", + "##als\n", + "##zhou\n", + "##cio\n", + "##une\n", + "##bc\n", + "##ids\n", + "##hus\n", + "##tel\n", + "##mie\n", + "##list\n", + "##phone\n", + "##ulate\n", + "##ography\n", + "##ole\n", + "##hall\n", + "##cho\n", + "##ree\n", + "##ensis\n", + "##inger\n", + "##esh\n", + "##room\n", + "##ito\n", + "##iness\n", + "##logical\n", + "##car\n", + "##min\n", + "##kh\n", + "##bra\n", + "##ori\n", + "##long\n", + "##ois\n", + "##izes\n", + "##stic\n", + "##oc\n", + "##nne\n", + "##ological\n", + "##mia\n", + "##win\n", + "##nte\n", + "##ence\n", + "##if\n", + "##iers\n", + "##yi\n", + "##cht\n", + "##woman\n", + "##val\n", + "##gne\n", + "##ui\n", + "##nus\n", + "##tine\n", + "##mel\n", + "##eau\n", + "##hen\n", + "##nen\n", + "##tas\n", + "##borough\n", + "##eon\n", + "##ode\n", + "##ory\n", + "##fl\n", + "##day\n", + "##а\n", + "##bal\n", + "##die\n", + "##lf\n", + "##fire\n", + "##lam\n", + "##born\n", + "##ees\n", + "##sar\n", + "##ex\n", + "##bb\n", + "##и\n", + "##fs\n", + "##wski\n", + "##af\n", + "##like\n", + "##dle\n", + "##fold\n", + "##pes\n", + "##aw\n", + "##usa\n", + "##rah\n", + "##lic\n", + "##craft\n", + "##ute\n", + "##tsu\n", + "##zen\n", + "##gia\n", + "##oa\n", + "##cion\n", + "##oi\n", + "##ati\n", + "##fied\n", + "##iest\n", + "##aro\n", + "##bing\n", + "##los\n", + "##ille\n", + "##illo\n", + "##end\n", + "##hurst\n", + "##yu\n", + "##dis\n", + "##row\n", + "##cast\n", + "##yer\n", + "##hy\n", + "##abad\n", + "##lee\n", + "##ela\n", + "##ines\n", + "##ough\n", + "##eus\n", + "##cks\n", + "##hin\n", + "##ben\n", + "##ato\n", + "##rg\n", + "##ero\n", + "##lor\n", + "##ami\n", + "##tch\n", + "##mark\n", + "##dine\n", + "##hart\n", + "##nn\n", + "##ave\n", + "##oni\n", + "##²\n", + "##ations\n", + "##tia\n", + "##cation\n", + "##logist\n", + "##ace\n", + "##ios\n", + "##vy\n", + "##var\n", + "##the\n", + "##igan\n", + "##tian\n", + "##10\n", + "##fication\n", + "##ple\n", + "##ller\n", + "##awa\n", + "##cu\n", + "##rm\n", + "##uch\n", + "##table\n", + "##oli\n", + "##lessly\n", + "##ulating\n", + "##ison\n", + "##hai\n", + "##az\n", + "##uro\n", + "##aria\n", + "##cted\n", + "##sion\n", + "##iz\n", + "##lot\n", + "##ques\n", + "##lled\n", + "##pot\n", + "##eck\n", + "##sc\n", + "##ase\n", + "##enberg\n", + "##eth\n", + "##ht\n", + "##oke\n", + "##aa\n", + "##load\n", + "##oria\n", + "##hara\n", + "##boy\n", + "##wind\n", + "##eh\n", + "##world\n", + "##tones\n", + "##eri\n", + "##try\n", + "##ural\n", + "##rch\n", + "##nberg\n", + "##nian\n", + "##ats\n", + "##kai\n", + "##weight\n", + "##ents\n", + "##wald\n", + "##piece\n", + "##mba\n", + "##air\n", + "##ean\n", + "##lings\n", + "##nu\n", + "##mine\n", + "##eur\n", + "##gie\n", + "##ture\n", + "##sel\n", + "##of\n", + "##zes\n", + "##ico\n", + "##fu\n", + "##cat\n", + "##rily\n", + "##bie\n", + "##rick\n", + "##bee\n", + "##ult\n", + "##ichi\n", + "##fc\n", + "##rra\n", + "##bble\n", + "##vis\n", + "##met\n", + "##20\n", + "##ants\n", + "##nger\n", + "##sse\n", + "##iana\n", + "##gio\n", + "##av\n", + "##oto\n", + "##mond\n", + "##iva\n", + "##kers\n", + "##power\n", + "##gent\n", + "##rine\n", + "##pped\n", + "##lene\n", + "##ali\n", + "##nin\n", + "##hole\n", + "##ssa\n", + "##sin\n", + "##eer\n", + "##sman\n", + "##ip\n", + "##card\n", + "##gin\n", + "##gled\n", + "##nder\n", + "##ort\n", + "##dorf\n", + "##zon\n", + "##kie\n", + "##bia\n", + "##eria\n", + "##yama\n", + "##old\n", + "##₃\n", + "##sch\n", + "##ulus\n", + "##oh\n", + "##bourne\n", + "##ox\n", + "##ient\n", + "##ann\n", + "##gated\n", + "##nas\n", + "##ars\n", + "##ancy\n", + "##rate\n", + "##och\n", + "##tum\n", + "##dian\n", + "##kel\n", + "##sberg\n", + "##chy\n", + "##rton\n", + "##ı\n", + "##ila\n", + "##bon\n", + "##sie\n", + "##nsis\n", + "##plane\n", + "##borg\n", + "##wyn\n", + "##hand\n", + "##hard\n", + "##ifying\n", + "##ced\n", + "##ern\n", + "##rina\n", + "##most\n", + "##nar\n", + "##dge\n", + "##ash\n", + "##pen\n", + "##₁\n", + "##wara\n", + "##cting\n", + "##nel\n", + "##pel\n", + "##rc\n", + "##aka\n", + "##ency\n", + "##ista\n", + "##ops\n", + "##dt\n", + "##eda\n", + "##hir\n", + "##boat\n", + "##lies\n", + "##ried\n", + "##sal\n", + "##fy\n", + "##nal\n", + "##zzo\n", + "##vas\n", + "##hing\n", + "##ass\n", + "##enburg\n", + "##are\n", + "##atic\n", + "##tter\n", + "##ub\n", + "##aries\n", + "##makers\n", + "##rst\n", + "##eim\n", + "##rne\n", + "##een\n", + "##nor\n", + "##ils\n", + "##wo\n", + "##ont\n", + "##ured\n", + "##outs\n", + "##rr\n", + "##face\n", + "##rad\n", + "##llen\n", + "##ote\n", + "##aya\n", + "##rl\n", + "##gu\n", + "##yang\n", + "##arian\n", + "##pus\n", + "##iah\n", + "##backs\n", + "##shing\n", + "##uring\n", + "##vre\n", + "##ander\n", + "##rry\n", + "##uma\n", + "##sworth\n", + "##tate\n", + "##ele\n", + "##dos\n", + "##nc\n", + "##mu\n", + "##rov\n", + "##ovich\n", + "##flow\n", + "##ib\n", + "##nse\n", + "##hot\n", + "##gos\n", + "##gus\n", + "##oka\n", + "##onic\n", + "##50\n", + "##ein\n", + "##nta\n", + "##own\n", + "##ther\n", + "##tric\n", + "##wich\n", + "##vey\n", + "##vable\n", + "##zio\n", + "##gel\n", + "##wen\n", + "##mc\n", + "##ava\n", + "##itt\n", + "##onia\n", + "##ffer\n", + "##ail\n", + "##urg\n", + "##tation\n", + "##quin\n", + "##12\n", + "##gation\n", + "##yr\n", + "##nate\n", + "##erly\n", + "##graphy\n", + "##gging\n", + "##metric\n", + "##making\n", + "##gas\n", + "##bro\n", + "##lman\n", + "##zel\n", + "##hold\n", + "##matic\n", + "##quet\n", + "##osis\n", + "##dell\n", + "##ude\n", + "##iko\n", + "##nch\n", + "##bes\n", + "##cut\n", + "##boro\n", + "##stan\n", + "##hat\n", + "##umi\n", + "##lls\n", + "##uck\n", + "##band\n", + "##gun\n", + "##lines\n", + "##40\n", + "##sive\n", + "##⁺\n", + "##beck\n", + "##ination\n", + "##its\n", + "##nica\n", + "##rna\n", + "##front\n", + "##lio\n", + "##dium\n", + "##bbled\n", + "##bor\n", + "##grave\n", + "##sts\n", + "##yle\n", + "##iv\n", + "##gic\n", + "##rley\n", + "##ots\n", + "##ete\n", + "##zia\n", + "##ef\n", + "##rf\n", + "##birds\n", + "##ield\n", + "##olo\n", + "##kal\n", + "##lers\n", + "##ister\n", + "##ashi\n", + "##cated\n", + "##uted\n", + "##eta\n", + "##vich\n", + "##lum\n", + "##pal\n", + "##ante\n", + "##city\n", + "##hia\n", + "##aj\n", + "##cent\n", + "##tting\n", + "##fort\n", + "##rand\n", + "##heads\n", + "##itive\n", + "##pies\n", + "##hausen\n", + "##foot\n", + "##play\n", + "##kawa\n", + "##ises\n", + "##wr\n", + "##eed\n", + "##uer\n", + "##ury\n", + "##sp\n", + "##keeper\n", + "##lling\n", + "##gram\n", + "##tos\n", + "##cott\n", + "##nam\n", + "##iate\n", + "##rich\n", + "##zong\n", + "##rol\n", + "##eng\n", + "##tro\n", + "##cos\n", + "##sus\n", + "##uta\n", + "##zz\n", + "##lice\n", + "##roy\n", + "##ania\n", + "##rius\n", + "##cial\n", + "##rose\n", + "##rous\n", + "##inal\n", + "##ished\n", + "##ctic\n", + "##vik\n", + "##rta\n", + "##gger\n", + "##eva\n", + "##tree\n", + "##iga\n", + "##mbo\n", + "##elli\n", + "##iff\n", + "##oning\n", + "##ders\n", + "##yar\n", + "##oda\n", + "##court\n", + "##inus\n", + "##gard\n", + "##ously\n", + "##nova\n", + "##lets\n", + "##set\n", + "##ibility\n", + "##ret\n", + "##vie\n", + "##zan\n", + "##ste\n", + "##wal\n", + "##garh\n", + "##lation\n", + "##hra\n", + "##bles\n", + "##gt\n", + "##tc\n", + "##nick\n", + "##gren\n", + "##bre\n", + "##bic\n", + "##ams\n", + "##lish\n", + "##leigh\n", + "##hler\n", + "##idge\n", + "##dr\n", + "##nde\n", + "##rda\n", + "##rade\n", + "##nto\n", + "##ement\n", + "##wl\n", + "##ool\n", + "##ience\n", + "##lk\n", + "##ep\n", + "##ution\n", + "##date\n", + "##page\n", + "##ographic\n", + "##itis\n", + "##½\n", + "##kas\n", + "##ische\n", + "##lm\n", + "##stown\n", + "##aux\n", + "##mere\n", + "##eu\n", + "##link\n", + "##tina\n", + "##ead\n", + "##lated\n", + "##wer\n", + "##hardt\n", + "##lina\n", + "##zzi\n", + "##late\n", + "##nga\n", + "##ake\n", + "##ido\n", + "##haus\n", + "##anda\n", + "##lal\n", + "##uan\n", + "##gg\n", + "##type\n", + "##pt\n", + "##trom\n", + "##hman\n", + "##ght\n", + "##used\n", + "##elia\n", + "##eg\n", + "##alis\n", + "##ages\n", + "##uded\n", + "##ppa\n", + "##lton\n", + "##cock\n", + "##worthy\n", + "##fall\n", + "##yon\n", + "##hine\n", + "##vers\n", + "##igo\n", + "##ways\n", + "##some\n", + "##atory\n", + "##tered\n", + "##uda\n", + "##rrell\n", + "##ame\n", + "##bby\n", + "##fest\n", + "##ast\n", + "##ented\n", + "##ided\n", + "##fying\n", + "##star\n", + "##ost\n", + "##rod\n", + "##uru\n", + "##yard\n", + "##owing\n", + "##dd\n", + "##30\n", + "##ifies\n", + "##ying\n", + "##combe\n", + "##о\n", + "##fly\n", + "##flower\n", + "##ه\n", + "##tail\n", + "##nese\n", + "##nz\n", + "##form\n", + "##uc\n", + "##hian\n", + "##fies\n", + "##raj\n", + "##xton\n", + "##hm\n", + "##uki\n", + "##dley\n", + "##shu\n", + "##haw\n", + "##icus\n", + "##wise\n", + "##isa\n", + "##kis\n", + "##zie\n", + "##eld\n", + "##lp\n", + "##urn\n", + "##pu\n", + "##lov\n", + "##uth\n", + "##cle\n", + "##kins\n", + "##aid\n", + "##jon\n", + "##him\n", + "##rre\n", + "##nagar\n", + "##pling\n", + "##lier\n", + "##vier\n", + "##mouth\n", + "##pf\n", + "##top\n", + "##how\n", + "##graph\n", + "##ssen\n", + "##bone\n", + "##dling\n", + "##ime\n", + "##lah\n", + "##park\n", + "##bil\n", + "##sby\n", + "##bat\n", + "##rial\n", + "##cian\n", + "##hoe\n", + "##ي\n", + "##usion\n", + "##mir\n", + "##uation\n", + "##lby\n", + "##oll\n", + "##rman\n", + "##ott\n", + "##11\n", + "##holder\n", + "##lake\n", + "##rp\n", + "##sl\n", + "##rer\n", + "##ema\n", + "##ively\n", + "##vor\n", + "##culture\n", + "##tead\n", + "##oth\n", + "##ttes\n", + "##hof\n", + "##oro\n", + "##tics\n", + "##α\n", + "##rid\n", + "##iard\n", + "##tera\n", + "##sies\n", + "##tly\n", + "##aan\n", + "##jin\n", + "##iss\n", + "##ear\n", + "##dock\n", + "##haven\n", + "##tical\n", + "##ook\n", + "##rata\n", + "##uit\n", + "##rama\n", + "##bilities\n", + "##hua\n", + "##cci\n", + "##dad\n", + "##sted\n", + "##qi\n", + "##nted\n", + "##ija\n", + "##liga\n", + "##croft\n", + "##ede\n", + "##kovic\n", + "##rica\n", + "##aire\n", + "##shed\n", + "##pie\n", + "##stock\n", + "##mma\n", + "##vil\n", + "##ncies\n", + "##eous\n", + "##rion\n", + "##graphic\n", + "##elle\n", + "##inate\n", + "##rit\n", + "##tled\n", + "##xia\n", + "##ttered\n", + "##dic\n", + "##eum\n", + "##force\n", + "##key\n", + "##hey\n", + "##yam\n", + "##pping\n", + "##hol\n", + "##chan\n", + "##berger\n", + "##nier\n", + "##fo\n", + "##lson\n", + "##cture\n", + "##baum\n", + "##ures\n", + "##mb\n", + "##nium\n", + "##law\n", + "##hd\n", + "##has\n", + "##bol\n", + "##iving\n", + "##ddy\n", + "##far\n", + "##lav\n", + "##rai\n", + "##lip\n", + "##ically\n", + "##hos\n", + "##tech\n", + "##erty\n", + "##pc\n", + "##pole\n", + "##base\n", + "##rist\n", + "##path\n", + "##iated\n", + "##tling\n", + "##vs\n", + "##oss\n", + "##owed\n", + "##nton\n", + "##rail\n", + "##18\n", + "##eter\n", + "##fan\n", + "##sdale\n", + "##ility\n", + "##lda\n", + "##mans\n", + "##fields\n", + "##avia\n", + "##take\n", + "##rating\n", + "##rb\n", + "##pass\n", + "##itated\n", + "##rey\n", + "##lian\n", + "##uchi\n", + "##thi\n", + "##inas\n", + "##hale\n", + "##girl\n", + "##owski\n", + "##kha\n", + "##rth\n", + "##encies\n", + "##boards\n", + "##nah\n", + "##ctive\n", + "##tile\n", + "##е\n", + "##ος\n", + "##nco\n", + "##tron\n", + "##moto\n", + "##pace\n", + "##vent\n", + "##bbling\n", + "##ello\n", + "##tty\n", + "##nett\n", + "##witz\n", + "##iating\n", + "##rz\n", + "##ffin\n", + "##ffed\n", + "##د\n", + "##ache\n", + "##asia\n", + "##iting\n", + "##ии\n", + "##mates\n", + "##quent\n", + "##ond\n", + "##cular\n", + "##ouse\n", + "##tai\n", + "##kowski\n", + "##pad\n", + "##ipe\n", + "##cin\n", + "##nos\n", + "##tam\n", + "##nge\n", + "##lc\n", + "##tton\n", + "##ndo\n", + "##nstein\n", + "##bound\n", + "##aking\n", + "##burgh\n", + "##bbed\n", + "##quest\n", + "##life\n", + "##lius\n", + "##mos\n", + "##run\n", + "##lous\n", + "##ingen\n", + "##qui\n", + "##nson\n", + "##wed\n", + "##eet\n", + "##rik\n", + "##gged\n", + "##ows\n", + "##cup\n", + "##nies\n", + "##atus\n", + "##ais\n", + "##bian\n", + "##rew\n", + "##sters\n", + "##orted\n", + "##glass\n", + "##forth\n", + "##mis\n", + "##ride\n", + "##physics\n", + "##frame\n", + "##iidae\n", + "##itor\n", + "##houses\n", + "##iano\n", + "##cas\n", + "##nding\n", + "##strom\n", + "##hes\n", + "##antly\n", + "##ogy\n", + "##kos\n", + "##kka\n", + "##acy\n", + "##chel\n", + "##plate\n", + "##aru\n", + "##lights\n", + "##iri\n", + "##uka\n", + "##ntal\n", + "##jet\n", + "##written\n", + "##gers\n", + "##rity\n", + "##ente\n", + "##sca\n", + "##ingly\n", + "##hana\n", + "##oft\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "##ues\n", + "##mmer\n", + "##sai\n", + "##inian\n", + "##inated\n", + "##uke\n", + "##bos\n", + "##pton\n", + "##uli\n", + "##night\n", + "##chemical\n", + "##kill\n", + "##eb\n", + "##eal\n", + "##tag\n", + "##vsky\n", + "##bay\n", + "##lit\n", + "##ن\n", + "##ug\n", + "##yk\n", + "##ril\n", + "##ech\n", + "##right\n", + "##sfield\n", + "##rky\n", + "##zone\n", + "##udge\n", + "##vel\n", + "##lain\n", + "##jk\n", + "##writer\n", + "##hel\n", + "##ffe\n", + "##vn\n", + "##onal\n", + "##sto\n", + "##turing\n", + "##hawks\n", + "##code\n", + "##16\n", + "##wu\n", + "##bahn\n", + "##ovo\n", + "##hic\n", + "##15\n", + "##mura\n", + "##verse\n", + "##anza\n", + "##bag\n", + "##jar\n", + "##60\n", + "##ndi\n", + "##uf\n", + "##aga\n", + "##had\n", + "##azi\n", + "##nko\n", + "##olved\n", + "##nr\n", + "##ressed\n", + "##lent\n", + "##19\n", + "##sd\n", + "##uto\n", + "##dog\n", + "##sten\n", + "##ν\n", + "##chev\n", + "##cope\n", + "##tted\n", + "##chus\n", + "##ович\n", + "##dre\n", + "##ulous\n", + "##gn\n", + "##nath\n", + "##qua\n", + "##bler\n", + "##0s\n", + "##rell\n", + "##tated\n", + "##rier\n", + "##duction\n", + "##hc\n", + "##rator\n", + "##np\n", + "##evich\n", + "##wig\n", + "##cate\n", + "##iling\n", + "##uel\n", + "##coe\n", + "##fin\n", + "##care\n", + "##yas\n", + "##grad\n", + "##ules\n", + "##bit\n", + "##ffy\n", + "##abe\n", + "##rift\n", + "##imo\n", + "##pop\n", + "##tr\n", + "##orf\n", + "##yre\n", + "##ground\n", + "##oko\n", + "##hor\n", + "##hima\n", + "##uga\n", + "##mity\n", + "##tium\n", + "##iver\n", + "##dc\n", + "##inae\n", + "##ø\n", + "##rea\n", + "##dh\n", + "##ob\n", + "##ingham\n", + "##uts\n", + "##tern\n", + "##uated\n", + "##dent\n", + "##cross\n", + "##dicate\n", + "##lder\n", + "##oat\n", + "##genic\n", + "##oor\n", + "##eno\n", + "##itating\n", + "##gr\n", + "##wc\n", + "##gins\n", + "##etic\n", + "##coat\n", + "##wave\n", + "##etta\n", + "##print\n", + "##rak\n", + "##bl\n", + "##mons\n", + "##nard\n", + "##kara\n", + "##cine\n", + "##rel\n", + "##17\n", + "##hit\n", + "##ony\n", + "##aging\n", + "##wang\n", + "##ores\n", + "##amp\n", + "##dating\n", + "##sti\n", + "##cts\n", + "##game\n", + "##rae\n", + "##ngo\n", + "##cca\n", + "##rable\n", + "##unt\n", + "##static\n", + "##wear\n", + "##nov\n", + "##lana\n", + "##ense\n", + "##32\n", + "##eman\n", + "##fm\n", + "##rana\n", + "##zal\n", + "##nay\n", + "##cre\n", + "##zers\n", + "##eration\n", + "##ctor\n", + "##bine\n", + "##tist\n", + "##oured\n", + "##nti\n", + "##piration\n", + "##asa\n", + "##nza\n", + "##ption\n", + "##yana\n", + "##unk\n", + "##rek\n", + "##ucci\n", + "##ario\n", + "##sat\n", + "##erated\n", + "##р\n", + "##mers\n", + "##suke\n", + "##pool\n", + "##vd\n", + "##vert\n", + "##cellular\n", + "##nant\n", + "##ologists\n", + "##hore\n", + "##xie\n", + "##rock\n", + "##ners\n", + "##stad\n", + "##guchi\n", + "##thy\n", + "##lem\n", + "##14\n", + "##omy\n", + "##vate\n", + "##gating\n", + "##jee\n", + "##media\n", + "##idal\n", + "##hora\n", + "##gna\n", + "##lining\n", + "##rgan\n", + "##₄\n", + "##ark\n", + "##bius\n", + "##gong\n", + "##uz\n", + "##sian\n", + "##not\n", + "##group\n", + "##bid\n", + "##sos\n", + "##iger\n", + "##rdi\n", + "##vision\n", + "##oids\n", + "##dden\n", + "##₀\n", + "##sz\n", + "##cer\n", + "##walk\n", + "##gles\n", + "##dam\n", + "##13\n", + "##ood\n", + "##ske\n", + "##ر\n", + "##hun\n", + "##eiro\n", + "##outh\n", + "##zin\n", + "##ono\n", + "##adi\n", + "##aneous\n", + "##bers\n", + "##oot\n", + "##bbs\n", + "##chin\n", + "##yuan\n", + "##nya\n", + "##yev\n", + "##yte\n", + "##gies\n", + "##vid\n", + "##zzled\n", + "##yx\n", + "##rington\n", + "##arium\n", + "##ota\n", + "##iser\n", + "##ibly\n", + "##lau\n", + "##pd\n", + "##ieu\n", + "##iary\n", + "##llar\n", + "##athy\n", + "##sea\n", + "##was\n", + "##iche\n", + "##ager\n", + "##bell\n", + "##ike\n", + "##ntes\n", + "##aurus\n", + "##core\n", + "##jack\n", + "##osh\n", + "##uddin\n", + "##erie\n", + "##jas\n", + "##tee\n", + "##tock\n", + "##cky\n", + "##isi\n", + "##gler\n", + "##sum\n", + "##shin\n", + "##я\n", + "##ailed\n", + "##ivating\n", + "##nae\n", + "##tism\n", + "##unce\n", + "##rdy\n", + "##21\n", + "##loaded\n", + "##books\n", + "##iki\n", + "##vale\n", + "##geny\n", + "##ße\n", + "##cratic\n", + "##dha\n", + "##emann\n", + "##yah\n", + "##athlon\n", + "##itate\n", + "##ited\n", + "##emia\n", + "##tier\n", + "##eis\n", + "##rong\n", + "##pate\n", + "##atics\n", + "##rove\n", + "##rice\n", + "##gre\n", + "##dus\n", + "##moor\n", + "##rite\n", + "##izer\n", + "##ope\n", + "##gra\n", + "##zzle\n", + "##oom\n", + "##sford\n", + "##dham\n", + "##sper\n", + "##ndra\n", + "##dong\n", + "##tani\n", + "##rix\n", + "##eye\n", + "##oping\n", + "##cap\n", + "##polis\n", + "##gis\n", + "##bir\n", + "##tad\n", + "##rted\n", + "##evic\n", + "##rita\n", + "##sque\n", + "##mobile\n", + "##rson\n", + "##sity\n", + "##25\n", + "##von\n", + "##oney\n", + "##holders\n", + "##oned\n", + "##lag\n", + "##puram\n", + "##rds\n", + "##rino\n", + "##eding\n", + "##por\n", + "##rma\n", + "##cite\n", + "##max\n", + "##uss\n", + "##enko\n", + "##icated\n", + "##hrer\n", + "##fare\n", + "##rant\n", + "##hoff\n", + "##ume\n", + "##taking\n", + "##gence\n", + "##yman\n", + "##80\n", + "##hya\n", + "##lde\n", + "##iu\n", + "##phic\n", + "##ares\n", + "##ested\n", + "##vina\n", + "##cake\n", + "##lim\n", + "##cards\n", + "##cene\n", + "##shaw\n", + "##agh\n", + "##tering\n", + "##ych\n", + "##hawk\n", + "##hang\n", + "##cki\n", + "##lund\n", + "##ffen\n", + "##xy\n", + "##weed\n", + "##rane\n", + "##nock\n", + "##ulata\n", + "##sbury\n", + "##chs\n", + "##vian\n", + "##psy\n", + "##morphic\n", + "##ull\n", + "##ifier\n", + "##pr\n", + "##uca\n", + "##³\n", + "##cliffe\n", + "##sser\n", + "##ards\n", + "##yde\n", + "##pis\n", + "##48\n", + "##cked\n", + "##ffle\n", + "##ryn\n", + "##get\n", + "##oz\n", + "##pol\n", + "##using\n", + "##ums\n", + "##oga\n", + "##aine\n", + "##screen\n", + "##wes\n", + "##lined\n", + "##gc\n", + "##ι\n", + "##text\n", + "##tary\n", + "##anga\n", + "##hell\n", + "##oya\n", + "##rden\n", + "##tain\n", + "##cating\n", + "##onne\n", + "##gb\n", + "##tase\n", + "##comb\n", + "##ddin\n", + "##neck\n", + "##yna\n", + "##itic\n", + "##truct\n", + "##jak\n", + "##etti\n", + "##keeping\n", + "##rland\n", + "##quist\n", + "##hiro\n", + "##lich\n", + "##aceae\n", + "##elo\n", + "##word\n", + "##edes\n", + "##nac\n", + "##wart\n", + "##gee\n", + "##nds\n", + "##igh\n", + "##cise\n", + "##case\n", + "##bot\n", + "##dies\n", + "##lik\n", + "##ital\n", + "##guard\n", + "##psis\n", + "##iba\n", + "##lift\n", + "##xt\n", + "##dah\n", + "##wy\n", + "##iful\n", + "##rized\n", + "##unda\n", + "##hari\n", + "##cious\n", + "##name\n", + "##int\n", + "##iled\n", + "##hop\n", + "##bis\n", + "##gling\n", + "##ection\n", + "##tley\n", + "##kumar\n", + "##iman\n", + "##gible\n", + "##balls\n", + "##ان\n", + "##ific\n", + "##rative\n", + "##iq\n", + "##uity\n", + "##tem\n", + "##ught\n", + "##ending\n", + "##mbe\n", + "##itation\n", + "##writing\n", + "##kur\n", + "##loading\n", + "##rgo\n", + "##sonic\n", + "##oop\n", + "##eni\n", + "##chal\n", + "##llah\n", + "##mler\n", + "##lity\n", + "##osing\n", + "##100\n", + "##erson\n", + "##pper\n", + "##ili\n", + "##brush\n", + "##acle\n", + "##ady\n", + "##zaki\n", + "##ulin\n", + "##bolic\n", + "##aged\n", + "##grapher\n", + "##vial\n", + "##hwa\n", + "##ades\n", + "##nous\n", + "##itude\n", + "##icz\n", + "##xa\n", + "##ider\n", + "##erman\n", + "##kell\n", + "##uled\n", + "##eve\n", + "##eres\n", + "##rner\n", + "##tok\n", + "##color\n", + "##dly\n", + "##ssi\n", + "##ometer\n", + "##lington\n", + "##tility\n", + "##adt\n", + "##logists\n", + "##ight\n", + "##rri\n", + "##phs\n", + "##riation\n", + "##rish\n", + "##put\n", + "##tow\n", + "##uce\n", + "##rium\n", + "##jana\n", + "##rring\n", + "##tadt\n", + "##elin\n", + "##kova\n", + "##ł\n", + "##kind\n", + "##heimer\n", + "##24\n", + "##gaard\n", + "##oran\n", + "##ulo\n", + "##olin\n", + "##ype\n", + "##watch\n", + "##ylus\n", + "##jah\n", + "##mmy\n", + "##holm\n", + "##tner\n", + "##tri\n", + "##avi\n", + "##irs\n", + "##mat\n", + "##jit\n", + "##eto\n", + "##proof\n", + "##act\n", + "##ories\n", + "##bow\n", + "##fted\n", + "##uration\n", + "##ators\n", + "##dp\n", + "##rro\n", + "##coming\n", + "##mot\n", + "##db\n", + "##fen\n", + "##vant\n", + "##н\n", + "##cles\n", + "##iation\n", + "##lion\n", + "##ssing\n", + "##ulates\n", + "##dina\n", + "##grant\n", + "##rop\n", + "##rca\n", + "##iom\n", + "##leader\n", + "##iae\n", + "##esis\n", + "##rsten\n", + "##sb\n", + "##cens\n", + "##eka\n", + "##llan\n", + "##shot\n", + "##uman\n", + "##cic\n", + "##ald\n", + "##qa\n", + "##xed\n", + "##eded\n", + "##any\n", + "##phones\n", + "##uo\n", + "##kle\n", + "##nine\n", + "##ᵢ\n", + "##ₙ\n", + "##dhi\n", + "##estinal\n", + "##oso\n", + "##rno\n", + "##uche\n", + "##lma\n", + "##rva\n", + "##sable\n", + "##vocation\n", + "##posed\n", + "##cturing\n", + "##tres\n", + "##rce\n", + "##num\n", + "##bey\n", + "##inating\n", + "##ih\n", + "##yoshi\n", + "##imeter\n", + "##bei\n", + "##shore\n", + "##iable\n", + "##leaf\n", + "##lace\n", + "##oud\n", + "##gned\n", + "##swell\n", + "##sms\n", + "##uil\n", + "##osition\n", + "##ckle\n", + "##itzer\n", + "##ов\n", + "##leton\n", + "##pine\n", + "##minate\n", + "##tland\n", + "##tore\n", + "##bt\n", + "##eca\n", + "##nched\n", + "##borne\n", + "##won\n", + "##ional\n", + "##ads\n", + "##entation\n", + "##sible\n", + "##ß\n", + "##pia\n", + "##imus\n", + "##22\n", + "##att\n", + "##ndon\n", + "##child\n", + "##lica\n", + "##cera\n", + "##selle\n", + "##par\n", + "##plex\n", + "##tooth\n", + "##gny\n", + "##rlin\n", + "##cured\n", + "##jima\n", + "##rter\n", + "##oic\n", + "##dl\n", + "##olate\n", + "##iously\n", + "##ة\n", + "##escu\n", + "##zhi\n", + "##dron\n", + "##beat\n", + "##bana\n", + "##sol\n", + "##cape\n", + "##hil\n", + "##boats\n", + "##bbe\n", + "##olar\n", + "##35\n", + "##xide\n", + "##uni\n", + "##pac\n", + "##ease\n", + "##omo\n", + "##vet\n", + "##aud\n", + "##iques\n", + "##dded\n", + "##endra\n", + "##hala\n", + "##morphism\n", + "##cier\n", + "##yra\n", + "##iso\n", + "##ttering\n", + "##sic\n", + "##ored\n", + "##ς\n", + "##urt\n", + "##cats\n", + "##sher\n", + "##xing\n", + "##active\n", + "##aca\n", + "##pala\n", + "##tl\n", + "##kon\n", + "##west\n", + "##kk\n", + "##mble\n", + "##yuki\n", + "##cko\n", + "##ln\n", + "##grass\n", + "##gua\n", + "##fr\n", + "##ław\n", + "##pas\n", + "##zawa\n", + "##vr\n", + "##storm\n", + "##vu\n", + "##sun\n", + "##rte\n", + "##aba\n", + "##lea\n", + "##hammer\n", + "##neer\n", + "##uba\n", + "##see\n", + "##cken\n", + "##henko\n", + "##lai\n", + "##now\n", + "##qing\n", + "##gill\n", + "##jun\n", + "##cd\n", + "##ioned\n", + "##cote\n", + "##hips\n", + "##pressed\n", + "##cology\n", + "##enia\n", + "##erry\n", + "##nat\n", + "##islav\n", + "##ink\n", + "##70\n", + "##wei\n", + "##odes\n", + "##rar\n", + "##rked\n", + "##lein\n", + "##kled\n", + "##vos\n", + "##mith\n", + "##на\n", + "##cke\n", + "##thus\n", + "##cula\n", + "##inski\n", + "##br\n", + "##post\n", + "##ask\n", + "##uter\n", + "##yya\n", + "##mbre\n", + "##ntial\n", + "##mill\n", + "##amine\n", + "##while\n", + "##jos\n", + "##ldon\n", + "##chman\n", + "##isch\n", + "##45\n", + "##ust\n", + "##ml\n", + "##ision\n", + "##lord\n", + "##ishly\n", + "##rks\n", + "##holes\n", + "##hong\n", + "##wife\n", + "##jer\n", + "##glia\n", + "##uin\n", + "##rim\n", + "##fighter\n", + "##gonal\n", + "##orescence\n", + "##wari\n", + "##due\n", + "##elt\n", + "##dled\n", + "##mount\n", + "##osi\n", + "##lat\n", + "##mme\n", + "##akes\n", + "##etto\n", + "##hetic\n", + "##urus\n", + "##atter\n", + "##station\n", + "##sef\n", + "##press\n", + "##acious\n", + "##icient\n", + "##mur\n", + "##gil\n", + "##anne\n", + "##xes\n", + "##llus\n", + "##pathy\n", + "##hue\n", + "##eit\n", + "##bate\n", + "##lore\n", + "##itch\n", + "##hea\n", + "##phobic\n", + "##vati\n", + "##sport\n", + "##dation\n", + "##eyer\n", + "##otic\n", + "##udy\n", + "##kari\n", + "##sier\n", + "##sei\n", + "##gor\n", + "##isman\n", + "##kling\n", + "##ego\n", + "##utz\n", + "##chule\n", + "##nesian\n", + "##iol\n", + "##market\n", + "##xin\n", + "##egan\n", + "##chet\n", + "##user\n", + "##ddle\n", + "##illon\n", + "##xx\n", + "##finger\n", + "##ulator\n", + "##wire\n", + "##mour\n", + "##atin\n", + "##chrome\n", + "##ester\n", + "##rates\n", + "##yria\n", + "##llation\n", + "##tom\n", + "##ulu\n", + "##uze\n", + "##raz\n", + "##ako\n", + "##lev\n", + "##gau\n", + "##bourg\n", + "##lles\n", + "##rya\n", + "##nius\n", + "##fight\n", + "##hak\n", + "##cl\n", + "##nham\n", + "##iac\n", + "##lab\n", + "##rber\n", + "##sner\n", + "##isto\n", + "##aran\n", + "##mt\n", + "##tana\n", + "##acies\n", + "##atz\n", + "##gement\n", + "##thest\n", + "##ej\n", + "##fusion\n", + "##orum\n", + "##stra\n", + "##rred\n", + "##vine\n", + "##hini\n", + "##bies\n", + "##eering\n", + "##hui\n", + "##kee\n", + "##nl\n", + "##aus\n", + "##dition\n", + "##notes\n", + "##iology\n", + "##mology\n", + "##isk\n", + "##zione\n", + "##illy\n", + "##naire\n", + "##sler\n", + "##arts\n", + "##imated\n", + "##uate\n", + "##wley\n", + "##ject\n", + "##dio\n", + "##ods\n", + "##ricted\n", + "##eti\n", + "##ntly\n", + "##lane\n", + "##ggio\n", + "##torm\n", + "##oting\n", + "##liner\n", + "##ush\n", + "##ooped\n", + "##lage\n", + "##rdo\n", + "##yen\n", + "##zak\n", + "##pose\n", + "##tur\n", + "##enity\n", + "##gat\n", + "##bara\n", + "##zza\n", + "##kaya\n", + "##raphic\n", + "##zam\n", + "##ogical\n", + "##phine\n", + "##fide\n", + "##thing\n", + "##cars\n", + "##ptic\n", + "##ibe\n", + "##chu\n", + "##sio\n", + "##aly\n", + "##rano\n", + "##tious\n", + "##oman\n", + "##pire\n", + "##dable\n", + "##aq\n", + "##dder\n", + "##ologies\n", + "##rone\n", + "##mani\n", + "##rge\n", + "##eli\n", + "##uting\n", + "##cao\n", + "##agawa\n", + "##yed\n", + "##lard\n", + "##under\n", + "##zzling\n", + "##86\n", + "##lena\n", + "##llum\n", + "##phon\n", + "##anus\n", + "##lb\n", + "##yler\n", + "##eux\n", + "##olis\n", + "##astic\n", + "##gina\n", + "##chia\n", + "##obe\n", + "##insky\n", + "##lett\n", + "##lean\n", + "##lves\n", + "##therapy\n", + "##tery\n", + "##hire\n", + "##nca\n", + "##nical\n", + "##bet\n", + "##icles\n", + "##ulia\n", + "##mian\n", + "##tial\n", + "##rle\n", + "##erence\n", + "##omi\n", + "##fulness\n", + "##sas\n", + "##rwood\n", + "##liness\n", + "##df\n", + "##42\n", + "##xley\n", + "##ysis\n", + "##ffa\n", + "##berries\n", + "##athic\n", + "##lr\n", + "##ivo\n", + "##erton\n", + "##founded\n", + "##ulf\n", + "##sham\n", + "##tries\n", + "##tania\n", + "##uron\n", + "##nology\n", + "##mata\n", + "##hee\n", + "##fle\n", + "##udi\n", + "##cheng\n", + "##achi\n", + "##ental\n", + "##aves\n", + "##90\n", + "##twined\n", + "##cino\n", + "##64\n", + "##yal\n", + "##bial\n", + "##ucible\n", + "##ples\n", + "##bina\n", + "##rned\n", + "##auer\n", + "##kia\n", + "##ogan\n", + "##pled\n", + "##kim\n", + "##lani\n", + "##ael\n", + "##elled\n", + "##onate\n", + "##feit\n", + "##aur\n", + "##cter\n", + "##tour\n", + "##oir\n", + "##rain\n", + "##cable\n", + "##boarding\n", + "##tment\n", + "##eville\n", + "##gawa\n", + "##dry\n", + "##rly\n", + "##log\n", + "##berto\n", + "##llin\n", + "##breaker\n", + "##issa\n", + "##rts\n", + "##ssel\n", + "##dler\n", + "##oration\n", + "##cule\n", + "##ulously\n", + "##pura\n", + "##gens\n", + "##rricular\n", + "##oris\n", + "##tm\n", + "##ytic\n", + "##iere\n", + "##zine\n", + "##ication\n", + "##mins\n", + "##gold\n", + "##uid\n", + "##lid\n", + "##aby\n", + "##ined\n", + "##phy\n", + "##uld\n", + "##liest\n", + "##owa\n", + "##lom\n", + "##eira\n", + "##titled\n", + "##ggs\n", + "##otti\n", + "##roud\n", + "##iza\n", + "##bron\n", + "##sr\n", + "##diment\n", + "##dai\n", + "##stick\n", + "##wicz\n", + "##acio\n", + "##asi\n", + "##eme\n", + "##mail\n", + "##working\n", + "##smith\n", + "##cco\n", + "##enbach\n", + "##icular\n", + "##eson\n", + "##stream\n", + "##tya\n", + "##uber\n", + "##factory\n", + "##cea\n", + "##bard\n", + "##ahu\n", + "##ivate\n", + "##hesion\n", + "##46\n", + "##rangle\n", + "##dridge\n", + "##31\n", + "##tral\n", + "##imate\n", + "##dington\n", + "##folding\n", + "##nesia\n", + "##oof\n", + "##ppe\n", + "##stand\n", + "##grove\n", + "##manship\n", + "##rup\n", + "##stituting\n", + "##carriage\n", + "##lston\n", + "##stadt\n", + "##wai\n", + "##zier\n", + "##bria\n", + "##plication\n", + "##nged\n", + "##sam\n", + "##belt\n", + "##eem\n", + "##made\n", + "##pro\n", + "##nent\n", + "##rani\n", + "##hesive\n", + "##sko\n", + "##lts\n", + "##lidae\n", + "##vation\n", + "##gp\n", + "##than\n", + "##erus\n", + "##logies\n", + "##36\n", + "##rance\n", + "##anto\n", + "##kr\n", + "##vary\n", + "##iter\n", + "##pired\n", + "##avian\n", + "##vili\n", + "##vir\n", + "##eral\n", + "##sett\n", + "##aling\n", + "##biology\n", + "##gm\n", + "##orus\n", + "##bella\n", + "##rot\n", + "##folia\n", + "##llis\n", + "##rom\n", + "##ount\n", + "##wd\n", + "##rocity\n", + "##acion\n", + "##urne\n", + "##sor\n", + "##icide\n", + "##sty\n", + "##ilised\n", + "##org\n", + "##wana\n", + "##ghton\n", + "##rcle\n", + "##mona\n", + "##mber\n", + "##jiang\n", + "##vance\n", + "##rogate\n", + "##dman\n", + "##tenberg\n", + "##ffs\n", + "##ishment\n", + "##ddling\n", + "##kor\n", + "##lium\n", + "##ove\n", + "##enstein\n", + "##inen\n", + "##ones\n", + "##uti\n", + "##vington\n", + "##rella\n", + "##ishing\n", + "##ossa\n", + "##chers\n", + "##tung\n", + "##phi\n", + "##tidae\n", + "##cade\n", + "##drum\n", + "##riz\n", + "##hul\n", + "##pha\n", + "##bino\n", + "##resh\n", + "##cp\n", + "##wine\n", + "##23\n", + "##vah\n", + "##lter\n", + "##riding\n", + "##´s\n", + "##ieri\n", + "##oku\n", + "##ended\n", + "##hampton\n", + "##jong\n", + "##marine\n", + "##ivated\n", + "##ovsky\n", + "##aea\n", + "##ivist\n", + "##verance\n", + "##brate\n", + "##ctions\n", + "##usions\n", + "##34\n", + "##38\n", + "##omic\n", + "##rling\n", + "##ange\n", + "##horpe\n", + "##inations\n", + "##roving\n", + "##eptive\n", + "##moral\n", + "##tale\n", + "##apa\n", + "##pio\n", + "##note\n", + "##tails\n", + "##bas\n", + "##nea\n", + "##ply\n", + "##udes\n", + "##pile\n", + "##words\n", + "##roup\n", + "##dm\n", + "##cede\n", + "##mora\n", + "##yt\n", + "##rut\n", + "##erate\n", + "##lva\n", + "##ulton\n", + "##lini\n", + "##rrie\n", + "##fighting\n", + "##icum\n", + "##dim\n", + "##llon\n", + "##ulla\n", + "##م\n", + "##dro\n", + "##quel\n", + "##test\n", + "##51\n", + "##hiko\n", + "##aver\n", + "##ghan\n", + "##oms\n", + "##sho\n", + "##saurus\n", + "##lating\n", + "##wny\n", + "##ind\n", + "##gall\n", + "##ups\n", + "##hp\n", + "##nall\n", + "##kra\n", + "##53\n", + "##rgos\n", + "##tose\n", + "##km\n", + "##turn\n", + "##chang\n", + "##mina\n", + "##athing\n", + "##kley\n", + "##izations\n", + "##aint\n", + "##pet\n", + "##hers\n", + "##kus\n", + "##sant\n", + "##hend\n", + "##mart\n", + "##eley\n", + "##ilo\n", + "##edd\n", + "##ucher\n", + "##nging\n", + "##heart\n", + "##rka\n", + "##rsa\n", + "##weiler\n", + "##unced\n", + "##33\n", + "##aring\n", + "##thorpe\n", + "##rave\n", + "##28\n", + "##bered\n", + "##bba\n", + "##eric\n", + "##arth\n", + "##kko\n", + "##bush\n", + "##aton\n", + "##hma\n", + "##esa\n", + "##centric\n", + "##kti\n", + "##aith\n", + "##ect\n", + "##script\n", + "##ivism\n", + "##erland\n", + "##rou\n", + "##lco\n", + "##xon\n", + "##oes\n", + "##ever\n", + "##bery\n", + "##khar\n", + "##tet\n", + "##stle\n", + "##wide\n", + "##ogist\n", + "##tham\n", + "##fp\n", + "##taff\n", + "##−\n", + "##isms\n", + "##yp\n", + "##rse\n", + "##nikov\n", + "##js\n", + "##uaries\n", + "##frey\n", + "##amo\n", + "##llet\n", + "##opsis\n", + "##ctric\n", + "##47\n", + "##rini\n", + "##rified\n", + "##charged\n", + "##aker\n", + "##iform\n", + "##rgy\n", + "##tius\n", + "##nburg\n", + "##евич\n", + "##rac\n", + "##bha\n", + "##hering\n", + "##tures\n", + "##eber\n", + "##zow\n", + "##ctus\n", + "##aco\n", + "##lander\n", + "##chfield\n", + "##forms\n", + "##icides\n", + "##lence\n", + "##tica\n", + "##chment\n", + "##lization\n", + "##aja\n", + "##ganj\n", + "##sari\n", + "##church\n", + "##sf\n", + "##fia\n", + "##ncia\n", + "##ition\n", + "##nity\n", + "##worm\n", + "##ggy\n", + "##voking\n", + "##lite\n", + "##grate\n", + "##nets\n", + "##alia\n", + "##rent\n", + "##nitz\n", + "##pts\n", + "##pta\n", + "##bolt\n", + "##pheus\n", + "##onale\n", + "##meter\n", + "##placed\n", + "##imating\n", + "##sche\n", + "##ogo\n", + "##mony\n", + "##gum\n", + "##real\n", + "##eers\n", + "##gam\n", + "##elles\n", + "##vat\n", + "##trick\n", + "##uge\n", + "##hta\n", + "##jn\n", + "##race\n", + "##27\n", + "##slin\n", + "##uve\n", + "##mac\n", + "##ays\n", + "##oja\n", + "##т\n", + "##wheel\n", + "##laya\n", + "##mics\n", + "##pods\n", + "##lberg\n", + "##ennial\n", + "##mit\n", + "##44\n", + "##rigues\n", + "##zquez\n", + "##tman\n", + "##roid\n", + "##relli\n", + "##ours\n", + "##hdi\n", + "##nable\n", + "##gues\n", + "##zuka\n", + "##gley\n", + "##ła\n", + "##agi\n", + "##mx\n", + "##cis\n", + "##rogen\n", + "##vot\n", + "##ulsive\n", + "##krishna\n", + "##horse\n", + "##gga\n", + "##economic\n", + "##mun\n", + "##eves\n", + "##thic\n", + "##uj\n", + "##otto\n", + "##utable\n", + "##lei\n", + "##space\n", + "##aris\n", + "##vern\n", + "##mento\n", + "##alo\n", + "##skaya\n", + "##eses\n", + "##kyu\n", + "##lance\n", + "##oslav\n", + "##urable\n", + "##tagram\n", + "##aman\n", + "##cloth\n", + "##tite\n", + "##jou\n", + "##linger\n", + "##tze\n", + "##hism\n", + "##inn\n", + "##leg\n", + "##tek\n", + "##uttered\n", + "##igraphy\n", + "##istan\n", + "##firmed\n", + "##rien\n", + "##yes\n", + "##nington\n", + "##eran\n", + "##cking\n", + "##inging\n", + "##crat\n", + "##typic\n", + "##dit\n", + "##runner\n", + "##tower\n", + "##bbing\n", + "##inator\n", + "##lford\n", + "##oki\n", + "##zoo\n", + "##lto\n", + "##sov\n", + "##cript\n", + "##codes\n", + "##emi\n", + "##ungen\n", + "##bled\n", + "##giri\n", + "##ciation\n", + "##ropolis\n", + "##ales\n", + "##pid\n", + "##pit\n", + "##yse\n", + "##aha\n", + "##erin\n", + "##gl\n", + "##paper\n", + "##free\n", + "##physical\n", + "##sław\n", + "##inia\n", + "##lce\n", + "##ulsion\n", + "##ryl\n", + "##drich\n", + "##kot\n", + "##mple\n", + "##sons\n", + "##virus\n", + "##75\n", + "##tized\n", + "##mind\n", + "##iaceae\n", + "##uet\n", + "##thermal\n", + "##lbert\n", + "##oese\n", + "##ssler\n", + "##hom\n", + "##tangle\n", + "##lmer\n", + "##cie\n", + "##holding\n", + "##hoot\n", + "##redo\n", + "##mite\n", + "##ango\n", + "##crats\n", + "##wice\n", + "##ː\n", + "##ntation\n", + "##reus\n", + "##lak\n", + "##fine\n", + "##oked\n", + "##block\n", + "##tology\n", + "##ия\n", + "##vyn\n", + "##cycle\n", + "##isse\n", + "##inge\n", + "##39\n", + "##nni\n", + "##ault\n", + "##fell\n", + "##farlane\n", + "##olic\n", + "##ices\n", + "##rians\n", + "##brand\n", + "##sume\n", + "##arns\n", + "##icing\n", + "##oche\n", + "##eving\n", + "##oise\n", + "##tell\n", + "##hani\n", + "##mada\n", + "##ctable\n", + "##enham\n", + "##chio\n", + "##neo\n", + "##dak\n", + "##ept\n", + "##kit\n", + "##kir\n", + "##41\n", + "##clusive\n", + "##hh\n", + "##romatic\n", + "##clave\n", + "##train\n", + "##essed\n", + "##castle\n", + "##drive\n", + "##ifice\n", + "##film\n", + "##buro\n", + "##ratic\n", + "##ل\n", + "##dote\n", + "##body\n", + "##ago\n", + "##finder\n", + "##llie\n", + "##bh\n", + "##oun\n", + "##sul\n", + "##ality\n", + "##bri\n", + "##genesis\n", + "##mist\n", + "##ь\n", + "##lou\n", + "##wives\n", + "##zyn\n", + "##bation\n", + "##ign\n", + "##43\n", + "##rika\n", + "##ifer\n", + "##ading\n", + "##iec\n", + "##region\n", + "##kker\n", + "##giving\n", + "##schen\n", + "##rase\n", + "##cano\n", + "##apple\n", + "##gai\n", + "##git\n", + "##nst\n", + "##stor\n", + "##thed\n", + "##sau\n", + "##kovsky\n", + "##elman\n", + "##26\n", + "##door\n", + "##sell\n", + "##orne\n", + "##nated\n", + "##lz\n", + "##cend\n", + "##arty\n", + "##sphere\n", + "##wala\n", + "##oge\n", + "##cure\n", + "##break\n", + "##ilde\n", + "##haling\n", + "##fixed\n", + "##unas\n", + "##ocation\n", + "##lkirk\n", + "##elling\n", + "##ogen\n", + "##к\n", + "##iferous\n", + "##mbled\n", + "##hita\n", + "##inda\n", + "##zee\n", + "##eke\n", + "##yla\n", + "##pack\n", + "##powering\n", + "##skie\n", + "##berman\n", + "##utus\n", + "##ining\n", + "##tlement\n", + "##nish\n", + "##zuki\n", + "##flies\n", + "##isha\n", + "##eller\n", + "##nary\n", + "##nee\n", + "##gist\n", + "##ape\n", + "##dick\n", + "##rera\n", + "##nut\n", + "##pment\n", + "##anu\n", + "##isson\n", + "##amy\n", + "##ckman\n", + "##zell\n", + "##55\n", + "##mable\n", + "##thal\n", + "##drick\n", + "##vira\n", + "##01\n", + "##rting\n", + "##unciation\n", + "##♭\n", + "##kki\n", + "##icia\n", + "##lusion\n", + "##usia\n", + "##hesis\n", + "##pressing\n", + "##leen\n", + "##uating\n", + "##sso\n", + "##thes\n", + "##eras\n", + "##gol\n", + "##kow\n", + "##asian\n", + "##good\n", + "##zano\n", + "##iculate\n", + "##his\n", + "##oco\n", + "##alle\n", + "##stered\n", + "##tters\n", + "##grade\n", + "##oped\n", + "##rza\n", + "##ellant\n", + "##hay\n", + "##kken\n", + "##lide\n", + "##bbly\n", + "##buck\n", + "##bah\n", + "##dust\n", + "##lova\n", + "##edge\n", + "##erine\n", + "##lty\n", + "##chemist\n", + "##connected\n", + "##ump\n", + "##main\n", + "##istle\n", + "##aster\n", + "##uming\n", + "##ential\n", + "##logue\n", + "##ogenic\n", + "##sities\n", + "##wat\n", + "##mide\n", + "##orra\n", + "##bola\n", + "##dget\n", + "##rith\n", + "##wark\n", + "##iny\n", + "##tracted\n", + "##overs\n", + "##oshi\n", + "##cot\n", + "##layer\n", + "##fk\n", + "##itas\n", + "##say\n", + "##foil\n", + "##metry\n", + "##pic\n", + "##fast\n", + "##ym\n", + "##enne\n", + "##zman\n", + "##raph\n", + "##patient\n", + "##meyer\n", + "##river\n", + "##eil\n", + "##nting\n", + "##cona\n", + "##crow\n", + "##mare\n", + "##feng\n", + "##uary\n", + "##rang\n", + "##torium\n", + "##laid\n", + "##ergy\n", + "##fers\n", + "##enna\n", + "##achal\n", + "##creen\n", + "##ilis\n", + "##lins\n", + "##rence\n", + "##with\n", + "##ception\n", + "##furt\n", + "##minster\n", + "##37\n", + "##llary\n", + "##landa\n", + "##rage\n", + "##ener\n", + "##jected\n", + "##trum\n", + "##bill\n", + "##lta\n", + "##dek\n", + "##laze\n", + "##tf\n", + "##ischen\n", + "##around\n", + "##kat\n", + "##zek\n", + "##ffey\n", + "##vara\n", + "##tute\n", + "##mmon\n", + "##lese\n", + "##uding\n", + "##helm\n", + "##pipe\n", + "##enary\n", + "##phate\n", + "##chon\n", + "##dora\n", + "##hur\n", + "##lding\n", + "##corp\n", + "##elial\n", + "##dened\n", + "##29\n", + "##bek\n", + "##dice\n", + "##dez\n", + "##ivision\n", + "##mori\n", + "##dier\n", + "##naut\n", + "##utnant\n", + "##ardo\n", + "##havan\n", + "##ives\n", + "##aldi\n", + "##lth\n", + "##ehan\n", + "##puri\n", + "##poulos\n", + "##poo\n", + "##trust\n", + "##opus\n", + "##ggle\n", + "##vao\n", + "##icate\n", + "##bn\n", + "##jm\n", + "##rill\n", + "##sius\n", + "##litz\n", + "##loh\n", + "##teacher\n", + "##ege\n", + "##oca\n", + "##pl\n", + "##keepers\n", + "##osed\n", + "##rys\n", + "##iring\n", + "##shima\n", + "##oum\n", + "##tish\n", + "##vres\n", + "##joy\n", + "##ignon\n", + "##mg\n", + "##urai\n", + "##mana\n", + "##ctors\n", + "##η\n", + "##ulio\n", + "##tou\n", + "##ی\n", + "##iens\n", + "##ignment\n", + "##dev\n", + "##arte\n", + "##gul\n", + "##held\n", + "##grin\n", + "##kou\n", + "##phile\n", + "##gara\n", + "##quisite\n", + "##vity\n", + "##jord\n", + "##valent\n", + "##koto\n", + "##vac\n", + "##onus\n", + "##cum\n", + "##scopic\n", + "##trip\n", + "##standing\n", + "##lessness\n", + "##dran\n", + "##logram\n", + "##boys\n", + "##kushima\n", + "##vious\n", + "##phobia\n", + "##chai\n", + "##gang\n", + "##ater\n", + "##lassified\n", + "##pati\n", + "##ginal\n", + "##straße\n", + "##vish\n", + "##ptive\n", + "##dur\n", + "##antes\n", + "##rral\n", + "##ggles\n", + "##omba\n", + "##ament\n", + "##uen\n", + "##rrick\n", + "##lase\n", + "##jic\n", + "##tonic\n", + "##promising\n", + "##cala\n", + "##sle\n", + "##lang\n", + "##dication\n", + "##fed\n", + "##rh\n", + "##oza\n", + "##woods\n", + "##linson\n", + "##mming\n", + "##ouin\n", + "##bala\n", + "##dda\n", + "##eased\n", + "##oides\n", + "##rdial\n", + "##rke\n", + "##thesis\n", + "##nob\n", + "##tically\n", + "##mined\n", + "##iti\n", + "##tler\n", + "##iente\n", + "##ulum\n", + "##tip\n", + "##lley\n", + "##iam\n", + "##dson\n", + "##ower\n", + "##anger\n", + "##laise\n", + "##bour\n", + "##icle\n", + "##urity\n", + "##lux\n", + "##yad\n", + "##bang\n", + "##claim\n", + "##erving\n", + "##uing\n", + "##amps\n", + "##sund\n", + "##xious\n", + "##tops\n", + "##icative\n", + "##iot\n", + "##dberg\n", + "##nified\n", + "##adia\n", + "##vite\n", + "##yme\n", + "##lino\n", + "##hosis\n", + "##lick\n", + "##ophone\n", + "##arable\n", + "##jure\n", + "##esian\n", + "##phus\n", + "##brates\n", + "##ritan\n", + "##erative\n", + "##zai\n", + "##hae\n", + "##imov\n", + "##mini\n", + "##rso\n", + "##taken\n", + "##nh\n", + "##crest\n", + "##ntino\n", + "##chester\n", + "##optera\n", + "##dara\n", + "##esthesia\n", + "##ior\n", + "##basket\n", + "##umatic\n", + "##cek\n", + "##mps\n", + "##orous\n", + "##omp\n", + "##ports\n", + "##tream\n", + "##deh\n", + "##ocks\n", + "##yson\n", + "##nad\n", + "##cius\n", + "##gli\n", + "##rook\n", + "##anov\n", + "##acker\n", + "##lika\n", + "##alla\n", + "##som\n", + "##national\n", + "##umb\n", + "##agne\n", + "##nessy\n", + "##iani\n", + "##osphere\n", + "##champ\n", + "##itan\n", + "##athi\n", + "##hab\n", + "##kong\n", + "##oia\n", + "##nail\n", + "##vc\n", + "##dity\n", + "##riated\n", + "##mission\n", + "##tort\n", + "##caster\n", + "##gman\n", + "##khov\n", + "##tively\n", + "##vio\n", + "##eak\n", + "##kt\n", + "##dance\n", + "##nig\n", + "##bham\n", + "##ference\n", + "##omics\n", + "##bm\n", + "##tropical\n", + "##в\n", + "##meric\n", + "##raction\n", + "##ige\n", + "##shida\n", + "##rde\n", + "##glers\n", + "##ssar\n", + "##riam\n", + "##aceous\n", + "##rard\n", + "##nsk\n", + "##cta\n", + "##ا\n", + "##mund\n", + "##quay\n", + "##uses\n", + "##ieving\n", + "##oven\n", + "##ignant\n", + "##peed\n", + "##sack\n", + "##fus\n", + "##shah\n", + "##hg\n", + "##sboro\n", + "##hunter\n", + "##dhar\n", + "##ctuated\n", + "##eaux\n", + "##gly\n", + "##brick\n", + "##stead\n", + "##nzo\n", + "##nsky\n", + "##tson\n", + "##9th\n", + "##movable\n", + "##mad\n", + "##rao\n", + "##yeh\n", + "##islaus\n", + "##shaft\n", + "##tyn\n", + "##mah\n", + "##yd\n", + "##eland\n", + "##tino\n", + "##itarian\n", + "##gui\n", + "##ausen\n", + "##gf\n", + "##rize\n", + "##drop\n", + "##ross\n", + "##bry\n", + "##ezer\n", + "##52\n", + "##gpur\n", + "##ivation\n", + "##belle\n", + "##osaurus\n", + "##col\n", + "##lving\n", + "##oint\n", + "##jal\n", + "##anna\n", + "##ocene\n", + "##orestation\n", + "##hiff\n", + "##باد\n", + "##nka\n", + "##sight\n", + "##tens\n", + "##cey\n", + "##yin\n", + "##llas\n", + "##building\n", + "##arney\n", + "##nem\n", + "##dya\n", + "##lellan\n", + "##nded\n", + "##routed\n", + "##hog\n", + "##smo\n", + "##tp\n", + "##rger\n", + "##oton\n", + "##urance\n", + "##ayan\n", + "##chenko\n", + "##arat\n", + "##dern\n", + "##lete\n", + "##rgen\n", + "##vered\n", + "##analysis\n", + "##awan\n", + "##khand\n", + "##vard\n", + "##nden\n", + "##dana\n", + "##oper\n", + "##chee\n", + "##vies\n", + "##resses\n", + "##pathic\n", + "##erved\n", + "##osity\n", + "##tosis\n", + "##cchi\n", + "##raus\n", + "##lham\n", + "##fect\n", + "##tten\n", + "##uw\n", + "##buch\n", + "##bari\n", + "##6th\n", + "##ngen\n", + "##ece\n", + "##ely\n", + "##edo\n", + "##irus\n", + "##wad\n", + "##kato\n", + "##dicated\n", + "##pon\n", + "##anian\n", + "##hei\n", + "##dini\n", + "##erina\n", + "##partisan\n", + "##itha\n", + "##vius\n", + "##channel\n", + "##vera\n", + "##tila\n", + "##tang\n", + "##bai\n", + "##phila\n", + "##kla\n", + "##lland\n", + "##nche\n", + "##dee\n", + "##hide\n", + "##haya\n", + "##itical\n", + "##utation\n", + "##ropriation\n", + "##koff\n", + "##scope\n", + "##vez\n", + "##ructured\n", + "##yat\n", + "##tight\n", + "##ographer\n", + "##quil\n", + "##nare\n", + "##zard\n", + "##odle\n", + "##naud\n", + "##fting\n", + "##dome\n", + "##otted\n", + "##65\n", + "##carbon\n", + "##estra\n", + "##chua\n", + "##edly\n", + "##sur\n", + "##sma\n", + "##acing\n", + "##49\n", + "##hair\n", + "##raphy\n", + "##lver\n", + "##uy\n", + "##ounded\n", + "##cit\n", + "##meo\n", + "##oire\n", + "##roved\n", + "##lative\n", + "##class\n", + "##yles\n", + "##bio\n", + "##cola\n", + "##wk\n", + "##orno\n", + "##chase\n", + "##tua\n", + "##otype\n", + "##×\n", + "##tructing\n", + "##eger\n", + "##etz\n", + "##ttle\n", + "##fires\n", + "##adan\n", + "##ciful\n", + "##fb\n", + "##slow\n", + "##ials\n", + "##tford\n", + "##tick\n", + "##onga\n", + "##heard\n", + "##khan\n", + "##rdes\n", + "##write\n", + "##bians\n", + "##hri\n", + "##ndt\n", + "##monium\n", + "##orough\n", + "##games\n", + "##lysis\n", + "##beau\n", + "##dalen\n", + "##hila\n", + "##nai\n", + "##qual\n", + "##rford\n", + "##mei\n", + "##rnik\n", + "##hedron\n", + "##hope\n", + "##ʻi\n", + "##ags\n", + "##iner\n", + "##raine\n", + "##wright\n", + "##copic\n", + "##ador\n", + "##camp\n", + "##enas\n", + "##vating\n", + "##ears\n", + "##vb\n", + "##zd\n", + "##hein\n", + "##chuk\n", + "##gami\n", + "##lka\n", + "##points\n", + "##tov\n", + "##aar\n", + "##schaft\n", + "##vino\n", + "##eron\n", + "##iography\n", + "##jia\n", + "##suka\n", + "##deck\n", + "##vill\n", + "##rug\n", + "##tec\n", + "##dorff\n", + "##hear\n", + "##rogated\n", + "##pani\n", + "##rissa\n", + "##rnet\n", + "##eki\n", + "##kson\n", + "##lewood\n", + "##rval\n", + "##gata\n", + "##biotic\n", + "##ettes\n", + "##otide\n", + "##runa\n", + "##umble\n", + "##roller\n", + "##bright\n", + "##uance\n", + "##planes\n", + "##esses\n", + "##ductive\n", + "##unes\n", + "##cans\n", + "##hosh\n", + "##lifting\n", + "##sation\n", + "##christ\n", + "##llins\n", + "##ibar\n", + "##balance\n", + "##uso\n", + "##emy\n", + "##felt\n", + "##wt\n", + "##blood\n", + "##aghan\n", + "##verted\n", + "##ythe\n", + "##pore\n", + "##roi\n", + "##unds\n", + "##tage\n", + "##venting\n", + "##vances\n", + "##gical\n", + "##4th\n", + "##mism\n", + "##ntine\n", + "##neas\n", + "##eles\n", + "##eurs\n", + "##gno\n", + "##mute\n", + "##ances\n", + "##sw\n", + "##rank\n", + "##rder\n", + "##missible\n", + "##cr\n", + "##jevic\n", + "##lates\n", + "##pina\n", + "##rona\n", + "##ου\n", + "##gative\n", + "##mpton\n", + "##dou\n", + "##rries\n", + "##anta\n", + "##venor\n", + "##nx\n", + "##bags\n", + "##tsky\n", + "##nally\n", + "##ths\n", + "##lved\n", + "##hmi\n", + "##loe\n", + "##mage\n", + "##sily\n", + "##cute\n", + "##md\n", + "##strel\n", + "##utter\n", + "##ractive\n", + "##rkin\n", + "##coll\n", + "##lun\n", + "##tance\n", + "##mental\n", + "##kala\n", + "##rization\n", + "##open\n", + "##ruff\n", + "##entes\n", + "##emon\n", + "##nist\n", + "##mack\n", + "##jured\n", + "##parts\n", + "##enting\n", + "##pg\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "##walker\n", + "##going\n", + "##minated\n", + "##56\n", + "##gnon\n", + "##igny\n", + "##growth\n", + "##ywood\n", + "##ffi\n", + "##rdan\n", + "##kney\n", + "##position\n", + "##dlow\n", + "##54\n", + "##mania\n", + "##bots\n", + "##evsky\n", + "##uis\n", + "##americana\n", + "##dding\n", + "##inton\n", + "##nage\n", + "##rret\n", + "##bread\n", + "##rrier\n", + "##kam\n", + "##tea\n", + "##ditional\n", + "##het\n", + "##udged\n", + "##lash\n", + "##alic\n", + "##gaon\n", + "##cide\n", + "##cini\n", + "##typical\n", + "##viere\n", + "##logie\n", + "##itte\n", + "##lass\n", + "##lists\n", + "##cor\n", + "##nosis\n", + "##tsa\n", + "##icio\n", + "##rney\n", + "##tara\n", + "##dates\n", + "##aia\n", + "##mum\n", + "##oys\n", + "##wehr\n", + "##lind\n", + "##lone\n", + "##rgh\n", + "##oons\n", + "##urgent\n", + "##logic\n", + "##dial\n", + "##hered\n", + "##usly\n", + "##cous\n", + "##egorical\n", + "##weig\n", + "##scia\n", + "##uh\n", + "##efe\n", + "##isches\n", + "##asse\n", + "##earing\n", + "##amen\n", + "##bund\n", + "##lad\n", + "##powered\n", + "##yst\n", + "##ctum\n", + "##music\n", + "##neil\n", + "##washed\n", + "##itors\n", + "##opped\n", + "##arm\n", + "##plicity\n", + "##onis\n", + "##hedral\n", + "##vana\n", + "##aldo\n", + "##cytes\n", + "##hopper\n", + "##izan\n", + "##graphs\n", + "##opers\n", + "##uven\n", + "##listic\n", + "##rwin\n", + "##erik\n", + "##tify\n", + "##bson\n", + "##eros\n", + "##rained\n", + "##rath\n", + "##dot\n", + "##rbin\n", + "##marks\n", + "##gart\n", + "##kota\n", + "##oder\n", + "##phonic\n", + "##gur\n", + "##odies\n", + "##⁄₄\n", + "##tness\n", + "##ety\n", + "##hone\n", + "##liche\n", + "##nator\n", + "##nery\n", + "##orio\n", + "##umen\n", + "##cb\n", + "##oted\n", + "##titles\n", + "##tura\n", + "##ια\n", + "##frid\n", + "##grants\n", + "##tative\n", + "##cave\n", + "##oses\n", + "##sions\n", + "##ople\n", + "##rsk\n", + "##offs\n", + "##ammed\n", + "##ocating\n", + "##pressive\n", + "##cm\n", + "##kshi\n", + "##bold\n", + "##vus\n", + "##rled\n", + "##7th\n", + "##hid\n", + "##rmin\n", + "##cen\n", + "##raf\n", + "##85\n", + "##anial\n", + "##abas\n", + "##bane\n", + "##arion\n", + "##erian\n", + "##ired\n", + "##sil\n", + "##akh\n", + "##person\n", + "##pants\n", + "##cliff\n", + "##ulent\n", + "##dun\n", + "##inium\n", + "##zic\n", + "##urer\n", + "##imi\n", + "##lita\n", + "##agger\n", + "##lynn\n", + "##rigue\n", + "##eborg\n", + "##uram\n", + "##breakers\n", + "##udeau\n", + "##hony\n", + "##ccus\n", + "##mounted\n", + "##pod\n", + "##eche\n", + "##claiming\n", + "##osomal\n", + "##amina\n", + "##scent\n", + "##fleet\n", + "##ppy\n", + "##lowe\n", + "##nio\n", + "##bbon\n", + "##jian\n", + "##jean\n", + "##øy\n", + "##hearted\n", + "##spar\n", + "##nb\n", + "##uria\n", + "##vinsky\n", + "##fera\n", + "##loid\n", + "##mous\n", + "##a1\n", + "##mpt\n", + "##swick\n", + "##enay\n", + "##nsed\n", + "##hly\n", + "##wyl\n", + "##encia\n", + "##hyllum\n", + "##masters\n", + "##fat\n", + "##pour\n", + "##mium\n", + "##vani\n", + "##hli\n", + "##wg\n", + "##bau\n", + "##version\n", + "##hort\n", + "##chison\n", + "##hiti\n", + "##nnis\n", + "##iensis\n", + "##raße\n", + "##58\n", + "##atal\n", + "##uno\n", + "##iji\n", + "##dles\n", + "##terol\n", + "##rasia\n", + "##riety\n", + "##fra\n", + "##thor\n", + "##heater\n", + "##mering\n", + "##ilia\n", + "##aer\n", + "##anor\n", + "##iste\n", + "##may\n", + "##oue\n", + "##jad\n", + "##missive\n", + "##ppel\n", + "##gnant\n", + "##lga\n", + "##atable\n", + "##idad\n", + "##ols\n", + "##ouring\n", + "##tangled\n", + "##very\n", + "##lette\n", + "##sden\n", + "##¹\n", + "##olt\n", + "##pins\n", + "##gut\n", + "##pher\n", + "##zh\n", + "##rok\n", + "##boot\n", + "##liffe\n", + "##minating\n", + "##rrado\n", + "##fur\n", + "##arina\n", + "##−1\n", + "##herton\n", + "##anal\n", + "##eia\n", + "##lub\n", + "##bilis\n", + "##cz\n", + "##ouk\n", + "##aina\n", + "##firm\n", + "##anum\n", + "##bbies\n", + "##tyle\n", + "##nction\n", + "##dner\n", + "##edging\n", + "##hane\n", + "##iy\n", + "##talk\n", + "##nais\n", + "##olf\n", + "##reen\n", + "##sit\n", + "##arded\n", + "##aday\n", + "##onte\n", + "##tained\n", + "##lez\n", + "##lho\n", + "##anies\n", + "##bib\n", + "##falls\n", + "##harat\n", + "##week\n", + "##eries\n", + "##uously\n", + "##ahl\n", + "##pee\n", + "##ddled\n", + "##holz\n", + "##iction\n", + "##cheon\n", + "##oit\n", + "##neuve\n", + "##ipes\n", + "##recht\n", + "##nism\n", + "##zumi\n", + "##riders\n", + "##ados\n", + "##mament\n", + "##mut\n", + "##rud\n", + "##laus\n", + "##ksha\n", + "##imeters\n", + "##isance\n", + "##pre\n", + "##ronia\n", + "##lke\n", + "##tablished\n", + "##scoe\n", + "##59\n", + "##taro\n", + "##cuit\n", + "##idi\n", + "##rdon\n", + "##grating\n", + "##inates\n", + "##asco\n", + "##ecin\n", + "##kovich\n", + "##ently\n", + "##nostic\n", + "##ttal\n", + "##idon\n", + "##gnan\n", + "##ikh\n", + "##dant\n", + "##rons\n", + "##lary\n", + "##mara\n", + "##iciencies\n", + "##rti\n", + "##inatory\n", + "##ssion\n", + "##inga\n", + "##lism\n", + "##ately\n", + "##rgeon\n", + "##ains\n", + "##plify\n", + "##tub\n", + "##chner\n", + "##sibility\n", + "##kura\n", + "##oulos\n", + "##8th\n", + "##tched\n", + "##lateral\n", + "##pps\n", + "##tama\n", + "##ifiers\n", + "##plin\n", + "##quitable\n", + "##beam\n", + "##sitor\n", + "##57\n", + "##cton\n", + "##tees\n", + "##rran\n", + "##asurable\n", + "##fles\n", + "##200\n", + "##iance\n", + "##efined\n", + "##till\n", + "##duk\n", + "##nished\n", + "##hre\n", + "##wled\n", + "##arians\n", + "##zos\n", + "##yck\n", + "##gingly\n", + "##urse\n", + "##wee\n", + "##mies\n", + "##pw\n", + "##roll\n", + "##vita\n", + "##urized\n", + "##taka\n", + "##rito\n", + "##ij\n", + "##uls\n", + "##zily\n", + "##hema\n", + "##tique\n", + "##avio\n", + "##cision\n", + "##tray\n", + "##lden\n", + "##maid\n", + "##oxide\n", + "##rba\n", + "##rnier\n", + "##ually\n", + "##otte\n", + "##hett\n", + "##omorphic\n", + "##zog\n", + "##bula\n", + "##lithic\n", + "##rada\n", + "##abi\n", + "##bla\n", + "##icon\n", + "##lvis\n", + "##rest\n", + "##rzy\n", + "##kian\n", + "##utive\n", + "##rmi\n", + "##rued\n", + "##enes\n", + "##tao\n", + "##wash\n", + "##inkles\n", + "##kiewicz\n", + "##ando\n", + "##rem\n", + "##ffled\n", + "##uising\n", + "##guide\n", + "##vron\n", + "##imum\n", + "##rrow\n", + "##ка\n", + "##hum\n", + "##orth\n", + "##kali\n", + "##veda\n", + "##yala\n", + "##cana\n", + "##sure\n", + "##gree\n", + "##eza\n", + "##mation\n", + "##vitt\n", + "##clops\n", + "##gizing\n", + "##iad\n", + "##filtration\n", + "##merie\n", + "##dgets\n", + "##ceptive\n", + "##para\n", + "##lars\n", + "##osta\n", + "##oux\n", + "##culus\n", + "##lais\n", + "##qvist\n", + "##rrigan\n", + "##odon\n", + "##lastic\n", + "##cam\n", + "##erted\n", + "##drik\n", + "##igate\n", + "##mise\n", + "##zbek\n", + "##istles\n", + "##ivar\n", + "##orin\n", + "##idium\n", + "##sg\n", + "##cina\n", + "##etano\n", + "##zzy\n", + "##66\n", + "##bedo\n", + "##oin\n", + "##ici\n", + "##endez\n", + "##ocytes\n", + "##sop\n", + "##actic\n", + "##baldi\n", + "##bular\n", + "##ensburg\n", + "##itung\n", + "##scu\n", + "##ound\n", + "##personal\n", + "##meister\n", + "##nberger\n", + "##ricting\n", + "##dilly\n", + "##genase\n", + "##erre\n", + "##ayo\n", + "##lizer\n", + "##ajan\n", + "##kulam\n", + "##ieg\n", + "##lge\n", + "##mbit\n", + "##suit\n", + "##miento\n", + "##rites\n", + "##sling\n", + "##ghi\n", + "##rations\n", + "##tarian\n", + "##duced\n", + "##ragan\n", + "##dna\n", + "##rga\n", + "##tlan\n", + "##lized\n", + "##qu\n", + "##vere\n", + "##jali\n", + "##weather\n", + "##grounds\n", + "##iii\n", + "##nbc\n", + "##escence\n", + "##flight\n", + "##cased\n", + "##tula\n", + "##fahan\n", + "##bruck\n", + "##dents\n", + "##nami\n", + "##hner\n", + "##meral\n", + "##isen\n", + "##ometric\n", + "##pres\n", + "##ан\n", + "##jhl\n", + "##zko\n", + "##lten\n", + "##rcus\n", + "##section\n", + "##rooms\n", + "##formed\n", + "##lok\n", + "##stellar\n", + "##mmel\n", + "##abia\n", + "##apes\n", + "##chaft\n", + "##dav\n", + "##ooping\n", + "##tension\n", + "##itia\n", + "##ffie\n", + "##tsk\n", + "##onda\n", + "##tiv\n", + "##rvis\n", + "##gni\n", + "##mberg\n", + "##urian\n", + "##wani\n", + "##3d\n", + "##app\n", + "##oed\n", + "##year\n", + "##ega\n", + "##cel\n", + "##enter\n", + "##oles\n", + "##oteric\n", + "##ы\n", + "##hem\n", + "##kata\n", + "##ciency\n", + "##ה\n", + "##arus\n", + "##mussen\n", + "##nidae\n", + "##rzburg\n", + "##ingdon\n", + "##tituted\n", + "##lices\n", + "##oj\n", + "##bain\n", + "##ecure\n", + "##arding\n", + "##ης\n", + "##andra\n", + "##broken\n", + "##cuting\n", + "##iface\n", + "##ror\n", + "##rosis\n", + "##drome\n", + "##ioms\n", + "##oric\n", + "##rag\n", + "##ckey\n", + "##trix\n", + "##stems\n", + "##uder\n", + "##nivorous\n", + "##isan\n", + "##dict\n", + "##igen\n", + "##vna\n", + "##zziness\n", + "##eft\n", + "##mbs\n", + "##scribe\n", + "##aks\n", + "##ifolia\n", + "##athan\n", + "##zle\n", + "##pse\n", + "##mbling\n", + "##urrent\n", + "##izzly\n", + "##ɛ\n", + "##for\n", + "##elis\n", + "##folk\n", + "##lwyn\n", + "##otho\n", + "##saka\n", + "##bf\n", + "##itative\n", + "##yce\n", + "##flict\n", + "##miya\n", + "##reate\n", + "##ruck\n", + "##tucket\n", + "##ayton\n", + "##cence\n", + "##ife\n", + "##bber\n", + "##skin\n", + "##tat\n", + "##you\n", + "##nir\n", + "##idia\n", + "##inho\n", + "##500\n", + "##rise\n", + "##lovic\n", + "##lch\n", + "##urities\n", + "##dermott\n", + "##inking\n", + "##scan\n", + "##ostal\n", + "##owe\n", + "##bner\n", + "##rchy\n", + "##systems\n", + "##trics\n", + "##gration\n", + "##olio\n", + "##urst\n", + "##nty\n", + "##cultural\n", + "##quette\n", + "##ssed\n", + "##tma\n", + "##zcz\n", + "##itaire\n", + "##stones\n", + "##udence\n", + "##just\n", + "##nsen\n", + "##л\n", + "##umber\n", + "##upt\n", + "##rip\n", + "##bution\n", + "##gano\n", + "##onzo\n", + "##orro\n", + "##puted\n", + "##tori\n", + "##stis\n", + "##stov\n", + "##opa\n", + "##glio\n", + "##sir\n", + "##peration\n", + "##uez\n", + "##kic\n", + "##kei\n", + "##ducted\n", + "##pone\n", + "##roids\n", + "##jing\n", + "##ppet\n", + "##lib\n", + "##ssee\n", + "##pkins\n", + "##400\n", + "##bley\n", + "##raya\n", + "##rmed\n", + "##ailing\n", + "##ilation\n", + "##tzer\n", + "##uppe\n", + "##werk\n", + "##avs\n", + "##ands\n", + "##rco\n", + "##dion\n", + "##etched\n", + "##lster\n", + "##nsor\n", + "##toy\n", + "##ticus\n", + "##urbed\n", + "##hyl\n", + "##rrard\n", + "##waite\n", + "##wil\n", + "##bant\n", + "##edance\n", + "##!\n", + "##\"\n", + "###\n", + "##$\n", + "##%\n", + "##&\n", + "##'\n", + "##(\n", + "##)\n", + "##*\n", + "##+\n", + "##,\n", + "##-\n", + "##.\n", + "##/\n", + "##:\n", + "##;\n", + "##<\n", + "##=\n", + "##>\n", + "##?\n", + "##@\n", + "##[\n", + "##\\\n", + "##]\n", + "##^\n", + "##_\n", + "##`\n", + "##{\n", + "##|\n", + "##}\n", + "##~\n", + "##¡\n", + "##¢\n", + "##£\n", + "##¤\n", + "##¥\n", + "##¦\n", + "##§\n", + "##¨\n", + "##©\n", + "##ª\n", + "##«\n", + "##¬\n", + "##®\n", + "##±\n", + "##´\n", + "##µ\n", + "##¶\n", + "##·\n", + "##º\n", + "##»\n", + "##¼\n", + "##¾\n", + "##¿\n", + "##æ\n", + "##ð\n", + "##÷\n", + "##þ\n", + "##đ\n", + "##ħ\n", + "##ŋ\n", + "##œ\n", + "##ƒ\n", + "##ɐ\n", + "##ɑ\n", + "##ɒ\n", + "##ɔ\n", + "##ɕ\n", + "##ə\n", + "##ɡ\n", + "##ɣ\n", + "##ɨ\n", + "##ɪ\n", + "##ɫ\n", + "##ɬ\n", + "##ɯ\n", + "##ɲ\n", + "##ɴ\n", + "##ɹ\n", + "##ɾ\n", + "##ʀ\n", + "##ʁ\n", + "##ʂ\n", + "##ʃ\n", + "##ʉ\n", + "##ʊ\n", + "##ʋ\n", + "##ʌ\n", + "##ʎ\n", + "##ʐ\n", + "##ʑ\n", + "##ʒ\n", + "##ʔ\n", + "##ʰ\n", + "##ʲ\n", + "##ʳ\n", + "##ʷ\n", + "##ʸ\n", + "##ʻ\n", + "##ʼ\n", + "##ʾ\n", + "##ʿ\n", + "##ˈ\n", + "##ˡ\n", + "##ˢ\n", + "##ˣ\n", + "##ˤ\n", + "##β\n", + "##γ\n", + "##δ\n", + "##ε\n", + "##ζ\n", + "##θ\n", + "##κ\n", + "##λ\n", + "##μ\n", + "##ξ\n", + "##ο\n", + "##π\n", + "##ρ\n", + "##σ\n", + "##τ\n", + "##υ\n", + "##φ\n", + "##χ\n", + "##ψ\n", + "##ω\n", + "##б\n", + "##г\n", + "##д\n", + "##ж\n", + "##з\n", + "##м\n", + "##п\n", + "##с\n", + "##у\n", + "##ф\n", + "##х\n", + "##ц\n", + "##ч\n", + "##ш\n", + "##щ\n", + "##ъ\n", + "##э\n", + "##ю\n", + "##ђ\n", + "##є\n", + "##і\n", + "##ј\n", + "##љ\n", + "##њ\n", + "##ћ\n", + "##ӏ\n", + "##ա\n", + "##բ\n", + "##գ\n", + "##դ\n", + "##ե\n", + "##թ\n", + "##ի\n", + "##լ\n", + "##կ\n", + "##հ\n", + "##մ\n", + "##յ\n", + "##ն\n", + "##ո\n", + "##պ\n", + "##ս\n", + "##վ\n", + "##տ\n", + "##ր\n", + "##ւ\n", + "##ք\n", + "##־\n", + "##א\n", + "##ב\n", + "##ג\n", + "##ד\n", + "##ו\n", + "##ז\n", + "##ח\n", + "##ט\n", + "##י\n", + "##ך\n", + "##כ\n", + "##ל\n", + "##ם\n", + "##מ\n", + "##ן\n", + "##נ\n", + "##ס\n", + "##ע\n", + "##ף\n", + "##פ\n", + "##ץ\n", + "##צ\n", + "##ק\n", + "##ר\n", + "##ש\n", + "##ת\n", + "##،\n", + "##ء\n", + "##ب\n", + "##ت\n", + "##ث\n", + "##ج\n", + "##ح\n", + "##خ\n", + "##ذ\n", + "##ز\n", + "##س\n", + "##ش\n", + "##ص\n", + "##ض\n", + "##ط\n", + "##ظ\n", + "##ع\n", + "##غ\n", + "##ـ\n", + "##ف\n", + "##ق\n", + "##ك\n", + "##و\n", + "##ى\n", + "##ٹ\n", + "##پ\n", + "##چ\n", + "##ک\n", + "##گ\n", + "##ں\n", + "##ھ\n", + "##ہ\n", + "##ے\n", + "##अ\n", + "##आ\n", + "##उ\n", + "##ए\n", + "##क\n", + "##ख\n", + "##ग\n", + "##च\n", + "##ज\n", + "##ट\n", + "##ड\n", + "##ण\n", + "##त\n", + "##थ\n", + "##द\n", + "##ध\n", + "##न\n", + "##प\n", + "##ब\n", + "##भ\n", + "##म\n", + "##य\n", + "##र\n", + "##ल\n", + "##व\n", + "##श\n", + "##ष\n", + "##स\n", + "##ह\n", + "##ा\n", + "##ि\n", + "##ी\n", + "##ो\n", + "##।\n", + "##॥\n", + "##ং\n", + "##অ\n", + "##আ\n", + "##ই\n", + "##উ\n", + "##এ\n", + "##ও\n", + "##ক\n", + "##খ\n", + "##গ\n", + "##চ\n", + "##ছ\n", + "##জ\n", + "##ট\n", + "##ড\n", + "##ণ\n", + "##ত\n", + "##থ\n", + "##দ\n", + "##ধ\n", + "##ন\n", + "##প\n", + "##ব\n", + "##ভ\n", + "##ম\n", + "##য\n", + "##র\n", + "##ল\n", + "##শ\n", + "##ষ\n", + "##স\n", + "##হ\n", + "##া\n", + "##ি\n", + "##ী\n", + "##ে\n", + "##க\n", + "##ச\n", + "##ட\n", + "##த\n", + "##ந\n", + "##ன\n", + "##ப\n", + "##ம\n", + "##ய\n", + "##ர\n", + "##ல\n", + "##ள\n", + "##வ\n", + "##ா\n", + "##ி\n", + "##ு\n", + "##ே\n", + "##ை\n", + "##ನ\n", + "##ರ\n", + "##ಾ\n", + "##ක\n", + "##ය\n", + "##ර\n", + "##ල\n", + "##ව\n", + "##ා\n", + "##ก\n", + "##ง\n", + "##ต\n", + "##ท\n", + "##น\n", + "##พ\n", + "##ม\n", + "##ย\n", + "##ร\n", + "##ล\n", + "##ว\n", + "##ส\n", + "##อ\n", + "##า\n", + "##เ\n", + "##་\n", + "##།\n", + "##ག\n", + "##ང\n", + "##ད\n", + "##ན\n", + "##པ\n", + "##བ\n", + "##མ\n", + "##འ\n", + "##ར\n", + "##ལ\n", + "##ས\n", + "##မ\n", + "##ა\n", + "##ბ\n", + "##გ\n", + "##დ\n", + "##ე\n", + "##ვ\n", + "##თ\n", + "##ი\n", + "##კ\n", + "##ლ\n", + "##მ\n", + "##ნ\n", + "##ო\n", + "##რ\n", + "##ს\n", + "##ტ\n", + "##უ\n", + "##ᄀ\n", + "##ᄂ\n", + "##ᄃ\n", + "##ᄅ\n", + "##ᄆ\n", + "##ᄇ\n", + "##ᄉ\n", + "##ᄊ\n", + "##ᄋ\n", + "##ᄌ\n", + "##ᄎ\n", + "##ᄏ\n", + "##ᄐ\n", + "##ᄑ\n", + "##ᄒ\n", + "##ᅡ\n", + "##ᅢ\n", + "##ᅥ\n", + "##ᅦ\n", + "##ᅧ\n", + "##ᅩ\n", + "##ᅪ\n", + "##ᅭ\n", + "##ᅮ\n", + "##ᅯ\n", + "##ᅲ\n", + "##ᅳ\n", + "##ᅴ\n", + "##ᅵ\n", + "##ᆨ\n", + "##ᆫ\n", + "##ᆯ\n", + "##ᆷ\n", + "##ᆸ\n", + "##ᆼ\n", + "##ᴬ\n", + "##ᴮ\n", + "##ᴰ\n", + "##ᴵ\n", + "##ᴺ\n", + "##ᵀ\n", + "##ᵃ\n", + "##ᵇ\n", + "##ᵈ\n", + "##ᵉ\n", + "##ᵍ\n", + "##ᵏ\n", + "##ᵐ\n", + "##ᵒ\n", + "##ᵖ\n", + "##ᵗ\n", + "##ᵘ\n", + "##ᵣ\n", + "##ᵤ\n", + "##ᵥ\n", + "##ᶜ\n", + "##ᶠ\n", + "##‐\n", + "##‑\n", + "##‒\n", + "##–\n", + "##—\n", + "##―\n", + "##‖\n", + "##‘\n", + "##’\n", + "##‚\n", + "##“\n", + "##”\n", + "##„\n", + "##†\n", + "##‡\n", + "##•\n", + "##…\n", + "##‰\n", + "##′\n", + "##″\n", + "##›\n", + "##‿\n", + "##⁄\n", + "##⁰\n", + "##ⁱ\n", + "##⁴\n", + "##⁵\n", + "##⁶\n", + "##⁷\n", + "##⁸\n", + "##⁹\n", + "##⁻\n", + "##ⁿ\n", + "##₅\n", + "##₆\n", + "##₇\n", + "##₈\n", + "##₉\n", + "##₊\n", + "##₍\n", + "##₎\n", + "##ₐ\n", + "##ₑ\n", + "##ₒ\n", + "##ₓ\n", + "##ₕ\n", + "##ₖ\n", + "##ₗ\n", + "##ₘ\n", + "##ₚ\n", + "##ₛ\n", + "##ₜ\n", + "##₤\n", + "##₩\n", + "##€\n", + "##₱\n", + "##₹\n", + "##ℓ\n", + "##№\n", + "##ℝ\n", + "##™\n", + "##⅓\n", + "##⅔\n", + "##←\n", + "##↑\n", + "##→\n", + "##↓\n", + "##↔\n", + "##↦\n", + "##⇄\n", + "##⇌\n", + "##⇒\n", + "##∂\n", + "##∅\n", + "##∆\n", + "##∇\n", + "##∈\n", + "##∗\n", + "##∘\n", + "##√\n", + "##∞\n", + "##∧\n", + "##∨\n", + "##∩\n", + "##∪\n", + "##≈\n", + "##≡\n", + "##≤\n", + "##≥\n", + "##⊂\n", + "##⊆\n", + "##⊕\n", + "##⊗\n", + "##⋅\n", + "##─\n", + "##│\n", + "##■\n", + "##▪\n", + "##●\n", + "##★\n", + "##☆\n", + "##☉\n", + "##♠\n", + "##♣\n", + "##♥\n", + "##♦\n", + "##♯\n", + "##⟨\n", + "##⟩\n", + "##ⱼ\n", + "##⺩\n", + "##⺼\n", + "##⽥\n", + "##、\n", + "##。\n", + "##〈\n", + "##〉\n", + "##《\n", + "##》\n", + "##「\n", + "##」\n", + "##『\n", + "##』\n", + "##〜\n", + "##あ\n", + "##い\n", + "##う\n", + "##え\n", + "##お\n", + "##か\n", + "##き\n", + "##く\n", + "##け\n", + "##こ\n", + "##さ\n", + "##し\n", + "##す\n", + "##せ\n", + "##そ\n", + "##た\n", + "##ち\n", + "##っ\n", + "##つ\n", + "##て\n", + "##と\n", + "##な\n", + "##に\n", + "##ぬ\n", + "##ね\n", + "##の\n", + "##は\n", + "##ひ\n", + "##ふ\n", + "##へ\n", + "##ほ\n", + "##ま\n", + "##み\n", + "##む\n", + "##め\n", + "##も\n", + "##や\n", + "##ゆ\n", + "##よ\n", + "##ら\n", + "##り\n", + "##る\n", + "##れ\n", + "##ろ\n", + "##を\n", + "##ん\n", + "##ァ\n", + "##ア\n", + "##ィ\n", + "##イ\n", + "##ウ\n", + "##ェ\n", + "##エ\n", + "##オ\n", + "##カ\n", + "##キ\n", + "##ク\n", + "##ケ\n", + "##コ\n", + "##サ\n", + "##シ\n", + "##ス\n", + "##セ\n", + "##タ\n", + "##チ\n", + "##ッ\n", + "##ツ\n", + "##テ\n", + "##ト\n", + "##ナ\n", + "##ニ\n", + "##ノ\n", + "##ハ\n", + "##ヒ\n", + "##フ\n", + "##ヘ\n", + "##ホ\n", + "##マ\n", + "##ミ\n", + "##ム\n", + "##メ\n", + "##モ\n", + "##ャ\n", + "##ュ\n", + "##ョ\n", + "##ラ\n", + "##リ\n", + "##ル\n", + "##レ\n", + "##ロ\n", + "##ワ\n", + "##ン\n", + "##・\n", + "##ー\n", + "##一\n", + "##三\n", + "##上\n", + "##下\n", + "##不\n", + "##世\n", + "##中\n", + "##主\n", + "##久\n", + "##之\n", + "##也\n", + "##事\n", + "##二\n", + "##五\n", + "##井\n", + "##京\n", + "##人\n", + "##亻\n", + "##仁\n", + "##介\n", + "##代\n", + "##仮\n", + "##伊\n", + "##会\n", + "##佐\n", + "##侍\n", + "##保\n", + "##信\n", + "##健\n", + "##元\n", + "##光\n", + "##八\n", + "##公\n", + "##内\n", + "##出\n", + "##分\n", + "##前\n", + "##劉\n", + "##力\n", + "##加\n", + "##勝\n", + "##北\n", + "##区\n", + "##十\n", + "##千\n", + "##南\n", + "##博\n", + "##原\n", + "##口\n", + "##古\n", + "##史\n", + "##司\n", + "##合\n", + "##吉\n", + "##同\n", + "##名\n", + "##和\n", + "##囗\n", + "##四\n", + "##国\n", + "##國\n", + "##土\n", + "##地\n", + "##坂\n", + "##城\n", + "##堂\n", + "##場\n", + "##士\n", + "##夏\n", + "##外\n", + "##大\n", + "##天\n", + "##太\n", + "##夫\n", + "##奈\n", + "##女\n", + "##子\n", + "##学\n", + "##宀\n", + "##宇\n", + "##安\n", + "##宗\n", + "##定\n", + "##宣\n", + "##宮\n", + "##家\n", + "##宿\n", + "##寺\n", + "##將\n", + "##小\n", + "##尚\n", + "##山\n", + "##岡\n", + "##島\n", + "##崎\n", + "##川\n", + "##州\n", + "##巿\n", + "##帝\n", + "##平\n", + "##年\n", + "##幸\n", + "##广\n", + "##弘\n", + "##張\n", + "##彳\n", + "##後\n", + "##御\n", + "##德\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "##心\n", + "##忄\n", + "##志\n", + "##忠\n", + "##愛\n", + "##成\n", + "##我\n", + "##戦\n", + "##戸\n", + "##手\n", + "##扌\n", + "##政\n", + "##文\n", + "##新\n", + "##方\n", + "##日\n", + "##明\n", + "##星\n", + "##春\n", + "##昭\n", + "##智\n", + "##曲\n", + "##書\n", + "##月\n", + "##有\n", + "##朝\n", + "##木\n", + "##本\n", + "##李\n", + "##村\n", + "##東\n", + "##松\n", + "##林\n", + "##森\n", + "##楊\n", + "##樹\n", + "##橋\n", + "##歌\n", + "##止\n", + "##正\n", + "##武\n", + "##比\n", + "##氏\n", + "##民\n", + "##水\n", + "##氵\n", + "##氷\n", + "##永\n", + "##江\n", + "##沢\n", + "##河\n", + "##治\n", + "##法\n", + "##海\n", + "##清\n", + "##漢\n", + "##瀬\n", + "##火\n", + "##版\n", + "##犬\n", + "##王\n", + "##生\n", + "##田\n", + "##男\n", + "##疒\n", + "##発\n", + "##白\n", + "##的\n", + "##皇\n", + "##目\n", + "##相\n", + "##省\n", + "##真\n", + "##石\n", + "##示\n", + "##社\n", + "##神\n", + "##福\n", + "##禾\n", + "##秀\n", + "##秋\n", + "##空\n", + "##立\n", + "##章\n", + "##竹\n", + "##糹\n", + "##美\n", + "##義\n", + "##耳\n", + "##良\n", + "##艹\n", + "##花\n", + "##英\n", + "##華\n", + "##葉\n", + "##藤\n", + "##行\n", + "##街\n", + "##西\n", + "##見\n", + "##訁\n", + "##語\n", + "##谷\n", + "##貝\n", + "##貴\n", + "##車\n", + "##軍\n", + "##辶\n", + "##道\n", + "##郎\n", + "##郡\n", + "##部\n", + "##都\n", + "##里\n", + "##野\n", + "##金\n", + "##鈴\n", + "##镇\n", + "##長\n", + "##門\n", + "##間\n", + "##阝\n", + "##阿\n", + "##陳\n", + "##陽\n", + "##雄\n", + "##青\n", + "##面\n", + "##風\n", + "##食\n", + "##香\n", + "##馬\n", + "##高\n", + "##龍\n", + "##龸\n", + "##fi\n", + "##fl\n", + "##！\n", + "##（\n", + "##）\n", + "##，\n", + "##－\n", + "##．\n", + "##／\n", + "##：\n", + "##？\n", + "##～\n", + "5828\n" + ] + } + ], + "source": [ + "cnt_sharp = 0\n", + "for token, id in tokenizer.vocab.items():\n", + " if token.startswith('##'):\n", + " print(token)\n", + " cnt_sharp += 1\n", + "print(cnt_sharp)" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### 2. 样本子词测试" + ] + }, + { + "cell_type": "code", + "execution_count": 31, + "metadata": { + "ExecuteTime": { + "end_time": "2022-07-09T02:49:13.009587Z", + "start_time": "2022-07-09T02:49:13.005825Z" + } + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'input_ids': [101, 2004, 5092, 2546, 2860, 5369, 11631, 2860, 19205, 2546, 102], 'token_type_ids': [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0], 'attention_mask': [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]}\n", + "['[CLS]', 'as', '##bo', '##f', '##w', '##he', '##oh', '##w', '##bei', '##f', '[SEP]']\n" + ] + } + ], + "source": [ + "inputs = tokenizer(s6)\n", + "print(inputs)\n", + "print(tokenizer.convert_ids_to_tokens(inputs['input_ids']))" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### 3. summary" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "- tokenizer 轻易不会将一个词处理为 `[UNK] (100)`\n", + "- 基于词汇表，tokenize, encode, decode 一体\n", + " - tokenize：word => token(s)，将word尽可能地映射为 vocab 中的 keys\n", + " - encode: token => id\n", + " - decode: id => token => word\n", + " - encode 完了之后也不是终点（word），decode 还要能很好地将 id 还原，尽可能与输入的 word 对齐；" + ] + } + ], + "metadata": { + "kernelspec": { + "display_name": "Python 3", + "language": "python", + "name": "python3" + }, + "language_info": { + "codemirror_mode": { + "name": "ipython", + "version": 3 + }, + "file_extension": ".py", + "mimetype": "text/x-python", + "name": "python", + "nbconvert_exporter": "python", + "pygments_lexer": "ipython3", + "version": "3.6.8" + } + }, + "nbformat": 4, + "nbformat_minor": 2 +} |