Skip to content

Latest commit

 

History

History
11 lines (10 loc) · 714 Bytes

README.md

File metadata and controls

11 lines (10 loc) · 714 Bytes

Text-Summarization-models-for-Assamese

  1. Text summarization Models including (LSTM, BILSTM, & GRU with combination) to generate most efficient model
  2. Encoder Decoder Model is used together with FastText assamese bin.
  3. The efficiency is calculated by ROUGE Scores.
  4. You can download the FastText Assamese bin file from the link below :
    https://dl.fbaipublicfiles.com/fasttext/vectors-crawl/cc.as.300.bin.gz
  5. For the Dataset, refer to the link:
    https://www.kaggle.com/datasets/krishnabhdas/assamese-news-article-dataset
  6. For the Scrapper used (to extract data from news channels), refer to the link:
    https://github.com/Krishnabh-Das/Assamese-News-Article-Dataset-Web-Scrapper-