/SentenceCorrection

Using the deep learning model correction the corrupted text or sms text into normalized english text

Primary LanguageJupyter Notebook

Sentence Correction Using RNN

In this we are correcting the corrupted english text like whr r u going? to proper english text where are u going? using deep learning models.
Dataset is taken from https://www.comp.nus.edu.sg/~nlp/corpora.html which was publically available.
Relevant paper for this problem statement: https://cs224d.stanford.edu/reports/Lewis.pdf
Blog for this problem statement: https://nipun-97agrawal.medium.com/sentence-correction-using-recurrent-neural-network-6321527ee08b
Programming Language used- Python
image
All the codes are written in Jupyter Notebook of Google Colab
image
Libraries used in this problem statement
image image
image image
For visulisation Libraries used are:
image image
TF
Here we have used multiple models like

  1. LSTM and GRU with one hot encoding of characters.
  2. LSTM and GRU with character tokenization
  3. LSTM with character tokenization and Bahandanau Attention
  4. LSTM with fasttext word embedding and Bahadanau Attention