https://github.com/saritaphd/next_word_prediction_using_lstm

This project aims to develop a deep learning model for predicting the next word in a given sequence of words. The model is built using Long Short-Term Memory (LSTM) networks, which are well-suited for sequence prediction tasks
https://github.com/saritaphd/next_word_prediction_using_lstm

Last synced: 3 days ago
JSON representation

This project aims to develop a deep learning model for predicting the next word in a given sequence of words. The model is built using Long Short-Term Memory (LSTM) networks, which are well-suited for sequence prediction tasks

• Host: GitHub
• URL: https://github.com/saritaphd/next_word_prediction_using_lstm
• Owner: SaritaPhD
• License: mit
• Created: 2024-08-01T07:56:14.000Z (4 months ago)
• Default Branch: main
• Last Pushed: 2024-11-09T03:08:45.000Z (10 days ago)
• Last Synced: 2024-11-09T04:18:00.535Z (10 days ago)
• Language: Jupyter Notebook
• Homepage:
• Size: 24.4 MB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
## Project Description: Next Word Prediction Using LSTM    

#### Project Overview:

This project aims to develop a deep learning model for predicting the next word in a given sequence of words. The model is built using Long Short-Term Memory (LSTM) networks, which are well-suited for sequence prediction tasks. The project includes the following steps:

1- Data Collection: We use the text of Shakespeare's "Hamlet" as our dataset. This rich, complex text provides a good challenge for our model.

2- Data Preprocessing: The text data is tokenized, converted into sequences, and padded to ensure uniform input lengths. The sequences are then split into training and testing sets.

3- Model Building: An LSTM model is constructed with an embedding layer, two LSTM layers, and a dense output layer with a softmax activation function to predict the probability of the next word.

4- Model Training: The model is trained using the prepared sequences, with early stopping implemented to prevent overfitting. Early stopping monitors the validation loss and stops training when the loss stops improving.

5- Model Evaluation: The model is evaluated using a set of example sentences to test its ability to predict the next word accurately.

6- Deployment: A Streamlit web application is developed to allow users to input a sequence of words and get the predicted next word in real-time.

![alt text]()