EtymologyTagger / data /processed /labels.json
MarcusBennevall's picture
Update data/processed/labels.json - class balance and presentation refinements
88632e2 verified
{
"source_languages": [
"Latin",
"English",
"French",
"Greek",
"German",
"Chinese",
"Italian",
"Proto-Germanic",
"Spanish",
"Proto-Indo-European",
"Japanese",
"Arabic",
"Dutch",
"Russian",
"Sanskrit",
"Polish",
"Irish",
"Old Norse",
"Hebrew",
"Hindi",
"Other"
],
"mechanisms": [
"borrowed",
"derived",
"calqued",
"inherited"
],
"language_counts": {
"Latin": 23728,
"English": 20974,
"French": 16694,
"Greek": 10074,
"German": 7300,
"Chinese": 5017,
"Italian": 4729,
"Proto-Germanic": 4692,
"Spanish": 4628,
"Proto-Indo-European": 4097,
"Japanese": 2861,
"Arabic": 2475,
"Dutch": 2177,
"Russian": 1825,
"Sanskrit": 1714,
"Polish": 1694,
"Irish": 1628,
"Old Norse": 1593,
"Hebrew": 1268,
"Hindi": 1220,
"Ukrainian": 979,
"Welsh": 961,
"Portuguese": 922,
"Romanian": 858,
"Scottish Gaelic": 676,
"Czech": 593,
"Persian": 589,
"Korean": 554,
"Swedish": 542,
"Maori": 494,
"Yiddish": 479,
"Malay": 475,
"Armenian": 452,
"Frankish": 426,
"Norwegian": 408,
"Scots": 406,
"Classical Persian": 384,
"Afrikaans": 380,
"eu": 366,
"Meitei": 355,
"Danish": 318,
"Ottoman Turkish": 315,
"Serbo-Croatian": 305,
"Slovak": 304,
"Tamil": 298,
"tl": 291,
"Proto-Slavic": 281,
"Proto-Celtic": 277,
"Turkish": 276,
"Hungarian": 273,
"Hawaiian": 258,
"Urdu": 250,
"Catalan": 229,
"Bengali": 223,
"Norman": 219,
"Hindi-Urdu": 214,
"Biblical Hebrew": 199,
"Thai": 199,
"Egyptian": 198,
"sl": 183,
"North Germanic languages": 182,
"Taxonomic name": 171,
"Punjabi": 164,
"Indonesian": 159,
"Gaulish": 157,
"my": 155,
"Old Irish": 148,
"cel": 139,
"Georgian": 138,
"Occitan": 137,
"itc-pro": 132,
"Tibetan": 131,
"Uyghur": 130,
"Slavic languages": 128,
"Dzongkha": 126,
"Classical Nahuatl": 124,
"Finnish": 122,
"Vietnamese": 121,
"Cornish": 120,
"mr": 120,
"Malayalam": 119,
"gl": 119,
"Middle Persian": 116,
"Proto-Brythonic": 113,
"Khmer": 113,
"Telugu": 113,
"Aramaic": 112,
"Hopi": 106,
"Yoruba": 105,
"Bulgarian": 102,
"Belarusian": 100,
"Mongolian": 97,
"Sicilian": 97,
"Gujarati": 96,
"Nepali": 95,
"Cebuano": 95,
"Akkadian": 91,
"Amharic": 88,
"Postal Romanization": 88,
"Tongyong Pinyin": 88,
"Quechua": 85,
"Old Tupi": 80,
"pt-BR": 80,
"pro": 79,
"Old Persian": 79,
"Lithuanian": 77,
"Ojibwe": 74,
"Iranian Persian": 74,
"Swahili": 74,
"Albanian": 72,
"Sinhalese": 71,
"Cumbric": 69,
"Pre-Greek": 67,
"Turkic languages": 60,
"Sumerian": 60,
"Taino": 58,
"Picard": 56,
"Breton": 55,
"Macedonian": 55,
"Mexican Spanish": 53,
"Nahuatl languages": 53,
"Kazakh": 53,
"Brythonic languages": 52,
"Kannada": 52,
"Middle Irish": 51,
"Algonquian languages": 51,
"Icelandic": 50,
"Etruscan": 49,
"Phoenician": 48,
"Zulu": 48,
"Romani": 48,
"Jamaican Patois": 47,
"Javanese": 45,
"Inuktitut": 45,
"West Frisian": 45,
"Igbo": 44,
"Proto-Turkic": 44,
"Nahuan languages": 44,
"Old Spanish": 43,
"Cree": 43,
"Old Italian": 40,
"Lower Sorbian": 40,
"Hausa": 40,
"Yagara": 40,
"Azerbaijani": 40,
"Semitic languages": 38,
"Venetian": 38,
"Ibaloi": 38,
"Assamese": 37,
"Somali": 37,
"Dharug": 37,
"Classical Syriac": 37,
"Gothic": 37,
"Malagasy": 37,
"pam": 37,
"ak": 36,
"itc-ola": 36,
"es-PH": 36,
"qfa-sub": 36,
"orv": 35,
"xaa": 35,
"tn": 34,
"gv": 34,
"la-eme": 34,
"mt": 33,
"iir-pro": 33,
"owl": 33,
"nap": 33,
"Coptic": 33,
"sem-pro": 32,
"lo": 32,
"roa": 32,
"arz": 32,
"wam": 31,
"alg-pro": 31,
"ilo": 31,
"ps": 31,
"pim": 30,
"Latvian": 29,
"xh": 29,
"chn": 29,
"nv": 29,
"tg": 29,
"sm": 28,
"vls": 28,
"uz": 28,
"rue": 28,
"Esperanto": 27,
"poz-pol-pro": 27,
"mnc": 27,
"ru,uk": 27,
"pi": 27,
"unm": 27,
"nys": 26,
"fr-CA": 26,
"pdc": 26,
"car": 26,
"tup": 26,
"ky": 25,
"la-ren": 25,
"arn": 25,
"LL.": 24,
"kl": 24,
"mic": 24,
"roa-opt": 23,
"or": 23,
"mus": 23,
"kne": 23,
"dak": 22,
"sai-car": 22,
"hak": 22,
"ht": 22,
"NL.": 22,
"Proto-Iranian": 21,
"hur": 21,
"wo": 21,
"bnt": 21,
"wlm": 21,
"Hittite": 20,
"otk": 20,
"grk-pro": 20,
"och": 20,
"xng": 20,
"ary": 20,
"Avestan": 20,
"naq": 19,
"zhx-tai": 19,
"kaw": 19,
"nb": 19,
"ast": 19,
"gez": 18,
"kld": 18,
"cu": 18,
"hsb": 18,
"dra": 17,
"Estonian": 17,
"lng": 17,
"kmb": 17,
"pra": 17,
"arw": 17,
"pld": 17,
"xnt": 17,
"cmg": 17,
"abe": 17,
"ain": 17,
"apc": 17,
"umu": 16,
"dv": 16,
"kok": 16,
"enm-esc": 16,
"nrn": 16,
"pra-sau": 16,
"tpi": 16,
"trk-oat": 16,
"nuk": 16,
"poz-pro": 15,
"to": 15,
"sn": 15,
"kg": 15,
"egx-dem": 15,
"gmq-osw": 15,
"xil": 15,
"dra-pro": 15,
"ff": 15,
"lkt": 15,
"rme": 15,
"gug": 15,
"kwk": 15,
"del": 14,
"ty": 14,
"wrh": 14,
"ira-old": 14,
"xpu": 14,
"lmo": 14,
"yua": 14,
"moe": 14,
"chr": 14,
"jbo": 13,
"ira": 13,
"moh": 13,
"cpi": 13,
"gmw": 13,
"ML.": 13,
"cho": 13,
"frc": 13,
"de-AT": 13,
"sd": 13,
"mnk": 12,
"wya": 12,
"sah": 12,
"nn": 12,
"sai-car-pro": 12,
"nds-de": 12,
"mia": 12,
"oc-pro": 12,
"fon": 12,
"tli": 12,
"cdo": 12,
"myn": 11,
"arq": 11,
"st": 11,
"alq": 11,
"gmy": 11,
"fo": 11,
"ryu": 11,
"chh": 11,
"bar": 11,
"su": 11,
"bm": 11,
"lg": 10,
"tk": 10,
"ch": 10,
"ofs": 10,
"pml": 10,
"ay": 10,
"wa": 10,
"pt,es": 10,
"es,pt": 10,
"grc-dor": 10,
"frp": 10,
"ber": 10,
"xme-old": 10,
"shn": 10,
"gmq-oda": 10,
"bla": 10,
"hil": 10,
"kmr": 10,
"ti": 10,
"ks": 10,
"aaq": 10,
"see": 10,
"obt": 10,
"crh": 10,
"gyn": 10,
"map-pro": 9,
"qsb-ibe": 9,
"ny": 9,
"bnt-pro": 9,
"fj": 9,
"ang-ang": 9,
"alg-eas": 9,
"co": 9,
"poz-oce-pro": 9,
"inc": 9,
"ban": 9,
"pms": 9,
"mh": 9,
"xgn-pro": 9,
"iro": 9,
"esu": 9,
"txh": 9,
"xcl": 9,
"sc": 9,
"tew": 9,
"evn": 9,
"pag": 9,
"szl": 9,
"lzh-lit": 8,
"zlw-opl": 8,
"osc": 8,
"roa-oca": 8,
"mas": 8,
"sth": 8,
"ood": 8,
"de-CH": 8,
"prg": 8,
"urj": 8,
"aii": 8,
"afb": 8,
"cel-gae": 8,
"se": 8,
"lut": 8,
"aus-pam": 8,
"ik": 8,
"tyv": 8,
"gil": 7,
"xlg": 7,
"pjt": 7,
"wth": 7,
"awd": 7,
"aho": 7,
"ale": 7,
"lou": 7,
"rap": 7,
"xpq": 7,
"war": 7,
"tt": 7,
"shh": 7,
"ce": 7,
"xgn": 7,
"yrl": 7,
"itc": 7,
"shi": 7,
"wuu-sha": 7,
"ute": 7,
"da,no": 7,
"ajp": 7,
"str": 7,
"prs": 7,
"zhx": 6,
"ki": 6,
"sog": 6,
"xbc": 6,
"bcl": 6,
"esx-esk-pro": 6,
"xtg": 6,
"poz-pol": 6,
"inc-pro": 6,
"rm": 6,
"gmq-pro": 6,
"pot": 6,
"Min Nan": 6,
"fr-lou": 6,
"sjw": 6,
"xce": 6,
"pdt": 6,
"phi": 6,
"ksd": 6,
"lad": 6,
"mak": 6,
"gcf": 6,
"mnw": 6,
"lb": 6,
"cro": 6,
"aer": 6,
"oco": 6,
"oc-pro-old": 5,
"sem-wes-pro": 5,
"xib": 5,
"rw": 5,
"bi": 5,
"fos": 5,
"zlw-ocs": 5,
"grc-att": 5,
"dgr": 5,
"xsc": 5,
"ira-mid": 5,
"xve": 5,
"chg": 5,
"ss": 5,
"sqj-pro": 5,
"xpg": 5,
"xum": 5,
"khb": 5,
"gul": 5,
"inc-ash": 5,
"csb": 5,
"es-AR": 5,
"ibb": 5,
"zkt": 5,
"xno,frm": 5,
"mww": 5,
"tup-gua": 5,
"es-CU": 5,
"ckt": 5,
"miq": 5,
"swg": 5,
"urj-fin": 5,
"phr": 5,
"dif": 5,
"bal": 5,
"es-PR": 5,
"bdy": 5,
"pcm": 5,
"ady": 5,
"crk": 5,
"xld": 5,
"kln": 5,
"kbd": 5,
"xwo": 5,
"ln": 5,
"gaa": 5,
"nan-hbl-TW": 5,
"hei": 5,
"xgf": 5,
"wyi": 5,
"mov": 5,
"yur": 5,
"ium": 5,
"omq-mxt": 5,
"mfe": 5,
"oka": 5,
"ber-pro": 4,
"srn": 4,
"zlw": 4,
"es-ear": 4,
"iro-nor-pro": 4,
"tmh": 4,
"cuk": 4,
"ee": 4,
"mos": 4,
"azc-nah-pro": 4,
"ine-ana": 4,
"tbh": 4,
"es-US": 4,
"pcd": 4,
"sio": 4,
"azc-pro": 4,
"awd-pro": 4,
"lij": 4,
"os": 4,
"poz-pnp-pro": 4,
"uga": 4,
"line": 4,
"omr": 4,
"Proto-Mon-Khmer": 4,
"eve": 4,
"myv": 4,
"cad": 4,
"oge": 4,
"xww": 4,
"urj-pro": 4,
"yrk-tun": 4,
"qwm": 4,
"zlw-mpl": 4,
"fr-CH": 4,
"zku": 4,
"crg": 4,
"nds-nl": 4,
"frr": 4,
"an": 4,
"bin": 4,
"ba": 4,
"cs,sk": 4,
"xpr": 4,
"pgl": 4,
"elx": 4,
"mxi": 4,
"tsg": 4,
"cea": 4,
"awk": 4,
"unn": 4,
"xur": 4,
"ga,gd": 4,
"mdh": 4,
"it,pt,es": 4,
"xdc": 4,
"pua": 4,
"trk-cmn-pro": 4,
"gal": 4,
"dz,bo": 4,
"gnc": 4,
"es-CL": 4,
"min": 4,
"bem": 4,
"one": 4,
"kla": 4,
"pqm": 4,
"aeb": 4,
"ayn": 4,
"art-vlh": 4,
"kee": 4,
"kls": 4,
"roa-leo": 4,
"otw": 4,
"la-con": 4,
"zle": 4,
"apd": 4,
"clm": 4,
"wal": 4,
"xh-bha": 4,
"afa": 3,
"sbv": 3,
"phi-pro": 3,
"Afar": 3,
"kr": 3,
"tvl": 3,
"tkl": 3,
"non-oen": 3,
"pau": 3,
"emk": 3,
"nic": 3,
"mun": 3,
"zls": 3,
"xul": 3,
"nso": 3,
"hnm": 3,
"tuw": 3,
"it,es": 3,
"oty": 3,
"sit-pro": 3,
"qya": 3,
"dra-sou-pro": 3,
"nan-zha": 3,
"pap": 3,
"mjy": 3,
"yum": 3,
"xlo": 3,
"yij": 3,
"bat": 3,
"mdf": 3,
"lld": 3,
"blt": 3,
"nod": 3,
"tdd": 3,
"ts": 3,
"dollar": 3,
"sjn": 3,
"sco-uls": 3,
"ace": 3,
"cnx": 3,
"poz-pep-pro": 3,
"ine-bsl-pro": 3,
"iow": 3,
"stq": 3,
"smi": 3,
"wen": 3,
"qwc": 3,
"pqe-pro": 3,
"kpv": 3,
"xsc-sar-pro": 3,
"mns": 3,
"bug": 3,
"crb": 3,
"kfa": 3,
"tuw-pro": 3,
"hwc": 3,
"ku": 3,
"poz-mly-pro": 3,
"xuu": 3,
"tsi": 3,
"tzm": 3,
"nl,de": 3,
"smi-pro": 3,
"man": 3,
"ng": 3,
"hid": 3,
"tfn": 3,
"nez": 3,
"bua": 3,
"sht": 3,
"guu": 3,
"gbw": 3,
"bg,mk,ru": 3,
"ayl": 3,
"pnb": 3,
"mbc": 3,
"sat": 3,
"chl": 3,
"ike": 3,
"nay": 3,
"kum": 3,
"was": 3,
"din": 3,
"dua": 3,
"atj": 3,
"win": 3,
"grc-ion": 3,
"girl": 3,
"shs": 3,
"lil": 3,
"sem-srb": 3,
"xvn": 3,
"ibg": 3,
"art": 3,
"nsk": 3,
"nai-chu": 3,
"kkv": 3,
"kkz": 3,
"tow": 3,
"coo": 3,
"syl": 3,
"thp": 3,
"ksw": 3,
"wbp": 3,
"axm": 2,
"olt": 2,
"lre": 2,
"snk": 2,
"dyu": 2,
"na": 2,
"srr": 2,
"its": 2,
"urj-fin-pro": 2,
"niu": 2,
"fud": 2,
"vai": 2,
"av": 2,
"aoc": 2,
"lus": 2,
"njm": 2,
"business": 2,
"zle-mru": 2,
"xaq": 2,
"enm-wmi": 2,
"esx-inu-pro": 2,
"nd": 2,
"nap,scn": 2,
"bbn": 2,
"tok": 2,
"omn": 2,
"cic": 2,
"luo": 2,
"roa-pro": 2,
"nus": 2,
"zun": 2,
"en-ear": 2,
"zza": 2,
"yol": 2,
"frm,fr": 2,
"xhc": 2,
"jpx-pro": 2,
"pao": 2,
"bft": 2,
"zle-muk": 2,
"gjn": 2,
"xno-law": 2,
"cent": 2,
"gme": 2,
"hmn": 2,
"gmw-rfr": 2,
"summons": 2,
"ma'am": 2,
"fro-pic": 2,
"akz": 2,
"oma": 2,
"mez": 2,
"idb": 2,
"zkz": 2,
"boy": 2,
"sac": 2,
"udm": 2,
"alv-gbe": 2,
"dmn": 2,
"io": 2,
"esx-inu": 2,
"mfy": 2,
"pis": 2,
"inc-mbn": 2,
"chb": 2,
"fr-aca": 2,
"bnt-ngu": 2,
"iro-ere": 2,
"James": 2,
"ath": 2,
"chp": 2,
"kca-eas": 2,
"kca-nor": 2,
"cjm": 2,
"map": 2,
"khi-kho": 2,
"zle-ono": 2,
"opt": 2,
"half": 2,
"fla": 2,
"nai-utn": 2,
"egy-lat": 2,
"bg,ru": 2,
"wuu": 2,
"for": 2,
"poz": 2,
"gur": 2,
"zdj": 2,
"cab": 2,
"skr": 2,
"ket": 2,
"chc": 2,
"kyh": 2,
"ttj": 2,
"pox": 2,
"ang-nor": 2,
"atk": 2,
"gwi": 2,
"cop-sah": 2,
"ikt": 2,
"nup": 2,
"nai-cal": 2,
"tlh": 2,
"tbq": 2,
"juc": 2,
"bg,ru,uk": 2,
"xmr": 2,
"ckb": 2,
"kac": 2,
"ca-val": 2,
"convenience": 2,
"nai-kum": 2,
"es-PE": 2,
"bhw": 2,
"zle-ort": 2,
"bg,mk,ru,sh": 2,
"lzz": 2,
"hai": 2,
"sxc": 2,
"beefsteak": 2,
"gag": 2,
"ru, uk": 2,
"alt": 2,
"zea": 2,
"tcy": 2,
"xqa": 2,
"khw": 2,
"kaa": 2,
"gon": 2,
"pon": 2,
"mye": 2,
"hts": 2,
"coc": 2,
"veo": 2,
"gza": 2,
"sa-neo": 2,
"wym": 2,
"cpx": 2,
"hz": 2,
"trf": 2,
"ono": 2,
"Abkhaz": 2,
"apq": 2,
"es-CO": 2,
"ypk": 2,
"cwd": 2,
"art-dtk": 2,
"xlu": 2,
"rif": 2,
"scn-old": 2,
"new": 2,
"itl": 2,
"gld": 2,
"mai": 2,
"rar": 2,
"lbj": 2,
"chk": 2,
"bdq": 2,
"mng": 2,
"mui": 2,
"pwi": 2,
"nan-hbl-SG": 2,
"squ": 2,
"sek": 2,
"mik": 2,
"tmr": 2,
"nai-pom": 2,
"gbm": 2,
"nr": 2,
"mfa": 2,
"mnr": 2,
"csi": 2,
"wub": 2,
"iba": 2,
"cop-boh": 2,
"paw": 2,
"tol": 2,
"bob": 2,
"wac": 2,
"mam": 2,
"xmf": 2,
"rkt": 2,
"ojg": 2,
"mrw": 2,
"wbl": 2,
"mch": 2,
"bkk": 2,
"oru": 2,
"bsh": 2,
"sgh": 2,
"nli": 2,
"shy": 2,
"kut": 2,
"plk": 2,
"he-IL": 2,
"mwr": 2,
"mtr": 2,
"goq": 2,
"xvo": 2,
"tus": 2,
"blc": 2,
"lbk": 2,
"crs": 2,
"css": 1,
"tao": 1,
"adt": 1,
"euq": 1,
"kam": 1,
"Gilberts": 1,
"cba": 1,
"ia": 1,
"awd-taa": 1,
"bcq": 1,
"en-IE": 1,
"kro": 1,
"poz-clb": 1,
"kky": 1,
"khy": 1,
"Yankee": 1,
"afa-pro": 1,
"sem-nwe": 1,
"boss": 1,
"aav": 1,
"commercial": 1,
"iro-pro": 1,
"sip": 1,
"csw": 1,
"xrr": 1,
"short circuit": 1,
"eee": 1,
"vot": 1,
"animation": 1,
"chy": 1,
"mxh": 1,
"Mike": 1,
"talk + pidgin or business": 1,
"office + lady": 1,
"pfl": 1,
"otb": 1,
"cof": 1,
"cms": 1,
"talk": 1,
"drl": 1,
"alv-fwo": 1,
"mge": 1,
"kxm": 1,
"rand": 1,
"urj-ugr-pro": 1,
"cld": 1,
"odk": 1,
"public": 1,
"allelomorph": 1,
"nai-mus": 1,
"en-GB-SCT": 1,
"job": 1,
"along": 1,
"rop": 1,
"it,vec": 1,
"VL.": 1,
"dread": 1,
"locks": 1,
"cau-nec": 1,
"cau-nwc": 1,
"inz": 1,
"hgm": 1,
"ved": 1,
"he-med": 1,
"apw": 1,
"crp-mpp": 1,
"jot": 1,
"mohair": 1,
"xno,fro": 1,
"inc-ohi": 1,
"fiu-pro": 1,
"men": 1,
"mns-pro": 1,
"Skylab": 1,
"character+voice": 1,
"block": 1,
"fro,enm": 1,
"tango": 1,
"qua": 1,
"apk": 1,
"gor": 1,
"sough": 1,
"en-IN": 1,
"smit": 1,
"smutch": 1,
"cnh": 1,
"crabs": 1,
"ending": 1,
"yap": 1,
"boing": 1,
"what's going on": 1,
"pill": 1,
"azc": 1,
"home page": 1,
"roast beef": 1,
"pierce#Etymology 1": 1,
"ball": 1,
"rhg": 1,
"Tamara": 1,
"adult video": 1,
"no,sv": 1,
"H": 1,
"mk,ru,uk": 1,
"mrj": 1,
"pidgin": 1,
"sg": 1,
"tig": 1,
"efi": 1,
"all right": 1,
"roa-itd": 1,
"mpr": 1,
"gmw-ecg": 1,
"zlw-pom": 1,
"nrf-jer": 1,
"sh,ru": 1,
"food for powder": 1,
"inh": 1,
"amf": 1,
"tourist": 1,
"kbn": 1,
"kmf": 1,
"ksk": 1,
"mns-nor": 1,
"kca-sou": 1,
"xas": 1,
"txb": 1,
"my Lady": 1,
"amateur": 1,
"Christmas": 1,
"mk,ru": 1,
"bsk": 1,
"football": 1,
"mtq": 1,
"yuc": 1,
"it,ca,pt,mt": 1,
"gan": 1,
"hsn": 1,
"vep": 1,
"lml": 1,
"gue": 1,
"ebr": 1,
"wim": 1,
"bjs": 1,
"meagre": 1,
"cmt": 1,
"ppl": 1,
"dummy": 1,
"kea": 1,
"Silicon Valley": 1,
"abq": 1,
"bfq": 1,
"hne": 1,
"mki": 1,
"bej": 1,
"xhu": 1,
"Japanese pop": 1,
"bqc": 1,
"pudding": 1,
"gmw-jdt": 1,
"suk": 1,
"dwu": 1,
"wolf's-foot": 1,
"mkh-vie-pro": 1,
"roa-ona": 1,
"acy": 1,
"aus-psw": 1,
"dragon": 1,
"lbe": 1,
"tuo": 1,
"grc-epc": 1,
"ca,fr,it": 1,
"ruby": 1,
"film": 1,
"nyy": 1,
"ynn": 1,
"es,ca": 1,
"fkv": 1,
"William": 1,
"pmt": 1,
"opening": 1,
"yrl,tpw": 1,
"goddamn": 1,
"umb": 1,
"riding-coat": 1,
"mav": 1,
"cst": 1,
"xmk": 1,
"gmw-vog": 1,
"kru": 1,
"my Lord": 1,
"guc": 1,
"osa": 1,
"uln": 1,
"Diana": 1,
"Sulphur Island": 1,
"ribs": 1,
"teo": 1,
"copper": 1,
"ja-mid-lat": 1,
"xbj": 1,
"iir": 1,
"gem-sue": 1,
"da,et,fo,de,is,no,sv": 1,
"da,is,no,sv": 1,
"kde": 1,
"wkw": 1,
"loz": 1,
"cak": 1,
"technology": 1,
"cut": 1,
"cutlet": 1,
"gunner": 1,
"maid": 1,
"nl-BE": 1,
"extravage": 1,
"xsl": 1,
"kvh": 1,
"kdd": 1,
"punch": 1,
"crn": 1,
"nly": 1,
"yao": 1,
"poon": 1,
"abs": 1,
"fr,it,pt,es": 1,
"bvb": 1,
"board": 1,
"fa,ar": 1,
"dep": 1,
"urj-fpr-pro": 1,
"bll": 1,
"mod": 1,
"smn": 1,
"twf": 1,
"tuw-ewe": 1,
"tuw-sol": 1,
"sio-pro": 1,
"superchat": 1,
"kio": 1,
"sandwich": 1,
"idol": 1,
"background music": 1,
"salt": 1,
"fur-old": 1,
"cricket": 1,
"kpy": 1,
"bgc": 1,
"country dance": 1,
"rup": 1,
"hax": 1,
"trp": 1,
"kanaka": 1,
"tzh": 1,
"qfa-yen": 1,
"nxm": 1,
"paddle (tennis)": 1,
"thank you": 1,
"country-dance": 1,
"fur": 1,
"nai-mus-pro": 1,
"mgp": 1,
"tkn": 1,
"oui": 1,
"trk-ogz-pro": 1,
"lolita": 1,
"aht": 1,
"tsu": 1,
"tuv": 1,
"scl": 1,
"aitch": 1,
"mid": 1,
"tru": 1,
"professional wrestling": 1,
"border": 1,
"because": 1,
"portion": 1,
"ca,pl": 1,
"awa": 1,
"kju": 1,
"bloomers": 1,
"alv-kro": 1,
"myz": 1,
"ach": 1,
"kuj": 1,
"poz-cet-pro": 1,
"acx": 1,
"cs,hu": 1,
"sem-amo": 1,
"es,it,pt": 1,
"ecstasy": 1,
"en-AU": 1,
"feeling": 1,
"cia": 1,
"George": 1,
"haa": 1,
"kjq": 1,
"rsk": 1,
"dta": 1,
"one talk": 1,
"sai-mlb": 1,
"byn": 1,
"ass": 1,
"kqn": 1,
"kjb": 1,
"drama": 1,
"crr": 1,
"sml": 1,
"quc": 1,
"tem": 1,
"whiting": 1,
"yux": 1,
"wiy": 1,
"off": 1,
"watch": 1,
"erotic game": 1,
"shilling": 1,
"bdl": 1,
"abz": 1,
"aus-yol": 1,
"hrx": 1,
"es-ear,pt": 1,
"pants": 1,
"panty": 1,
"rascal": 1,
"dyo": 1,
"rmf": 1,
"sjd": 1,
"xal": 1,
"inc-dar": 1,
"kfc": 1,
"azc-num": 1,
"fr,it": 1,
"ami": 1,
"nij": 1,
"myn-pro": 1,
"cay": 1,
"dlm": 1,
"body conscious": 1,
"bluestocking": 1,
"bugger up": 1,
"dtd": 1,
"gd,ga": 1,
"akm": 1,
"amj": 1,
"kri": 1,
"taq": 1,
"pinnace": 1,
"sio-dhe": 1,
"myh": 1,
"custom": 1,
"alg-aga": 1,
"any": 1,
"sfw": 1,
"bazooka": 1,
"tly": 1,
"yai": 1,
"bmn": 1,
"byj": 1,
"rmo": 1,
"grotesque": 1,
"kek": 1,
"auc": 1,
"aunt": 1,
"Woodward": 1,
"asa": 1,
"atw": 1,
"rgn": 1,
"tzl": 1,
"aud": 1,
"wls": 1,
"narcodollar": 1,
"ncl": 1,
"bue": 1,
"sxu": 1,
"ojp": 1,
"ira-wes": 1,
"art-bsp": 1,
"dog": 1,
"xlp": 1,
"fan": 1,
"dar": 1,
"amw": 1,
"swb": 1,
"study": 1,
"ccp": 1,
"arc-nab": 1,
"white fella": 1,
"cku": 1,
"tjw": 1,
"talent": 1,
"hnj": 1,
"unr": 1,
"nai-spt": 1,
"irk": 1,
"nnt": 1,
"spo": 1,
"bah": 1,
"taa": 1,
"missionary": 1,
"ckv": 1,
"omq-cha": 1,
"con": 1,
"pra-mah": 1,
"xls": 1,
"ssf": 1,
"ard": 1,
"yag": 1,
"nll": 1,
"world": 1,
"azc-tak-pro": 1,
"cid": 1,
"saz": 1,
"bum": 1,
"mlv": 1,
"rrm": 1,
"face + control": 1,
"ish": 1,
"nai-ker": 1,
"lki": 1,
"abj": 1,
"peacock": 1,
"weather-gall": 1,
"koy": 1,
"stand by": 1,
"yaf": 1,
"art-lap": 1,
"jiv": 1,
"white day": 1,
"governor": 1,
"lif": 1,
"xbo": 1,
"xln": 1,
"nmu": 1,
"xni": 1,
"pit": 1,
"ynd": 1,
"go up": 1,
"aut": 1,
"cabaret club": 1,
"mqm": 1,
"vo": 1,
"wba": 1,
"gvc": 1,
"kuz": 1,
"trainer": 1,
"swi": 1,
"anu": 1,
"xsb": 1,
"evacuate": 1,
"mhi": 1,
"fng": 1,
"nqo": 1,
"rng": 1,
"oma,iow,ksk,osa": 1,
"azc-caz": 1,
"sem-tay": 1,
"aot": 1,
"ato": 1,
"free": 1,
"apron": 1,
"bea": 1,
"hns": 1,
"tog": 1,
"aqua- + aerobics": 1,
"pl,sk": 1,
"it,nap": 1,
"rice": 1,
"fairy": 1,
"nru": 1,
"shoot": 1,
"nyn": 1,
"cool": 1,
"agreement": 1,
"mis-rou": 1,
"sds": 1,
"it,mt": 1,
"cs,hu,sh,sk,sl": 1,
"cup": 1,
"gmw-fri": 1,
"bjb": 1,
"it,scn": 1,
"sai-ctq": 1,
"grk-ita": 1,
"hole": 1,
"nan-xia": 1,
"kjg": 1,
"wnw": 1,
"ceb,ilo,tl": 1,
"pen": 1,
"kyk": 1,
"pool": 1,
"pagan": 1,
"lsd": 1,
"yuf": 1,
"cce": 1,
"tiv": 1,
"nan-qua": 1,
"qwm-mam": 1,
"slam": 1,
"choco": 1,
"sjo": 1,
"cim": 1,
"hi,mr": 1,
"rad": 1,
"cps": 1,
"groundhog": 1,
"lic": 1,
"nxq": 1,
"rol": 1,
"akk-nas": 1,
"mno": 1,
"aus-guw": 1,
"wic": 1,
"grocery": 1,
"tnk": 1,
"mzs": 1,
"crazy sickness": 1,
"bgi": 1,
"majorette": 1,
"mile": 1,
"ikx": 1,
"bzj": 1,
"arse": 1,
"ill": 1,
"syb": 1,
"teh": 1,
"akl": 1,
"sgd": 1,
"obm": 1,
"mtt": 1,
"hard bass": 1,
"tbq-kuk": 1,
"decorated + truck": 1,
"arc-hat": 1,
"gmw-fin": 1,
"xyt": 1,
"oc-ara": 1,
"guernsey": 1,
"Gerard": 1,
"tbq-anp": 1,
"ari": 1,
"pea": 1,
"tnv": 1,
"clc": 1,
"kj": 1,
"lmy": 1,
"midshipman": 1,
"desktop": 1,
"dcc": 1,
"eya": 1,
"recycle": 1,
"kck": 1,
"cove": 1,
"shark": 1,
"kw,cy": 1,
"virtual": 1,
"nol": 1,
"platoon": 1,
"skd": 1,
"self": 1,
"puy": 1,
"xaw": 1,
"game, set, match": 1,
"xme": 1,
"fence sitter": 1,
"ser": 1,
"bcj": 1,
"doi": 1,
"mis-jie": 1,
"little": 1,
"okz": 1,
"go astern": 1,
"brother": 1,
"par": 1,
"cau-nkh": 1,
"sqn": 1,
"shu": 1,
"aborigine": 1,
"ohu": 1,
"queer": 1,
"za": 1,
"mep": 1,
"xyy": 1,
"bjj": 1,
"has": 1,
"hi-mum": 1,
"alh": 1,
"wbj": 1,
"bjn": 1,
"bck": 1,
"cbd": 1,
"compound": 1,
"crack": 1,
"be,ru,uk": 1,
"bns": 1,
"ve": 1,
"rue,rsk,uk": 1,
"roa-poi": 1,
"mhs": 1,
"arc-old": 1,
"xth": 1,
"igl": 1,
"qfa-kra-pro": 1,
"rki": 1,
"kab": 1,
"ems": 1,
"academy": 1,
"snap-link": 1,
"sister complex": 1,
"meeting": 1,
"sal": 1,
"fpe": 1,
"pidgin English": 1,
"kdr": 1,
"curry": 1,
"bba": 1,
"poz-ssw-pro": 1,
"Russia": 1,
"esx-tut": 1,
"kho": 1,
"mvy": 1,
"sbn": 1,
"kmz": 1,
"gwf": 1,
"sts": 1,
"gju": 1,
"mnj": 1,
"nty": 1,
"sgy": 1,
"paq": 1,
"bgq": 1,
"btv": 1,
"prx": 1,
"ush": 1,
"wne": 1,
"ydg": 1,
"clh": 1,
"shd": 1,
"jat": 1,
"deh": 1,
"gig": 1,
"xhe": 1,
"jnd": 1,
"bhe": 1,
"xka": 1,
"gjk": 1,
"kxp": 1,
"lrk": 1,
"gdx": 1,
"gwt": 1,
"lrl": 1,
"mhj": 1,
"ghr": 1,
"ggg": 1,
"aee": 1,
"prn": 1,
"sdg": 1,
"ssi": 1,
"kbu": 1,
"xvi": 1,
"lss": 1,
"nlm": 1,
"vgr": 1,
"mup": 1,
"mby": 1,
"luv": 1,
"hoh": 1,
"gdq": 1,
"hss": 1,
"inc-kho": 1,
"sqt": 1,
"tra": 1,
"glj": 1,
"lla": 1,
"tuq": 1,
"rzh": 1,
"shutter": 1,
"paper": 1,
"relax": 1,
"phl": 1,
"nrf,frm,it": 1,
"wo,ff": 1,
"ceb,tl": 1,
"beach": 1,
"ahn": 1,
"esx": 1,
"knife": 1,
"bkz": 1,
"sailor": 1,
"nyn,cgg,nyo,ttj": 1,
"bsa": 1,
"tbd": 1,
"sea": 1,
"hac": 1,
"settle": 1,
"hoc": 1,
"Slavey": 1,
"mop": 1,
"Byron": 1,
"xqt": 1,
"Americano": 1,
"office": 1,
"Tom Thumb": 1,
"nan-hbl,yue,cmn": 1,
"gax": 1,
"carefree": 1,
"yue-HK": 1,
"ice cream": 1,
"ntw": 1,
"Mobil": 1,
"brother complex": 1,
"forward": 1,
"dso": 1,
"hlb": 1,
"khn": 1,
"noe": 1,
"srb": 1,
"suz": 1,
"vah": 1,
"xmy": 1,
"lhu": 1,
"mjz": 1,
"doctor": 1,
"kxv": 1,
"avu": 1,
"dtp": 1,
"tpw-lga": 1,
"krl": 1,
"kmv": 1,
"dni": 1,
"yli": 1,
"ii": 1,
"ptw": 1,
"kfb": 1,
"Jerusalem": 1,
"om": 1,
"tiw": 1,
"gup": 1,
"city pop": 1,
"nan-hlh": 1,
"xeb": 1,
"brx": 1,
"corn + cheese": 1,
"character": 1,
"kff": 1,
"pga": 1,
"anime song": 1,
"ttz": 1,
"mis-xnu": 1,
"kzk": 1,
"ru,be": 1,
"collops": 1,
"zak": 1,
"rw-kin": 1,
"dis": 1,
"dbl": 1,
"luh": 1,
"bank": 1,
"nan-pen": 1,
"bg,mk": 1,
"pom": 1,
"president": 1,
"kda": 1,
"be,uk": 1,
"kak": 1,
"coffee": 1,
"mba": 1,
"mn-kha": 1,
"bag": 1,
"drg": 1,
"fly": 1,
"pea soup": 1,
"pay": 1,
"cmn-TW": 1,
"go": 1,
"xsc-sak-pro": 1,
"mfb": 1,
"water": 1,
"decoration": 1,
"kix": 1,
"kk,ru,uk": 1,
"Belter": 1,
"art-bel": 1,
"lang": 1,
"sto": 1,
"tuu": 1,
"bcr": 1,
"git": 1,
"ghs": 1,
"xsy": 1,
"oyd": 1,
"kcy": 1,
"nb,nn": 1,
"kpe": 1,
"tht": 1,
"Stephen": 1,
"it,pt": 1
}
}