NeTSlab/gpt2_parfind_en_nl_equal
0120
1{2 "schema_version": 1,3 "created_at": "2026-07-04T10:17:57Z",4 "meta": {5 "language_specific_paradigms": {6 "languages": [7 "eng",8 "nld"9 ],10 "paradigm_counts": {11 "eng": {12 "paradigm_count": 700,13 "extracted_type_count": 5000014 },15 "nld": {16 "paradigm_count": 671,17 "extracted_type_count": 5000018 }19 },20 "zero_morphemes": {21 "eng": "<ZERO:eng>",22 "nld": "<ZERO:nld>"23 }24 },25 "min_shared_stems": 2,26 "min_suffixes": 2,27 "enrich_suffix_sets": true,28 "fallback_top_k": 20,29 "normalization": {30 "lowercase": true,31 "separate_apostrophes": false,32 "separate_digits": true,33 "separate_punctuation": true34 },35 "enhanced_features": {36 "use_word_boundaries": false,37 "null_suffixes_as_tokens": false,38 "paradigm_specific_suffixes": false,39 "paradigm_specific_roots": false,40 "word_boundary_token": "▁",41 "null_suffix_token": "ε",42 "paradigm_token_format": "{token}_p{paradigm_idx}",43 "fallback_mode": "none",44 "segment_cache_size": 20000045 },46 "boundary_discovery": {47 "boundaries_discovery": true,48 "boundary_discovery_mode": "space_free_only",49 "boundary_space_marker": "_",50 "boundary_min_sequence_length": 2,51 "boundary_shorter_first": true52 },53 "multilingual_vocab": {54 "enabled": true,55 "languages": [56 "eng",57 "nld"58 ],59 "budget_per_language": 16384,60 "extensions": [61 "*.txt"62 ],63 "merge_mode": "soft",64 "language_dirs": {}65 },66 "reuse_existing_paradigms": false,67 "track_growth": false,68 "language_zero_morphemes": {69 "eng": "<ZERO:eng>",70 "nld": "<ZERO:nld>"71 }72 },73 "paradigms": [74 {75 "stems": [76 "abound",77 "absorb",78 "alarm",79 "amount",80 "anchor",81 "arrest",82 "ascend",83 "assault",84 "attempt",85 "await",86 "bargain",87 "bellow",88 "benefit",89 "bestow",90 "betray",91 "blind",92 "blossom",93 "blunder",94 "boast",95 "boom",96 "borrow",97 "braid",98 "brief",99 "brood",100 "burp",101 "burrow",102 "cheat",103 "churn",104 "clasp",105 "claw",106 "click",107 "cluster",108 "comb",109 "complain",110 "concern",111 "consent",112 "consist",113 "contact",114 "contrast",115 "convert",116 "coo",117 "correspond",118 "cost",119 "cough",120 "crowd",121 "debut",122 "decay",123 "deem",124 "defeat",125 "delay",126 "demand",127 "detail",128 "dial",129 "differ",130 "display",131 "dock",132 "download",133 "draft",134 "drain",135 "dread",136 "drown",137 "encounter",138 "endeavour",139 "escort",140 "exclaim",141 "exist",142 "exit",143 "expand",144 "explain",145 "export",146 "extend",147 "feast",148 "filter",149 "flank",150 "float",151 "flock",152 "flood",153 "forward",154 "frighten",155 "front",156 "frown",157 "fund",158 "gasp",159 "gleam",160 "glow",161 "groan",162 "growl",163 "grunt",164 "hail",165 "hammer",166 "haunt",167 "heap",168 "highlight",169 "hint",170 "hoard",171 "howl",172 "hump",173 "insert",174 "insist",175 "insult",176 "intend",177 "label",178 "lack",179 "last",180 "leap",181 "lick",182 "linger",183 "link",184 "loom",185 "lurk",186 "maintain",187 "mask",188 "mention",189 "model",190 "monitor",191 "nail",192 "overlook",193 "pant",194 "paw",195 "peak",196 "peep",197 "pioneer",198 "plaster",199 "portray",200 "prevail",201 "prick",202 "pump",203 "quack",204 "quarrel",205 "quaver",206 "quilt",207 "rack",208 "recall",209 "reckon",210 "reel",211 "regain",212 "register",213 "reign",214 "remain",215 "remember",216 "repeat",217 "request",218 "resort",219 "respond",220 "result",221 "retreat",222 "return",223 "reveal",224 "reward",225 "roof",226 "sack",227 "saw",228 "scream",229 "screen",230 "screw",231 "script",232 "shatter",233 "shelter",234 "shield",235 "shiver",236 "shout",237 "shriek",238 "sigh",239 "smack",240 "snarl",241 "spill",242 "sponsor",243 "squeal",244 "stack",245 "stammer",246 "stamp",247 "stew",248 "stray",249 "streak",250 "strengthen",251 "succeed",252 "summon",253 "swallow",254 "swarm",255 "swell",256 "taunt",257 "text",258 "thank",259 "thread",260 "toil",261 "toy",262 "tramp",263 "trigger",264 "unfold",265 "vault",266 "veil",267 "vent",268 "volunteer",269 "vow",270 "wail",271 "weigh",272 "whimper",273 "whisper",274 "wither",275 "wound",276 "yield"277 ],278 "suffixes": [279 "<ZERO:eng>",280 "ed",281 "ing",282 "s"283 ]284 },285 {286 "stems": [287 "attack",288 "bank",289 "board",290 "boil",291 "bow",292 "bowl",293 "broadcast",294 "bust",295 "camp",296 "coast",297 "command",298 "commission",299 "contain",300 "defend",301 "desert",302 "design",303 "destroy",304 "develop",305 "employ",306 "entertain",307 "farm",308 "fell",309 "flow",310 "fold",311 "follow",312 "heat",313 "join",314 "labour",315 "lead",316 "light",317 "murder",318 "pack",319 "perform",320 "plant",321 "post",322 "pound",323 "pray",324 "pretend",325 "raid",326 "reform",327 "remind",328 "report",329 "retain",330 "review",331 "rivet",332 "round",333 "row",334 "sew",335 "stream",336 "support",337 "tend",338 "trail",339 "train",340 "transform",341 "travel",342 "troop",343 "view",344 "warm",345 "wreck"346 ],347 "suffixes": [348 "<ZERO:eng>",349 "ed",350 "ing",351 "s",352 [353 "er",354 [355 "<ZERO:eng>",356 "s"357 ]358 ]359 ]360 },361 {362 "stems": [363 "back",364 "bark",365 "beam",366 "black",367 "blast",368 "blend",369 "block",370 "book",371 "breath",372 "calm",373 "campaign",374 "charm",375 "comfort",376 "condition",377 "cook",378 "cool",379 "drift",380 "drill",381 "field",382 "flick",383 "foot",384 "form",385 "head",386 "hook",387 "hoot",388 "inform",389 "interview",390 "kick",391 "knock",392 "lift",393 "load",394 "mail",395 "mow",396 "narrow",397 "out",398 "pal",399 "park",400 "pip",401 "scoop",402 "scrap",403 "seal",404 "second",405 "shock",406 "slow",407 "sort",408 "spoil",409 "spray",410 "stalk",411 "strain",412 "suck",413 "tap",414 "thrill",415 "thump",416 "thunder",417 "track",418 "transport",419 "wheel"420 ],421 "suffixes": [422 "<ZERO:eng>",423 "ed",424 "er",425 "ing",426 "s"427 ]428 },429 {430 "stems": [431 "break",432 "build",433 "buy",434 "call",435 "check",436 "climb",437 "crack",438 "draw",439 "dream",440 "drink",441 "eat",442 "fight",443 "help",444 "hold",445 "jump",446 "keep",447 "lay",448 "look",449 "paint",450 "pay",451 "pick",452 "play",453 "rock",454 "roll",455 "show",456 "sleep",457 "start",458 "stick",459 "suffer",460 "talk",461 "tell",462 "us",463 "wait",464 "walk",465 "work"466 ],467 "suffixes": [468 "<ZERO:eng>",469 "ed",470 "in'",471 "ing",472 "s",473 [474 "er",475 [476 "<ZERO:eng>",477 "s"478 ]479 ]480 ]481 },482 {483 "stems": [484 "answer",485 "arm",486 "bath",487 "board",488 "bow",489 "bowl",490 "button",491 "carpet",492 "cook",493 "count",494 "court",495 "crow",496 "doctor",497 "drink",498 "duck",499 "farm",500 "fool",501 "foot",502 "grant",503 "groom",504 "ground",505 "harm",506 "heat",507 "host",508 "labour",509 "mark",510 "milk",511 "mouth",512 "nick",513 "paint",514 "part",515 "pilot",516 "plant",517 "rent",518 "scout",519 "seal",520 "signal",521 "skirt",522 "snow",523 "sound",524 "sting",525 "storm",526 "stream",527 "suspect",528 "tail",529 "target",530 "track",531 "weather",532 "wheel"533 ],534 "suffixes": [535 "'s",536 "<ZERO:eng>",537 "ed",538 "ing",539 "s"540 ]541 },542 {543 "stems": [544 "arm",545 "band",546 "bill",547 "brand",548 "chew",549 "crawl",550 "creak",551 "curl",552 "duck",553 "feel",554 "freak",555 "frost",556 "go",557 "hand",558 "iron",559 "jerk",560 "leak",561 "loop",562 "milk",563 "mind",564 "mold",565 "mould",566 "mount",567 "need",568 "nick",569 "part",570 "poop",571 "recover",572 "risk",573 "seed",574 "shadow",575 "shell",576 "smell",577 "sniff",578 "snow",579 "sport",580 "stock",581 "stuff",582 "swirl",583 "tack",584 "treat",585 "trick",586 "trust",587 "twirl",588 "unit",589 "water",590 "well",591 "will",592 "wink"593 ],594 "suffixes": [595 "<ZERO:eng>",596 "ed",597 "ing",598 "s",599 "y"600 ]601 },602 {603 "stems": [604 "address",605 "approach",606 "blush",607 "bor",608 "branch",609 "brush",610 "caress",611 "chang",612 "chim",613 "clash",614 "clutch",615 "coach",616 "confess",617 "crash",618 "curs",619 "dar",620 "discuss",621 "distinguish",622 "echo",623 "encompass",624 "expos",625 "express",626 "ey",627 "fad",628 "fil",629 "finish",630 "fix",631 "flourish",632 "flush",633 "focus",634 "fum",635 "gaz",636 "guess",637 "hatch",638 "hir",639 "hiss",640 "improv",641 "lik",642 "march",643 "match",644 "mend",645 "munch",646 "nam",647 "ow",648 "pac",649 "perch",650 "pil",651 "pleas",652 "possess",653 "press",654 "prob",655 "process",656 "progress",657 "punch",658 "quot",659 "rais",660 "reach",661 "relax",662 "reproach",663 "rout",664 "rush",665 "search",666 "shar",667 "sid",668 "slop",669 "smash",670 "snatch",671 "sooth",672 "splash",673 "stitch",674 "stress",675 "tax",676 "teas",677 "til",678 "tir",679 "toss",680 "vanish",681 "waltz",682 "wast",683 "wish",684 "witness"685 ],686 "suffixes": [687 "<ZERO:eng>",688 "ed",689 "es",690 "ing"691 ]692 },693 {694 "stems": [695 "abc",696 "admiral",697 "afternoon",698 "airplane",699 "airport",700 "alien",701 "alligator",702 "ambassador",703 "andrew",704 "area",705 "attorney",706 "bachelor",707 "balloon",708 "barbie",709 "basket",710 "bathroom",711 "bicycle",712 "birthday",713 "bishop",714 "blacksmith",715 "bob",716 "bonnet",717 "borough",718 "boyfriend",719 "bread",720 "bumble",721 "cable",722 "camel",723 "camera",724 "cannon",725 "canon",726 "carpenter",727 "caterpillar",728 "channel",729 "chap",730 "chef",731 "chief",732 "chocolate",733 "christian",734 "chum",735 "client",736 "college",737 "colonel",738 "cousin",739 "cowboy",740 "crab",741 "creature",742 "crocodile",743 "crystal",744 "daffodil",745 "daniel",746 "devil",747 "dinosaur",748 "district",749 "donkey",750 "duke",751 "edmund",752 "edward",753 "emperor",754 "episode",755 "firm",756 "food",757 "football",758 "ford",759 "foundation",760 "franklin",761 "freeman",762 "friday",763 "frog",764 "gazelle",765 "general",766 "giraffe",767 "girlfriend",768 "goat",769 "gorgon",770 "grammy",771 "grandfather",772 "grandma",773 "grandmother",774 "grandpa",775 "grandson",776 "hairdresser",777 "helicopter",778 "helm",779 "highway",780 "hippo",781 "honey",782 "humphrey",783 "individual",784 "invalid",785 "jackson",786 "jew",787 "jigsaw",788 "joseph",789 "junior",790 "kangaroo",791 "kennedy",792 "kettle",793 "kitchen",794 "kitten",795 "knee",796 "ladybird",797 "lala",798 "landlord",799 "lawyer",800 "lid",801 "lieutenant",802 "lyon",803 "macdonald",804 "magician",805 "magistrate",806 "maid",807 "maiden",808 "marshal",809 "marshall",810 "marvel",811 "matthew",812 "mcdonald",813 "meat",814 "meeting",815 "michael",816 "microphone",817 "monday",818 "monk",819 "monkey",820 "nephew",821 "newspaper",822 "newton",823 "niece",824 "noah",825 "ocean",826 "old",827 "olive",828 "opponent",829 "oscar",830 "panda",831 "parrot",832 "penguin",833 "pharaoh",834 "philip",835 "philosopher",836 "pig",837 "pigeon",838 "piglet",839 "pirate",840 "pizza",841 "plaintiff",842 "potato",843 "priest",844 "primrose",845 "principal",846 "problem",847 "program",848 "rabbit",849 "reindeer",850 "restaurant",851 "rodger",852 "sainsbury",853 "saturday",854 "schooner",855 "senator",856 "sergeant",857 "shark",858 "sheep",859 "shepherd",860 "sheriff",861 "shirt",862 "shop",863 "snail",864 "spider",865 "spot",866 "squire",867 "stewart",868 "stuart",869 "sub",870 "submarine",871 "sunflower",872 "surgeon",873 "table",874 "tank",875 "tara",876 "taxi",877 "temple",878 "tesco",879 "throat",880 "thursday",881 "toad",882 "top",883 "tournament",884 "tractor",885 "traitor",886 "tuesday",887 "tunnel",888 "turkey",889 "tv",890 "uncle",891 "vessel",892 "vet",893 "video",894 "violet",895 "virgin",896 "vizier",897 "walter",898 "warrior",899 "wasp",900 "wazir",901 "wednesday",902 "wet",903 "wizard",904 "youth",905 "zebra",906 "zoo"907 ],908 "suffixes": [909 "'s",910 "<ZERO:eng>",911 "s"912 ]913 },914 {915 "stems": [916 "admir",917 "advis",918 "angl",919 "bak",920 "believ",921 "blaz",922 "challeng",923 "charg",924 "chas",925 "com",926 "consum",927 "cruis",928 "d",929 "danc",930 "div",931 "driv",932 "explor",933 "fenc",934 "fiddl",935 "g",936 "glid",937 "grad",938 "handl",939 "lectur",940 "lin",941 "liv",942 "lodg",943 "lov",944 "m",945 "mak",946 "manag",947 "manufactur",948 "mov",949 "observ",950 "organiz",951 "preserv",952 "produc",953 "programm",954 "promot",955 "provid",956 "pursu",957 "rac",958 "rang",959 "receiv",960 "rescu",961 "revolv",962 "rul",963 "sav",964 "scor",965 "serv",966 "settl",967 "shak",968 "skat",969 "slav",970 "smok",971 "sparkl",972 "sprinkl",973 "tak",974 "tim",975 "trad",976 "tumbl",977 "us",978 "vot",979 "wip",980 "wrestl",981 "writ"982 ],983 "suffixes": [984 "es",985 "ing",986 [987 "e",988 [989 "<ZERO:eng>",990 "d"991 ]992 ],993 [994 "er",995 [996 "<ZERO:eng>",997 "s"998 ]999 ]1000 ]1001 },1002 {1003 "stems": [1004 "all",1005 "arm",1006 "aunt",1007 "ball",1008 "band",1009 "beck",1010 "bell",1011 "bill",1012 "bird",1013 "blood",1014 "blue",1015 "brain",1016 "bull",1017 "butcher",1018 "card",1019 "cloud",1020 "cop",1021 "count",1022 "cream",1023 "doll",1024 "drake",1025 "duck",1026 "earl",1027 "earth",1028 "egg",1029 "frank",1030 "german",1031 "girl",1032 "grocer",1033 "hand",1034 "heart",1035 "hill",1036 "jack",1037 "jacob",1038 "jo",1039 "lad",1040 "lake",1041 "lamb",1042 "land",1043 "lord",1044 "mark",1045 "milk",1046 "mill",1047 "mind",1048 "monarch",1049 "nick",1050 "night",1051 "part",1052 "rick",1053 "room",1054 "saxon",1055 "scott",1056 "show",1057 "smith",1058 "snow",1059 "soldier",1060 "sting",1061 "storm",1062 "stuff",1063 "victor",1064 "wall",1065 "water",1066 "will",1067 "wind",1068 "wood",1069 "yellow"1070 ],1071 "suffixes": [1072 "'s",1073 "<ZERO:eng>",1074 "s",1075 "y"1076 ]1077 },1078 {1079 "stems": [1080 "ach",1081 "buzz",1082 "catch",1083 "cit",1084 "cod",1085 "crumbl",1086 "dress",1087 "fish",1088 "flash",1089 "go",1090 "grad",1091 "hid",1092 "ic",1093 "kiss",1094 "mess",1095 "miss",1096 "nos",1097 "pass",1098 "patch",1099 "phon",1100 "pok",1101 "pos",1102 "push",1103 "rac",1104 "scratch",1105 "shad",1106 "shak",1107 "sketch",1108 "squash",1109 "stor",1110 "stretch",1111 "touch",1112 "unit",1113 "wash",1114 "wax",1115 "well"1116 ],1117 "suffixes": [1118 "<ZERO:eng>",1119 "ed",1120 "es",1121 "ing",1122 "y"1123 ]1124 },1125 {1126 "stems": [1127 "abus",1128 "advocat",1129 "aid",1130 "allud",1131 "analys",1132 "apologiz",1133 "argu",1134 "assum",1135 "averag",1136 "balanc",1137 "barg",1138 "battl",1139 "behav",1140 "blam",1141 "bor",1142 "bottl",1143 "brac",1144 "brib",1145 "bristl",1146 "buckl",1147 "captur",1148 "ceas",1149 "chanc",1150 "chim",1151 "chok",1152 "chuckl",1153 "circl",1154 "clon",1155 "cloth",1156 "collaps",1157 "compet",1158 "compris",1159 "compromis",1160 "conclud",1161 "convinc",1162 "coupl",1163 "crackl",1164 "cran",1165 "crav",1166 "curs",1167 "cycl",1168 "damag",1169 "dar",1170 "debat",1171 "decid",1172 "declin",1173 "decreas",1174 "defin",1175 "denot",1176 "describ",1177 "deserv",1178 "discharg",1179 "disguis",1180 "dislik",1181 "disput",1182 "dissolv",1183 "distanc",1184 "divid",1185 "divorc",1186 "dribbl",1187 "dron",1188 "embrac",1189 "emerg",1190 "enabl",1191 "ensur",1192 "entranc",1193 "envelop",1194 "escap",1195 "exchang",1196 "exclud",1197 "exercis",1198 "experienc",1199 "explod",1200 "expos",