[Project Addition]: Next Word Predictor using Deep Learning

[Karthik110505]

Deep Learning Simplified Repository (Proposing new issue)

:red_circle: Project Title : Next Word Predictor using Deep Learning
:red_circle: Aim : To find the generate word of the given sentence using deep Learning algorithms
:red_circle: Dataset : https://www.kaggle.com/datasets/thedevastator/wikipedia-biographies-text-generation-dataset
:red_circle: Approach : Try to use 3-4 algorithms to implement the models and compare all the algorithms to find out the best fitted algorithm for the model by checking the accuracy scores. Also do not forget to do a exploratory data analysis before creating any model.

---

📍 Follow the Guidelines to Contribute in the Project :

• You need to create a separate folder named as the Project Title.
• Inside that folder, there will be four main components.
  • Images - To store the required images.
  • Dataset - To store the dataset or, information/source about the dataset.
  • Model - To store the machine learning model you've created using the dataset.
  • requirements.txt - This file will contain the required packages/libraries to run the project in other machines.
• Inside the Model folder, the README.md file must be filled up properly, with proper visualizations and conclusions.

---

:red_circle::yellow_circle: Points to Note :

• The issues will be assigned on a first come first serve basis, 1 Issue == 1 PR.
• "Issue Title" and "PR Title should be the same. Include issue number along with it.
• Follow Contributing Guidelines & Code of Conduct before start Contributing.

---

:white_check_mark: To be Mentioned while taking the issue :

• Full name : Veera Venkata Karthik Barrenkala

• GitHub Profile Link : https://github.com/Karthik110505

• Email ID :bvvkarthik1155@gmail.com

• Approach for this Project :

  • Load the Dataset
  • Exploratory Data Analysis (EDA):
  • Visualize common words and text length distributions.
  • Model Implementation:
  • Artificial Neural Network (ANN)
  • Long Short-Term Memory (LSTM)
  • BiLSTM
  • Train and evaluate each model.
  • Compare performance using accuracy and loss metrics.

• What is your participant role? (Mention the Open Source program) GSSoC24

  ---

  Happy Contributing 🚀

All the best. Enjoy your open source journey ahead. 😎

[github-actions[bot]]

Thank you for creating this issue! We'll look into it as soon as possible. Your contributions are highly appreciated! 😊

[abhisheks008]

You can start working on it. Assigned @Karthik110505

[Sakeebhasan123456]

hii @abhisheks008 ,i would like to work on this project

Approach

• Source: Kaggle - The Complete Works of Sherlock Holmes
• Description: A collection of texts providing rich language data for training.

Data Preprocessing

• Lowercasing: Converted all text to lowercase.
• Punctuation Removal: Removed all punctuation marks.
• Tokenization: Split text into individual words.
• Stop Words Removal: Removed common English stop words.
• Sequence Creation: Created sequences of 5 words each to use as input data.

Models Implemented

1. Basic LSTM Model
   • Single LSTM layer.
2. Stacked LSTM Model
   • Two LSTM layers stacked.
3. Bidirectional LSTM Model
   • LSTM layer that processes input in both directions.
4. LSTM with Dropout
   • LSTM layer with dropout regularization to prevent overfitting.

Fine-tunning

Using Optuna technique to find out best optimal result

Training

• Optimizer: Adam
• Loss Function: Categorical Crossentropy
• Metrics: Accuracy
• Epochs:
• Batch Size:
• Validation Split:

Results

• Accuracy: (Include accuracy results for each model)
• Loss: (Include loss results for each model)
• Plots: Accuracy and loss plots are saved in the Images/ folder.

[Sakeebhasan123456]

@abhisheks008 Actually I want to do this for the Gsocs Extended program please give me a chance to show my skill

[abhisheks008]

Assigning this issue to you @Sakeebhasan123456