Text summarisation made fun!

Harshdeep Harshdeep (~harshdeep)




The goal of this talk is to explain this quote : “You shall know a ‘word’ by the company it keeps!”

In this talk, we will go through as to how to build a model for text summarisation (from scratch) and its possible applications in the real world scenario.

An intuitive explanation will be provided (the talk would not be all mathematical!) as to how to do the data preprocessing for a large dataset and provide a reasoning as to why we choose a specific model for training. We will also talk about how certain Python libraries make it easier to structure a machine learning pipeline.

We will also walk through the best practices and various caveats while building these kinds of complex models and how to circumvent these.


The prospective audience should have a basic understanding of neural networks and natural language processing.

Speaker Info:

Harshdeep is currently a student at the University of Manchester pursuing his Bachelors in Artificial Intelligence and is interested in Natural Language Processing.

My experience with Python started at IBM Bristol where I worked for a year developing the compliance automation tool. After that, I worked on my final year research project using Python which was based on finding summaries and sentiment of news articles.

I have previously spoken at PyCon APAC in Malaysia last year in August which was a talk about the basics of Neural Networks.

After university, I will be working with some early stage startups in India related to AI and Aviation.

Id: 758
Section: Data science
Type: Talks
Target Audience: Intermediate
Last Updated: