Skip to content

This Case study is about creating an application which given a input sequence can predict output sequences

License

Notifications You must be signed in to change notification settings

Anuj-Codes/Gmail_Smart_Compose_Case_Study

Repository files navigation

Gmail_smart_compose_image

Gmail_Smart_Compose_Case_Study

Introduction

If you are a Gmail user, by now you would have experienced the smart compose feature (maybe even without knowing you are actually using it). It's the new automatic sentence completion feature that takes email productivity to an exciting new level. It was released in Google I/O 2018. Smart compose is smarter than you think, we engage in a lot of text-based communication on a daily basis. Most of the web and mobile apps today come with great features to improve productivity For instance, Whatsapp offers a predictive text, and Google search auto completes our queries with trending searches as you type in.

Business problem

Here we have to make a model, which can predict the sentences or words based on the given sentence or some words. So here the input is a sequence of words and the output is also a sequence of words, so we have to build the sequence-based model.

Bidirectional GRU Model Architecture

image

Deployed Gmail Smart compose Application demo

Smart_gamil_compose_demo

My detailed approach can be viewed in this medium article.

https://medium.com/@anujmlcode/gmail-smart-compose-using-neural-networks-to-help-write-emails-4a7a176ce5af

About

This Case study is about creating an application which given a input sequence can predict output sequences

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published