Add words from desiquintans wordlist

docs/WORDLIST.adoc

@@ -6,6 +6,11 @@ include::common.adoc.template[]
 
 = Wordlist
 
+== Status
+
+I downloaded the nounlist from link:https://www.desiquintans.com/nounlist[here^].
+The last word I checked through manually was `COOKBOOK`.
+
 == Description
 
 The wordlist for xpin begins with the wordlist from link:https://github.com/ps-kostikov/english-word-frequency/[ps-kostikov/english-word-frequency^] (link:https://github.com/ps-kostikov/english-word-frequency/blob/master/data/frequency_list.txt[data/frequency_list.txt^])

wordlist/01-errored-lemmatized-words.csv

@@ -1 +1,549 @@
 WORD,ATTEMPTED_LEMMATIZATION,LEMMATIZER
+ADVERTISING,ADVERTISE,SPACY
+BOSS,BOS,WORDNET
+COMICS,COMIC_STRIP,SPACY
+CORPS,CORP,WORDNET
+DIABETES,DIABETE,SPACY
+EARMUFFS,EARMUFF,WORDNET
+EAVES,EAVE,SPACY
+GREED,GREE,SPACY
+JODHPURS,JODHPUR,WORDNET
+KNICKERS,KNICKER,SPACY
+LEGGING,LEGGE,SPACY
+MARACAS,MARACA,WORDNET
+MATHEMATICS,MATHEMATIC,SPACY
+MEASLES,MEASLE,SPACY
+PAJAMAS,PAJAMA,WORDNET
+PANTIES,PANTIE,SPACY
+SERIES,SERIE,SPACY
+SIDEBURNS,SIDEBURN,WORDNET
+TROUSERS,TROUSER,WORDNET
+UNDERPANTS,UNDERPANT,SPACY
+VIBRISSAE,VIBRISSA,WORDNET
+LESS,LE,WORDNET
+THEMSELVES,THEMSELVE,SPACY
+PERHAPS,PERHAP,SPACY
+OURSELVES,OURSELVE,SPACY
+EXCEED,EXCEE,SPACY
+BLEED,BLEE,SPACY
+NAKED,NAKE,SPACY
+SKILLED,SKILLE,SPACY
+BELOVED,BELOVE,SPACY
+LEST,L,SPACY
+WICKED,WICKE,SPACY
+EMBED,EMBE,SPACY
+ONGOING,ONGOE,SPACY
+ASHAMED,ASHAME,SPACY
+CREED,CREE,SPACY
+VIS,VI,WORDNET
+SINNER,SINN,SPACY
+INDEBTED,INDEBTE,SPACY
+CAPITA,CAPUT,WORDNET
+UNCHANGED,UNCHANGE,SPACY
+UNPUBLISHED,UNPUBLISHE,SPACY
+BIS,BI,WORDNET
+UNEMPLOYED,UNEMPLOYE,SPACY
+FORTHCOMING,FORTHCOME,SPACY
+METAPHYSICS,METAPHYSIC,SPACY
+UNAFFECTED,UNAFFECTE,SPACY
+RENOWNED,RENOWNE,SPACY
+TALENTED,TALENTE,SPACY
+UNFINISHED,UNFINISHE,SPACY
+MS,M,WORDNET
+AESTHETICS,AESTHETIC,WORDNET
+INFRARED,INFRARE,SPACY
+DISINTERESTED,DISINTERESTE,SPACY
+OS,O,WORDNET
+UNNOTICED,UNNOTICE,SPACY
+TING,TE,SPACY
+ANNALS,ANNAL,SPACY
+PUS,PU,WORDNET
+OUTSKIRTS,OUTSKIRT,WORDNET
+DETEST,DET,SPACY
+FETTER,FETT,SPACY
+SIDEWAYS,SIDEWAY,SPACY
+ALMS,ALM,SPACY
+UNRESTRICTED,UNRESTRICTE,SPACY
+ARREARS,ARREAR,SPACY
+UNDEVELOPED,UNDEVELOPE,SPACY
+CARIES,CARIE,SPACY
+MORES,MORE,WORDNET
+UNALTERED,UNALTERE,SPACY
+UNPROTECTED,UNPROTECTE,SPACY
+UNEDUCATED,UNEDUCATE,SPACY
+GALLOWS,GALLOW,SPACY
+UNDATED,UNDATE,SPACY
+UNNAMED,UNNAME,SPACY
+MONIES,MONIE,SPACY
+UNAIDED,UNAIDE,SPACY
+UNQUESTIONED,UNQUESTIONE,SPACY
+IMBED,IMBE,SPACY
+AMINES,AMINE,WORDNET
+GRASSROOTS,GRASSROOT,SPACY
+ACCURSED,ACCURSE,SPACY
+UNDECIDED,UNDECIDE,SPACY
+UNCHECKED,UNCHECKE,SPACY
+UNCOMPLICATED,UNCOMPLICATE,SPACY
+BELATED,BELATE,SPACY
+UNDETERMINED,UNDETERMINE,SPACY
+DISAFFECTED,DISAFFECT,SPACY
+CIS,CI,WORDNET
+UNFULFILLED,UNFULFILLE,SPACY
+STRIATED,STRIATE,SPACY
+RICKETS,RICKET,SPACY
+CILIA,CILIUM,WORDNET
+PS,P,WORDNET
+BICEPS,BICEP,SPACY
+DEATHBED,DEATHBE,SPACY
+RABIES,RABIE,SPACY
+UNATTENDED,UNATTENDE,SPACY
+UNABATED,UNABATE,SPACY
+MANNERED,MANNERE,SPACY
+FAECES,FAECE,SPACY
+QUADRUPED,QUADRUPE,SPACY
+UNSTRUCTURED,UNSTRUCTURE,SPACY
+UNAVAILING,UNAVAILE,SPACY
+SUBSPECIES,SUBSPECIE,SPACY
+UNDETECTED,UNDETECTE,SPACY
+UNPLANNED,UNPLANNE,SPACY
+UNCONDITIONED,UNCONDITIONE,SPACY
+INBRED,INBREED,SPACY
+TONGS,TONG,SPACY
+BIGOTED,BIGOTE,SPACY
+ENTRAILS,ENTRAIL,SPACY
+UNEQUALLED,UNEQUALLE,SPACY
+ONCOMING,ONCOME,SPACY
+UNTHINKING,UNTHINKE,SPACY
+CESS,CE,WORDNET
+MENSES,MENSE,SPACY
+UNMITIGATED,UNMITIGATE,SPACY
+UNRECORDED,UNRECORDE,SPACY
+SEMIOTICS,SEMIOTIC,SPACY
+UNACKNOWLEDGED,UNACKNOWLEDGE,SPACY
+UNDISGUISED,UNDISGUISE,SPACY
+PYRITES,PYRITE,WORDNET
+ESS,ES,WORDNET
+UNOBSTRUCTED,UNOBSTRUCTE,SPACY
+UNATTACHED,UNATTACHE,SPACY
+MINUTIAE,MINUTIA,WORDNET
+UNMATCHED,UNMATCHE,SPACY
+HAEMORRHOIDS,HAEMORRHOID,WORDNET
+ENAMORED,ENAMOR,SPACY
+BACKWOODS,BACKWOOD,SPACY
+UNPROVOKED,UNPROVOKE,SPACY
+TRICEPS,TRICEP,SPACY
+MUSS,MUS,WORDNET
+UNCHARTED,UNCHARTE,SPACY
+MALNOURISHED,MALNOURISH,SPACY
+MONEYED,MONEYE,SPACY
+UNTAMED,UNTAME,SPACY
+METHYLATED,METHYLATE,SPACY
+UNRELIEVED,UNRELIEVE,SPACY
+UNLETTERED,UNLETTERE,SPACY
+HOTBED,HOTBE,SPACY
+UNIMPROVED,UNIMPROVE,SPACY
+LOPSIDED,LOPSIDE,SPACY
+UNFEIGNED,UNFEIGNE,SPACY
+UNTESTED,UNTESTE,SPACY
+UNBLEMISHED,UNBLEMISHE,SPACY
+TECHNICS,TECHNIC,SPACY
+UNTAINTED,UNTAINTE,SPACY
+UNREGISTERED,UNREGISTERE,SPACY
+CUTLASS,CUTLAS,WORDNET
+UNFORMED,UNFORME,SPACY
+OVERWEENING,OVERWEENE,SPACY
+UNPROVIDED,UNPROVIDE,SPACY
+FOOTLIGHTS,FOOTLIGHT,SPACY
+UNCONVERTED,UNCONVERTE,SPACY
+OBSEQUIES,OBSEQUIE,SPACY
+PINCERS,PINCER,WORDNET
+MALADJUSTED,MALADJUSTE,SPACY
+ISOSCELES,ISOSCELE,SPACY
+UNPROVED,UNPROVE,SPACY
+AMIDSHIPS,AMIDSHIP,SPACY
+SEMISKILLED,SEMISKILLE,SPACY
+UNDIRECTED,UNDIRECTE,SPACY
+TABES,TABE,SPACY
+UNCLAIMED,UNCLAIME,SPACY
+PYJAMAS,PYJAMA,WORDNET
+UNPOLISHED,UNPOLISHE,SPACY
+FARSIGHTED,FARSIGHTE,SPACY
+FAUCES,FAUCE,SPACY
+NONCOMMISSIONED,NONCOMMISSIONE,SPACY
+UNCHARGED,UNCHARGE,SPACY
+CONGERIES,CONGERIE,SPACY
+SCABIES,SCABIE,SPACY
+MALFORMED,MALFORME,SPACY
+INFORMATICS,INFORMATIC,SPACY
+INCREMENTED,INCREMENTE,SPACY
+UNDISTRIBUTED,UNDISTRIBUTE,SPACY
+HYDRODYNAMICS,HYDRODYNAMIC,SPACY
+ANTIPODES,ANTIPODE,WORDNET
+UNDEREMPLOYED,UNDEREMPLOYE,SPACY
+VOLTE,VOLTA,WORDNET
+BIPED,BIPE,SPACY
+ELECTRODYNAMICS,ELECTRODYNAMIC,SPACY
+FEEBLEMINDED,FEEBLEMINDE,SPACY
+SUDS,SUD,SPACY
+UNDERSIZED,UNDERSIZE,SPACY
+HUSTINGS,HUSTING,SPACY
+STOREYED,STOREYE,SPACY
+UNREFINED,UNREFINE,SPACY
+UNTURNED,UNTURNE,SPACY
+SERRIED,SERRIE,SPACY
+DOLDRUMS,DOLDRUM,SPACY
+STATS,STAT,SPACY
+GULES,GULE,SPACY
+UNREWARDING,UNREWARDE,SPACY
+CALIPERS,CALIPER,WORDNET
+ONESIDED,ONESIDE,SPACY
+UNABRIDGED,UNABRIDGE,SPACY
+UNFURNISHED,UNFURNISHE,SPACY
+UNREDEEMED,UNREDEEME,SPACY
+UNSEEING,UNSEEE,SPACY
+UNLISTED,UNLISTE,SPACY
+INNARDS,INNARD,SPACY
+GLANDERS,GLANDER,SPACY
+OVEREXTENDED,OVEREXTEND,SPACY
+RELATIVIZED,RELATIVIZE,SPACY
+UNFUNDED,UNFUNDE,SPACY
+COLUMNED,COLUMNE,SPACY
+CALISTHENICS,CALISTHENIC,SPACY
+SUPERFICIES,SUPERFICIE,SPACY
+CASTELLATED,CASTELLATE,SPACY
+PUREBRED,PUREBRE,SPACY
+HINDQUARTERS,HINDQUARTER,WORDNET
+CORTES,CORTE,SPACY
+REDHEADED,REDHEADE,SPACY
+UNPRACTISED,UNPRACTISE,SPACY
+UNEDITED,UNEDITE,SPACY
+FES,FE,WORDNET
+LIVERIED,LIVERIE,SPACY
+NOSEBLEED,NOSEBLEE,SPACY
+UNDERFUNDED,UNDERFUNDE,SPACY
+CULOTTES,CULOTTE,WORDNET
+UNGRADED,UNGRADE,SPACY
+UNREDUCED,UNREDUCE,SPACY
+SICKBED,SICKBE,SPACY
+FASCES,FASCE,SPACY
+AVIONICS,AVIONIC,SPACY
+CRENELATED,CRENELATE,SPACY
+NATES,NATE,SPACY
+UNREGARDED,UNREGARDE,SPACY
+UNRECONSTRUCTED,UNRECONSTRUCTE,SPACY
+BRITCHES,BRITCHE,SPACY
+DEDANS,DEDAN,SPACY
+PARATROOPS,PARATROOP,SPACY
+FINEGRAINED,FINEGRAINE,SPACY
+GREAVES,GREAVE,WORDNET
+SUBSCRIPTED,SUBSCRIPTE,SPACY
+LUES,LUE,SPACY
+BIOMETRICS,BIOMETRIC,SPACY
+ARIES,ARIE,SPACY
+GASWORKS,GASWORK,SPACY
+BULLETED,BULLETE,SPACY
+ARTEL,ROTL,WORDNET
+HEARTSTRINGS,HEARTSTRING,SPACY
+INCREMENTING,INCREMENTE,SPACY
+UNCLEARED,UNCLEARE,SPACY
+CONSOLS,CONSOL,SPACY
+MUDFLATS,MUDFLAT,SPACY
+BADLANDS,BADLAND,SPACY
+TALIPES,TALIPE,SPACY
+CROSSWAYS,CROSSWAY,WORDNET
+LANCINATING,LANCINATE,SPACY
+UNACCOMPLISHED,UNACCOMPLISHE,SPACY
+TESSELLATED,TESSELLATE,SPACY
+SEMIFINISHED,SEMIFINISHE,SPACY
+UNAVENGED,UNAVENGE,SPACY
+PLEXIGLASS,PLEXIGLAS,WORDNET
+SOAPSUDS,SOAPSUD,SPACY
+BRANCHIAE,BRANCHIA,WORDNET
+YEATS,YEAT,SPACY
+TELEMATICS,TELEMATIC,SPACY
+UNNOTED,UNNOTE,SPACY
+MEALIES,MEALIE,WORDNET
+PARIES,PARIE,SPACY
+AUROCHS,AUROCH,SPACY
+AGOING,AGOE,SPACY
+ODDMENTS,ODDMENT,WORDNET
+CLEARHEADED,CLEARHEADE,SPACY
+REDOUBTED,REDOUBTE,SPACY
+DREADLOCKS,DREADLOCK,WORDNET
+IVIED,IVIE,SPACY
+PINNIPED,PINNIPE,SPACY
+DEFATTED,DEFATTE,SPACY
+DECAFFEINATED,DECAFFEINATE,SPACY
+NINEPINS,NINEPIN,WORDNET
+CAMPHORATED,CAMPHORATE,SPACY
+GLASSWORKS,GLASSWORK,WORDNET
+SORITES,SORITE,SPACY
+AFFOREST,AFFOR,SPACY
+DISSAVING,DISSAVE,SPACY
+UNADVISED,UNADVISE,SPACY
+UNRECLAIMED,UNRECLAIME,SPACY
+LARES,LARE,SPACY
+LEVELHEADED,LEVELHEADE,SPACY
+SWEATPANTS,SWEATPANT,SPACY
+LOTOS,LOTO,SPACY
+GIBLETS,GIBLET,WORDNET
+UNBOWED,UNBOWE,SPACY
+UNPROMPTED,UNPROMPTE,SPACY
+ABSCESSED,ABSCESSE,SPACY
+NODULATED,NODULATE,SPACY
+RUBENS,RUBEN,SPACY
+UNPAGED,UNPAGE,SPACY
+CALENDS,CALEND,SPACY
+TRUNKED,TRUNKE,SPACY
+TROUSERED,TROUSERE,SPACY
+PENATES,PENATE,SPACY
+COMBINATORICS,COMBINATORIC,SPACY
+TRESSED,TRESSE,SPACY
+PARTICOLOURED,PARTICOLOURE,SPACY
+UNENCRYPTED,UNENCRYPTE,SPACY
+ASTRONAUTICS,ASTRONAUTIC,SPACY
+HYDROPONICS,HYDROPONIC,SPACY
+UNFORMATTED,UNFORMATTE,SPACY
+SEMIDETACHED,SEMIDETACHE,SPACY
+BONKERS,BONKER,SPACY
+UNDIES,UNDIE,SPACY
+EPS,EP,SPACY
+GIMBALS,GIMBAL,WORDNET
+BALCONIED,BALCONIE,SPACY
+SALTWORKS,SALTWORK,SPACY
+SUSS,SUS,WORDNET
+UNPLEDGED,UNPLEDGE,SPACY
+PREDESIGNED,PREDESIGNE,SPACY
+NFS,NF,SPACY
+VELOURS,VELOUR,WORDNET
+UNDERBRED,UNDERBRE,SPACY
+PRECOMPILED,PRECOMPILE,SPACY
+KALENDS,KALEND,SPACY
+LITOTES,LITOTE,SPACY
+INDIGESTED,INDIGESTE,SPACY
+CITS,CIT,SPACY
+UNPRICED,UNPRICE,SPACY
+PINCHERS,PINCHER,SPACY
+CANCELLATED,CANCELLATE,SPACY
+CHITTERLINGS,CHITTERLING,SPACY
+DIBS,DIB,SPACY
+PHARMACEUTICS,PHARMACEUTIC,WORDNET
+RIGHTWARDS,RIGHTWARD,SPACY
+CONVENANCES,CONVENANCE,SPACY
+INTERALLIED,INTERALLIE,SPACY
+FLINDERS,FLINDER,SPACY
+CRANNIED,CRANNIE,SPACY
+HOMEBRED,HOMEBRE,SPACY
+HIGHBRED,HIGHBRE,SPACY
+UNRULED,UNRULE,SPACY
+FOREHANDED,FOREHANDE,SPACY
+PREPACKED,PREPACKE,SPACY
+UNWISHED,UNWISHE,SPACY
+ENTREMETS,ENTREMET,SPACY
+ESTOVERS,ESTOVER,SPACY
+ANGELES,ANGELE,SPACY
+DAISIED,DAISIE,SPACY
+KUMISS,KUMIS,WORDNET
+UPRATED,UPRATE,SPACY
+THIGHED,THIGHE,SPACY
+TURPS,TURP,WORDNET
+WEAZENED,WEAZENE,SPACY
+EFFING,EFF,SPACY
+HOLS,HOL,SPACY
+JIGGERED,JIGGERE,SPACY
+SOCRATES,SOCRATE,SPACY
+AUDITORIES,AUDITORIE,SPACY
+AMBAGES,AMBAGE,WORDNET
+DOITED,DOITE,SPACY
+BIONICS,BIONIC,SPACY
+UNREFERENCED,UNREFERENCE,SPACY
+TENPINS,TENPIN,WORDNET
+EXEQUIES,EXEQUIE,SPACY
+JUDAS,JUDA,WORDNET
+CERASTES,CERASTE,SPACY
+SEMIMANUFACTURES,SEMIMANUFACTURE,SPACY
+GALLUSES,GALLUS,WORDNET
+RERECORDED,RERECORDE,SPACY
+TELESALES,TELESALE,SPACY
+MICROGRAPHICS,MICROGRAPHIC,SPACY
+SIEMENS,SIEMEN,SPACY
+ZOUNDS,ZOUND,SPACY
+SEMIFIXED,SEMIFIXE,SPACY
+UNDIVERTED,UNDIVERTE,SPACY
+BBS,BB,WORDNET
+LYONS,LYON,WORDNET
+SANIES,SANIE,SPACY
+BREECHING,BREECHE,SPACY
+MENTHOLATED,MENTHOLATE,SPACY
+PANTALETS,PANTALET,SPACY
+CRUDITES,CRUDITE,SPACY
+TRAPES,TRAPE,SPACY
+PIXILATED,PIXILATE,SPACY
+BOOTES,BOOTE,SPACY
+UNPOSTED,UNPOSTE,SPACY
+PLIMSOLLS,PLIMSOLL,WORDNET
+HANTS,HANT,SPACY
+UNDETAILED,UNDETAILE,SPACY
+HAVINGS,HAVING,SPACY
+OUTGIVING,OUTGIVE,SPACY
+UNCOMPLEMENTED,UNCOMPLEMENTE,SPACY
+PRATIES,PRATIE,SPACY
+ELEVENSES,ELEVENSE,SPACY
+UNENLIVENED,UNENLIVENE,SPACY
+NANTES,NANTE,SPACY
+AFFINED,AFFINE,SPACY
+NONNESTED,NONNESTE,SPACY
+FALLOWING,FALLOWE,SPACY
+KANSAS,KANSA,WORDNET
+HYDROMECHANICS,HYDROMECHANIC,SPACY
+CLIVERS,CLIVER,SPACY
+UNICES,UNICE,SPACY
+GRAMMATICS,GRAMMATIC,SPACY
+PRAPS,PRAP,SPACY
+INTERWORKING,INTERWORKE,SPACY
+VENTURIS,VENTURI,WORDNET
+HERCULES,HERCULE,SPACY
+BIGHEADED,BIGHEADE,SPACY
+KIES,KY,WORDNET
+NETHERLANDS,NETHERLAND,SPACY
+UNBOOKED,UNBOOKE,SPACY
+QUINS,QUIN,WORDNET
+CANNES,CANNE,SPACY
+UNNURTURED,UNNURTURE,SPACY
+WEDGIES,WEDGIE,WORDNET
+HANDWORKED,HANDWORKE,SPACY
+ANALECTS,ANALECT,SPACY
+HERTS,HERT,SPACY
+ORLEANS,ORLEAN,SPACY
+PESCADORES,PESCADORE,SPACY
+ULCERED,ULCERE,SPACY
+MISCREATED,MISCREATE,SPACY
+UNPRIZED,UNPRIZE,SPACY
+MEGAFLOPS,MEGAFLOP,WORDNET
+SLYBOOTS,SLYBOOT,SPACY
+RUNTED,RUNTE,SPACY
+REATTRIBUTED,REATTRIBUTE,SPACY
+HOUSETRAINED,HOUSETRAINE,SPACY
+SOBERSIDES,SOBERSIDE,SPACY
+COLESEED,COLESEE,SPACY
+BLUCHERS,BLUCHER,WORDNET
+MUGGINS,MUGGIN,SPACY
+UNCRIPPLED,UNCRIPPLE,SPACY
+HEPPED,HEPPE,SPACY
+WITHINDOORS,WITHINDOOR,SPACY
+BEESTINGS,BEESTING,SPACY
+FLANDERS,FLANDER,SPACY
+DIOGENES,DIOGENE,SPACY
+COSMONAUTICS,COSMONAUTIC,SPACY
+WHOLEGRAINS,WHOLEGRAIN,SPACY
+NEEDMENTS,NEEDMENT,SPACY
+ACHATES,ACHATE,SPACY
+PRECOMPILING,PRECOMPILE,SPACY
+BALUSTERED,BALUSTERE,SPACY
+JUGGINS,JUGGIN,SPACY
+UNCONFIGURED,UNCONFIGURE,SPACY
+SLUGABED,SLUGABE,SPACY
+CHARGRILLED,CHARGRILLE,SPACY
+GANGES,GANGE,SPACY
+FLATWAYS,FLATWAY,SPACY
+CHAMPERS,CHAMPER,SPACY
+GOLDILOCKS,GOLDILOCK,SPACY
+REIMS,REIM,SPACY
+REIMPORTING,REIMPORTE,SPACY
+EMOTIONED,EMOTIONE,SPACY
+AIRBED,AIRBE,SPACY
+GIGAFLOPS,GIGAFLOP,SPACY
+YONKS,YONK,SPACY
+CASALS,CASAL,SPACY
+ROCKIES,ROCKIE,SPACY
+ORESTES,ORESTE,SPACY
+REMAPPING,REMAPPE,SPACY
+EBONICS,EBONIC,SPACY
+BRUGES,BRUGE,SPACY
+JANKERS,JANKER,SPACY
+NOTTS,NOTT,SPACY
+PROCRUSTES,PROCRUSTE,SPACY
+MULTISCALED,MULTISCALE,SPACY
+AGROTECHNICS,AGROTECHNIC,SPACY
+WAYGOING,WAYGOE,SPACY
+GENDERING,GENDERE,SPACY
+TELEMECHANICS,TELEMECHANIC,SPACY
+DEGATING,DEGATE,SPACY
+THAMES,THAME,SPACY
+LOWLIVED,LOWLIVE,SPACY
+REEDING,REEDE,SPACY
+INTERCROSSING,INTERCROSSE,SPACY
+UNDEDUCTED,UNDEDUCTE,SPACY
+AGOGICS,AGOGIC,SPACY
+UNATTENDING,UNATTENDE,SPACY
+OVERMASTED,OVERMASTE,SPACY
+GILES,GILE,SPACY
+NONCOPYRIGHTED,NONCOPYRIGHTE,SPACY
+LUDDITES,LUDDITE,WORDNET
+SCURVIED,SCURVIE,SPACY
+REBREAKING,REBREAKE,SPACY
+KEATS,KEAT,SPACY
+CERVANTES,CERVANTE,SPACY
+UNCONDONED,UNCONDONE,SPACY
+DESCARTES,DESCARTE,SPACY
+BEJABERS,BEJABER,SPACY
+VIDEOGRAPHICS,VIDEOGRAPHIC,SPACY
+EURIPIDES,EURIPIDE,SPACY
+UNPERJURED,UNPERJURE,SPACY
+LAERTES,LAERTE,SPACY
+OVERCOLLECTED,OVERCOLLECTE,SPACY
+AMPHIBRACHYS,AMPHIBRACHY,SPACY
+CHEOPS,CHEOP,SPACY
+CHALONS,CHALON,SPACY
+VERSICOLOURED,VERSICOLOURE,SPACY
+SUBPARTITIONED,SUBPARTITIONE,SPACY
+BALBUTIES,BALBUTIE,SPACY
+ARCHIMEDES,ARCHIMEDE,SPACY
+GATELEGGED,GATELEGGE,SPACY
+POITIERS,POITIER,WORDNET
+HAVERING,HAVERE,SPACY
+THEBES,THEBE,WORDNET
+SEVRES,SEVRE,SPACY
+PERICLES,PERICLE,SPACY
+LIMOGES,LIMOGE,SPACY
+EVENTING,EVENTE,SPACY
+FATBITS,FATBIT,SPACY
+HUTTING,HUTTE,SPACY
+PYTHIAS,PYTHIA,WORDNET
+DOGSHORES,DOGSHORE,SPACY
+OVERBADING,OVERBADE,SPACY
+AZORES,AZORE,SPACY
+BLEWITS,BLEWIT,SPACY
+HIPOCRATES,HIPOCRATE,SPACY
+AMIENS,AMIEN,SPACY
+GUTTING,GUTTE,SPACY
+GLADYS,GLADY,SPACY
+CHADDED,CHADDE,SPACY
+EUPHRATES,EUPHRATE,SPACY
+TROWING,TROWE,SPACY
+LACEUPS,LACEUP,SPACY
+ALIPED,ALIPE,SPACY
+TALIPED,TALIPE,SPACY
+RAMSES,RAMSE,SPACY
+CENTRONICS,CENTRONIC,SPACY
+MITHRAS,MITHRA,WORDNET
+BANTING,BANTE,SPACY
+TELEPHOTOLENS,TELEPHOTOLEN,SPACY
+ARAKS,ARAK,WORDNET
+DONETS,DONET,SPACY
+CEROPLASTICS,CEROPLASTIC,SPACY
+BAYNETWORKS,BAYNETWORK,SPACY
+NORWARDS,NORWARD,SPACY
+HAPPING,HAPPE,SPACY
+BARENTS,BARENT,SPACY
+ABLINGS,ABLING,SPACY
+CELLING,CELLE,SPACY
+DONBASS,DONBAS,WORDNET
+CELEBES,CELEBE,SPACY
+NENETS,NENET,SPACY
+IMPING,IMPE,SPACY
+LINARES,LINARE,SPACY
+VAILING,VAILE,SPACY
+HABDABS,HABDAB,SPACY
+RELISTING,RELISTE,SPACY
+HOUGHING,HOUGHE,SPACY

wordlist/01-lemmatized-words.py

@@ -17,14 +17,17 @@ except:
 wordnet = WordNetLemmatizer()
 
 # Spacy
-nlp = spacy.load('en_core_web_trf', disable=['parser', 'ner'])
+nlp = spacy.load("en_core_web_trf", disable=["parser", "ner"])
 
 print("Loading initial wordlist")
 
 words = []
-with gzip.open("./00-frequency-list.csv.gz", 'r') as infile:
+with open("./00-dsiquintans-nounlist.txt", "r") as infile:
     for line in infile:
-        words.append(line.decode('ascii').split(",")[0])
+        words.append(line.split(",")[0].strip())
+with gzip.open("./00-frequency-list.csv.gz", "r") as infile:
+    for line in infile:
+        words.append(line.decode("ascii").split(",")[0])
 
 # Remove header
 words = words[1:]
@@ -35,10 +38,10 @@ print("Lemmatizing words")
 
 seen_lemmatizations = set()
 
-with open("./01-errored-lemmatized-words.csv", 'w') as erroutfile:
+with open("./01-errored-lemmatized-words.csv", "w") as erroutfile:
     erroutfile.write("WORD,ATTEMPTED_LEMMATIZATION,LEMMATIZER\n")
 
-    with gzip.open("./01-lemmatized-words.csv.gz", 'w') as outfile:
+    with gzip.open("./01-lemmatized-words.csv.gz", "w") as outfile:
         outfile.write("WORD,LEMMATIZED_WORD,LEMMATIZER\n".encode("ascii"))
 
         iter = tqdm(words)
@@ -46,12 +49,12 @@ with open("./01-errored-lemmatized-words.csv", 'w') as erroutfile:
         for word in iter:
             lemmatized_words = [
                 # Wordnet
-                (wordnet.lemmatize(word).upper(), 'WORDNET'),
+                (wordnet.lemmatize(word.lower()).upper(), "WORDNET"),
                 # Spacy
-                (nlp(word)[0].lemma_.upper().upper(), 'SPACY'),
+                (nlp(word)[0].lemma_.upper().upper(), "SPACY"),
             ]
 
-            for (lemmatized_word, lemmatizer) in lemmatized_words:
+            for lemmatized_word, lemmatizer in lemmatized_words:
                 if word == lemmatized_word:
                     continue
 
@@ -67,4 +70,6 @@ with open("./01-errored-lemmatized-words.csv", 'w') as erroutfile:
 
                 iter.write(f"{word} => {lemmatized_word} ({lemmatizer}) added")
 
-                outfile.write(f"{word},{lemmatized_word},{lemmatizer}\n".encode("ascii"))
+                outfile.write(
+                    f"{word},{lemmatized_word},{lemmatizer}\n".encode("ascii")
+                )

wordlist/02-custom-lemmatizations.csv

@@ -6,11 +6,14 @@ AFFECT,EFFECT
 AFFECTIONS,AFFECTION
 AFFECTIVE,EFFECT
 AFFECTS,EFFECT
+AID,AIDE
 ALUMINIUM,ALUMINUM
+ANALOGUE,ANALOG
 ANALYSE,ANALYZE
 ANALYSED,ANALYZE
 ANALYSES,ANALYZE
 AUX,OX
+BAGGY,BAGGIE
 BE,BEE
 BERRY,BARRY
 BLEW,BLUE
@@ -24,8 +27,12 @@ CAPITOL,CAPITAL
 CENTRE,CENTER
 CENTS,CENT
 CENTS,SENSE
+CERAMICS,CERAMIC
+CHEQUE,CHECK
 CHILE,CHILI
 CHILE,CHILLY
+CHORD,CORD
+CIVILISATION,CIVILIZATION
 COLOURLESS,COLORLESS
 COM,CALM
 CORP,CORE
@@ -109,3 +116,4 @@ WEARY,WARY
 WEIGHS,WAY
 WEIGH,WAY
 YELLOW,HELLO
+YOKE,YOLK

wordlist/04-deduplicated-words.py

@@ -6,22 +6,24 @@ from pprint import pprint
 from tqdm import tqdm
 
 # 2**13 + 2 since two can be skipped
-WORDLIST_SIZE=4096+2
+WORDLIST_SIZE = 4096 + 2
 
 print("Loading full wordlist")
 
 all_words = []
-with gzip.open("./00-frequency-list.csv.gz", 'r') as infile:
+with gzip.open("./00-frequency-list.csv.gz", "r") as infile:
     first = True
     for line in infile:
         if first:
             first = False
             continue
-        all_words.append(line.decode('ascii').split(",")[0])
+        all_words.append(line.decode("ascii").split(",")[0])
 
 print("Building lemmatization graph")
 
 lemmatization_graph = list()
+
+
 def add_lemmatization(word1, word2):
     for lemmatization in lemmatization_graph:
         word1_contained = word1 in lemmatization
@@ -29,7 +31,9 @@ def add_lemmatization(word1, word2):
 
         if word1_contained or word2_contained:
             if word1_contained and word2_contained:
-                print(f"Warning: lemmatization {word1}<=>{word2} already in set: {lemmatization}")
+                print(
+                    f"Warning: lemmatization {word1}<=>{word2} already in set: {lemmatization}"
+                )
 
             lemmatization.add(word1)
             lemmatization.add(word2)
@@ -43,11 +47,13 @@ def add_lemmatization(word1, word2):
     # If we get here, there is no known lemmatization between these two. Add it
     lemmatization_graph.append(set((word1, word2)))
 
+
 def get_lemmatization(word):
     for lemmatization in lemmatization_graph:
         if word in lemmatization:
             return lemmatization
 
+
 print("\tAdding automatic lemmatizations")
 # First, iterate over automated lemmatizations
 with gzip.open("./01-lemmatized-words.csv.gz") as infile:
@@ -56,7 +62,7 @@ with gzip.open("./01-lemmatized-words.csv.gz") as infile:
         if first:
             first = False
             continue
-        split = line.decode('ascii').strip().split(",")
+        split = line.decode("ascii").strip().split(",")
         add_lemmatization(split[0], split[1])
 
 print("\tAdding custom lemmatizations")
@@ -95,7 +101,7 @@ for word in all_words:
     if not word_lemmatizations:
         word_lemmatizations = set([word])
 
-    if len(word_lemmatizations - exclude_words) != len(word_lemmatizations) :
+    if len(word_lemmatizations - exclude_words) != len(word_lemmatizations):
         print(f"Note: {word_lemmatizations} is excluded")
         continue
 
@@ -125,8 +131,8 @@ final_wordlist = [
     for word in words
 ]
 
-with open("./04-deduplicated-words.csv", 'w') as outfile:
+with open("./04-deduplicated-words.csv", "w") as outfile:
     outfile.write("WORD,NUMBER\n")
-    for (idx, word) in final_wordlist:
+    for idx, word in final_wordlist:
         outfile.write(f"{word},{idx}\n")
         # all_words.append(line.decode('ascii').split(",")[0])