IA ci Decifrement làkk yu yàgg
IA dafay jàppale gëstukat yi ñu mëna jàng script yi réer ak mbind yi yàqu ci gis motif statistik yi ci màndarga yi, defaraat araf yi réer, ak digle tekki.
Résumé
It turns decipherment from decades of manual guesswork into a faster, data-driven collaboration.
Plongeur bu xóot
Decifre ab làkk bu yàgg mooy nga xam naka ay màndargaam di méngoo ak son yi ak luñuy tekki, lu ci bari du am benn mbind bu des te amul caabi ñaari làkk. Jàngum masin dafay jàppale ci anam yu bari. Reseau neuronal yi mën nañu boole ay màndarga yu bari ngir xàmmee baat yi, suffix yi ak nàfar yi. Su amee mbind mu yàqu wala mu yàqu, modelu sekans yiñ tàggat ci corpus bi mën nañu xam araf yi gëna ñàkk, ni telefon di defee baat yi ci seen bopp. Modèlu Ithaca bu DeepMind, tàggat ci fukki junni mbindu Grek, defaraat mbind yi yàqu, xayma fumu ak kañ lañu bind mbind, ba noppi jox taarixkat yi ay xalaat yu ñu wara jàngat. Yeneen projet yi jëfandikoo nañu ay lim ngir lëkkale mbind yiñ xamul, lu ci melni Linear B ak Ugaritic, ak làkk yiñ xam te gëna gaaw ci tekki làkk.
Gis-gis xarala
Model yi dañuy jàppee script yi ni ay jeton yu toppalante, ba noppi jàng ni màndarga yi di toppee ñeneen ñi. Ngir defaraat, ab transformateur wala reso recurrent lañuy tàggat ci passage yu amul benn sikk, ba noppi ñu laaj leen ñu feesal ay bërëb yuñ maske, ñu génne ay personage yuñ tànn ñu am poñ yu wóolu seen bopp. Alignment cross-lingual dafay dox ci xayma motif symbol yu lakk buñu xamul ci structure buñu xamee ci benn mbokk buñu xalaat, di wane ni xayma bi di defaree baat yu dëggu yi.
njeextalu pexe
Tabax tànneef
Ni ñuy jëmmale aplikaasioŋ bi mooy wane ndax IA dafay gëna baaxal njariñ yi.
Ekip ak def liggéey
Integraasioŋ bu baax ci def liggéey dafay jur njariñu liggéey bu jëfandikukat yi mëna wóolu.
Risk ak kaaraange
Jëfandikoo bu jaar yoon dina wàññi coono coppite ak risku samp gi.
Ëlëgu IA ci Deciphering làkk yu yàgg yi
Li gëna tar ci des mooy script yiñ desifrewul ak corpus yu ndaw te amul benn mbokk buñu xamul, lu melni script Indus Valley ak Linear A, fu ñàkkum done tënk li lim yi mëna firnde. Sistem yi ci kanam dina ñu boole ay misaali làkk ak jàngat nataal ngir jàng tablet yu erode yi ak seal yi ci nataal yi. Gëstukat yi wonenañu ni IA dina des ap ndimmbal bu am doole te du wuutu, loolu nak mungi jur ay xalaat yu nit ñi wara natt ci taarix ak ci anam wi ñu koy defe.
Doxal ci àdduna dëgg
Modèlu Ithaca bu DeepMind dafay defaraat kàddu yi ñàkk ci bind yu Grees yu yàgg yi yàqu, ba noppi xayma seen bis ak barab bi ñu bawoo, gëna yokk njubteg taarixkat yi suñu leen boole jëfandikoo.
Jàngum masin jëfandikoo nañu ko ci Linear B ak ci Linear A bi ko méngoo ngir natt fonetik ak vokabileer ci wàllu Grek bu Mycenaean.
Jëfandikoo nañu pexe yu ñuy jëfandikoo ngir tekki làkku Ugarit, ñu boole ko ci saasi ak làkku Hebrew bi gëna jege.
Gëstukat yi dañuy jëfandikoo juntuwaay yu bees yi ngir defaraat ak jàng ay tablo cuneiforme yu tass, di seetlu màndarga yu yàqu yi ci mbindu Akkadien ak Sumerien.
Risk yi ak balustrade yi
Otomatise procédure bu yàqu mën na yokk jafe-jafe yi fi nekk.
Ekip yi mën nañu otomatise lu ëpp ba noppi dindi àtteb nit ñi.
Kalite mën na wàññeeku sudee duñu wéy di jàngat li ñuy génne.
Roadmap ngir samp gi
Defal kàrt ni liggéey bi di doxee leegi nga ràññee jéego bi gëna am jafe-jafe.
Mandargal barabu saytu nit balaa otomatisasioŋ bu mat sëkk.
Taggat jëfandikukat yi ci ay laaj, yooni eskalaasioŋ ak seeni sàrti kalite.
Toppal njariñu niveau liggéey bi ngir firndeel valeur buy wéy.
Weyal di banneexu
Free newsletter
Get the daily AI briefing
Three verified AI stories every weekday morning, written in plain English. Free forever, no ads.
One email each weekday. Unsubscribe in one click. We never sell or share your address.
Test yourself
Take the AI in Ancient Language Decipherment quiz
Instant feedback on every answer, and a shareable certificate with a verifiable ID once you pass a course.
Support free AI education. AI Understanding is a 501(c)(3) nonprofit — no ads, no paywall, ever. Make a donation
Gis bi ci topp
IA ci tekki làkku màndarga
Laaj yi ñuy faral di laaj
What is AI in Ancient Language Decipherment?
IA dafay jàppale gëstukat yi ñu mëna jàng script yi réer ak mbind yi yàqu ci gis motif statistik yi ci màndarga yi, defaraat araf yi réer, ak digle tekki. Dafay soppi decifrement bi juge ci ay fukki at ci liggéeyum loxo ci liggéeyandoo bu gëna gaaw, lalu ci done.
Lan la xeetu Ithaca bu DeepMind def ci mbindu Grek yu yàgg ya?
Ithaca dañu ko tàggat ci fukki junniy mbindu Grek ngir defar barab yu yàqu, ba noppi xam kañ lañu leen bind ak fumu leen bind, te loolu dafay jàppale taarixkat yi.
Ak lan la xeetu toppalante di jàppale sudee mbind mu yàgg dafa yàqu wala dafa màgget?
Ñu ngi ko tàggat ci mbind mu amul benn sikk, model bi dafay feexal bërëb yiñ maskeer ci di wax luy waaja am ci araf yi, lu melni autocomplete, ba noppi di joxe kàndidaa yiñ tànn.
Lan moo waral script yu melni Linear A ak script Indus Valley di jafe lool ci IA mu déglu ko?
Pexem lim yi dañu soxla ay done ak ab mbokk buñu xamee; corpus yu ndaw ak script yuñ tàqale duñu bàyyi siñaal bu bari ngir firndeel desifre.
Luy lëkkaloo làkk yu bari ci wàllu desifre?
Su gëstukat yi boole làkk wi ñu xamul ci làkk wi ñu jàpp ni mooy làkk wiñ xam, ba noppi ñu xool ndax amna kàddu yu dëggu yu feeñ, dina ñu mëna saytu limu lëkkaloo, ni ñu ko defee ci Ougarit ak Hebreu.
naka la ko model yii di wane ab script ci biir?
Script yi dañu leen di jàppee ni mbind yu toppalante; model bi dafay jàng ban màndarga moo bëgga topp ban, loolu mooy tax ñu mëna defaraat ak gis motif yi.