/psu-language-modeling-session

The code of the "Language Models and Their Applications" session

Primary LanguageJupyter NotebookMIT LicenseMIT

Source code of My Language Modeling Session at Prince Sultan University

The code of the Language Models and Their Applications by Faris Abdullah Alasmary session. It contains three notebooks:

  • 1_Prepare_Data.ipynb: contains the data preparation steps.
  • 2_Train_N_Gram_Language_Model.ipynb: contains the steps to used the prepared data in the previous notebook to build an ARPA N-gram language model using KenLM.
  • 3_LM_Applications.ipynb: shows some applications of the language model such as next word prediction, spell correction and connected words splitting.