@prefix clarin_el: <http://w3id.org/clarin_el_dictionary/> .
@prefix skos: <http://www.w3.org/2004/02/skos/core#> .
@prefix dc: <http://purl.org/dc/terms/> .
@prefix omtd: <http://w3id.org/meta-share/omtd-share/> .

clarin_el:trainingOfNmtModels
  skos:prefLabel "training of NMT models"@en, "εκπαίδευση μοντέλων NMM"@el ;
  a skos:Concept ;
  skos:broader clarin_el:languageModelling .

clarin_el:trainingOfLanguageModels
  skos:prefLabel "training of language models"@en, "εκπαίδευση γλωσσικών μοντέλων"@el ;
  a skos:Concept ;
  skos:broader clarin_el:languageModelling .

clarin_el:dialogueModelling
  skos:prefLabel "dialogue modelling"@en, "μοντελοποίηση διαλόγου"@el ;
  a skos:Concept ;
  skos:broader clarin_el:languageModelling .

clarin_el:supportOperation
  skos:prefLabel "support operation"@en, "λειτουργία υποστήριξης"@el ;
  a skos:Concept ;
  skos:narrower clarin_el:languageModelling .

clarin_el:lrtInfrastructureScheme
  skos:prefLabel "Λεξικό CLARIN:EL"@el, "CLARIN:EL Dictionary"@en ;
  a skos:ConceptScheme .

clarin_el:trainingOfMachineLearningModels
  skos:prefLabel "training of machine learning models"@en, "εκπαίδευση μοντέλων μηχανικής μάθησης"@el ;
  a skos:Concept ;
  skos:broader clarin_el:languageModelling .

clarin_el:languageModelling
  skos:altLabel "language modeling"@en, "LM"@en ;
  skos:inScheme clarin_el:lrtInfrastructureScheme ;
  skos:narrower clarin_el:trainingOfNmtModels, clarin_el:trainingOfMachineLearningModels, clarin_el:trainingOfLanguageModels, clarin_el:dialogueModelling, clarin_el:statisticalLanguageModelling ;
  dc:source "https://www.di.uoa.gr/sites/default/files/documents/grad/M908-YPOLOGISTIKH_GLVSSOLOGIA_NLP_DIAXEIRISH_GLWSSIKWN_PORWN.pdf" ;
  skos:note "A Statistical Language Model predicts a word given a sequence of already known words (i.e. the history). Ist can also be applied to other sequences of symbols (e.g. DNA). Very often the history contains just the previous two words. This is called a trigram. The parameters of statistical language models are estimated from a set of training examples. Data sparsity and smoothing of the estimates is one of the core problems. The best smoothing technique known so far is Kneser-Ney-Smoothing. Maximum-Entropy techniques are also under investigation and may be the method of choice for long-range language models (beyond trigram). Language models are used in text-compression, speech recognition, information retrieval and information extraction."@en ;
  skos:definition "η κατασκευή στατιστικών γλωσσικών μοντέλων ή μοντέλων μηχανικής μάθησης"@el, "the construction of statistical or Machine Learning language models"@en ;
  skos:exactMatch omtd:LanguageModelling ;
  a skos:Concept ;
  skos:prefLabel "language modelling"@en, "γλωσσική μοντελοποίηση"@el ;
  skos:broader clarin_el:supportOperation .

clarin_el:statisticalLanguageModelling
  skos:prefLabel "statistical language modelling"@en, "στατιστική μοντελοποίηση γλώσσας"@el ;
  a skos:Concept ;
  skos:broader clarin_el:languageModelling .