Skip to content

Latest commit

 

History

History
9 lines (8 loc) · 681 Bytes

README.md

File metadata and controls

9 lines (8 loc) · 681 Bytes

Language-Translation

  1. Combination of different NMT architectures for Machine Translation Task. Currently, GCNN (Gated Convolution Neural Network) model is completed for German to English Translation and it has a BLEU score of 32.4.
  2. BERT-base model is completed.
  3. English to Hindi CNN Sequence to Sequence Model is trained with MultiIndic Language Corpus. Performance evaluation is left.
  4. English to Hindi Pre-process part is done in generic for all BERT-base, CNN Seq2Seq and RNN-With Attention Model.

Future Works:

  1. Training BERT-base is left.
  2. Web-App Frontend and Backend for Language Translation is currently being done parallelly in separate repo.