Sentence Auto Completion using DL

[ashis2004]

trafficstars

Deep Learning Simplified Repository (Proposing new issue)

:red_circle: Project Title : Sentence Auto completion using LSTM :red_circle: Aim :LSTM-based sentence auto-completion is in text editors and word processing software, where it enhances user productivity by suggesting the next word or phrase, thereby reducing typing effort. It can also be integrated into email clients to offer smart replies or in code editors to assist with code completion. :red_circle: Dataset :https://www.kaggle.com/datasets/noorsaeed/holmes :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.

1. Prepare dataset and preprocess the text data.
2. Define and compile the model using the provided script.
3. Train the model on dataset.
4. Use the trained model to predict the next word in a given sentence.

---

📍 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 : Ashish Kumar Patel
• GitHub Profile Link : https://github.com/ashis2004
• Email ID :[email protected]
• Participant ID (if applicable):
• Approach for this Project :

1. Prepare dataset and preprocess the text data.
2. Define and compile the model using the provided script.
3. Train the model on dataset.
4. Use the trained model to predict the next word in a given sentence.

• What is your participant role? Gssoc contributor

---

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]

LSTM is the most used model for this kind of problem statement, apart from it, what are the models you can apply for this problem statement. Need to share at least 3-4 architectures along with LSTM.

[ashis2004]

I can try GRU, Transformer and BERT pls assign it me @abhisheks008

[abhisheks008]

Assigned @ashis2004. Make sure you implement all the mentioned the models from your side.

[shivansh-2003]

Full name: Shivansh Mahajan GitHub Profile Link:https://github.com/shivansh-2003 Email ID: [email protected] Participant ID (if applicable): NA Approach for this Project: LSTM Participation role : SWOC

[abhisheks008]

Apart from LSTM what are the other models you can implement here? As in this project repository for each problem statement we mainly focus on implementing 3-4 models. @shivansh-2003

[shivansh-2003]

Pretrained Transformers form hugging face and GRU

[abhisheks008]

Cool, go ahead with the proposed three models/methods.

Assigned this issue to you @shivansh-2003