package shenikan // Tips: in python run // // import gensim.downloader // model = gensim.downloader.load("glove-wiki-gigaword-50") # or other models @https://github.com/piskvorky/gensim-data // // Then find words related to what you want in model[] and do math on them. // Then search through model to find nearby vectors using model.most_similar. // e.g. model.most_similar(model['aunt'] - model['woman'] + model['man']) // TODO: try generating a penta for each non-syntactic word in toki pona. // TODO: make more AvB BvC AvBvC penta/icosa sets _dictionary: { glyphs: { vowel: "i": ["outer"] vowel: "e": ["outer", "slashed"] vowel: "a": ["slashed"] vowel: "o": ["inner", "slashed"] vowel: "u": ["inner"] vowel: "y": ["inner", "outer"] cluster: "θ": ["left", "top"] cluster: "∫": ["left", "middle"] cluster: "x": ["left", "bottom"] cluster: "n": ["center", "middle"] cluster: "p": ["right", "top"] cluster: "t": ["right", "middle"] cluster: "k": ["right", "bottom"] cluster: "θl": ["left", "top", "wide"] cluster: "∫l": ["left", "middle", "wide"] cluster: "xl": ["left", "bottom", "wide"] cluster: "nl": ["center", "middle", "wide"] // use sparingly? cluster: "l": ["right", "top", "wide"] // allophone of pl cluster: "tl": ["right", "middle", "wide"] cluster: "kl": ["right", "bottom", "wide"] cluster: "θr": ["left", "top", "tall"] cluster: "∫r": ["left", "middle", "tall"] cluster: "xr": ["left", "bottom", "tall"] cluster: "nr": ["center", "middle", "tall"] // use sparingly? cluster: "r": ["right", "top", "tall"] // allophone of pr cluster: "tr": ["right", "middle", "tall"] cluster: "kr": ["right", "bottom", "tall"] cluster: "sθ": ["left", "top", "both"] cluster: "s∫": ["left", "middle", "both"] cluster: "sx": ["left", "bottom", "both"] cluster: "sn": ["center", "middle", "both"] cluster: "sp": ["right", "top", "both"] cluster: "st": ["right", "middle", "both"] cluster: "sk": ["right", "bottom", "both"] punctuation: "«": ["left"] punctuation: ".": [] punctuation: "»": ["right"] numeric: "0": ["circle"] numeric: "1": ["dash"] numeric: "2": ["vee"] numeric: "3": ["hump"] numeric: "4": ["dash", "hump"] numeric: "5": ["vee", "hump"] numeric: ",": ["dot"] } dialects: { // TODO: make these per-consonant-cluster "shenkian": { "l": "pl" "r": "pr" } "jukashenikan": { "x": "ç" "p": "j" } "gazhenigan": { "k": "g" "∫": "ʒ" "s": "z" "θ": "ð" "t": "d" } } dms: { "-at": noun: "place of" "plaxi-": noun: "study of" } words: { "t": { noun: "thing": "See t - dmPenta for better meaning." verb: "be" } "tit": { noun: "cool" from: "t": via: "-t" } } pentas: { "n x": { name: "Pronouns" extremes: {i: "Fully proximal", u: "Fully distal"} i: pronoun: "I/me" o: {} } "p ls": { name: "Coordinating Conjunctions" extremes: {i: "Fully constrasting", u: "Fully non-contrasting"} i: conjunction: "but/yet" e: conjunction: "exclusive or" a: conjunction: "or": "inclusive or" o: conjunction: "implies": "logical implication (not p or q)" u: conjunction: "and" } "sp ns": { name: "Group Clusivity" extremes: {i: "Fully included", u: "Fully excluded"} i: adposition: "among" e: adposition: "with" a: adposition: "throughout" o: adposition: "without" u: adposition: "out" } "r ks": { name: "Process" extremes: {i: "Beginning", u: "Ending"} i: {verb: "start", noun: "start"} e: {verb: "resume", noun: "resumption"} a: {verb: "continue", noun: "continuation"} o: {verb: "stop", noun: "stop"} u: {verb: "finish", noun: "finish"} } "sp t": { name: "Truth" extremes: {i: "True", u: "False"} i: {adjective: "true", noun: "truth"} e: {adjective: "valid", noun: "validity"} a: { adjective: unknown: "Truth value unknown" noun: unknown: "Unknown truth value" } o: {adjective: "invalid", noun: "invalidity"} u: {adjective: "false", noun: "falsehood"} } "sp shs": { name: "Biomes" extremes: {i: "Wet Biomes", u: "Dry Biomes"} i: noun: ["swamp", "wetlands"] e: noun: "rainforest" a: noun: "forest" o: noun: "grassland" u: noun: "desert" } "sth ps": { name: "Generic Plants" extremes: {i: "Trees", u: "Grasses"} i: noun: "tree" e: noun: "vine" a: noun: "bush" o: noun: "crop" u: noun: "grass" } "k ks": { name: "Queries" extremes: {i: "Abstract", u: "Concrete"} i: noun: "why" e: noun: "how" a: noun: "when" o: noun: "where" u: noun: ["what", "which", "who"] } } icosas: { "sth sp shs": { name: "Plants" extremes: { ix: "Trees" ux: "Grasses" xi: "Wet" xu: "Dry" } ix: "Trees" ex: "Vines" ax: "Bushes" ox: "Crops" ux: "Grasses" xi: "Swamp Plants" xe: "Rainforest Plants" xa: "Forest Plants" xo: "Grassland Plants" xu: "Desert Plants" ii: noun: "conifer tree" ie: noun: "deciduous tree" ia: noun: "temperate tree" io: noun: "palm tree" iu: noun: "desert tree": "Acacia for example" ei: noun: "lily" ee: noun: "vine" ea: noun: "ivy" eo: noun: "vine flower": "Rose for example" eu: noun: "thornbush" ai: noun: "seaweed" ae: noun: "fern" aa: noun: "bush" ao: noun: "shrub" au: noun: "cactus" oi: noun: "fruit tree" oe: noun: "berry bush" oa: noun: "legume" oo: noun: "cabbage": "Or similar grassland crop" ou: noun: "grain" ui: noun: "moss" ue: noun: "flower": "Specifically ground or \"low\" flowers" ua: noun: "grass" uo: noun: "corn/maize" uu: noun: "lichen" } "sth sp sshat": { name: "Biomes" } } dmPentas: { "t -": { name: "Articles" extremes: {i: "Specific", u: "General"} i: syntax: "proper noun indicator" e: syntax: "the" a: syntax: "a" o: syntax: ["any", "some"] u: syntax: "all" } "k -": { name: "Listing Prefixes" extremes: {i: "Additive", u: "Reductive"} i: syntax: "or": "Inclusive or" e: syntax: "or": "Exclusive or" a: syntax: "and" o: syntax: "xnor": "Exclusive nor" u: syntax: "nor": "Neither nor" } } }