Building an Open Source Topic Modeling Library

Banjo Obayomi

Prior knowledge:
No previous knowledge expected

Summary

Topic Modeling, is a popular task for Natural Language Processing (NLP) workloads. Getting started however has a high barrier of entry, due to the complexity of setting up the NLP pipeline.

Join me as I discuss how I lead a community-driven effort during Hacktoberfest to build TopicBlob. TopicBlob is an NLP library that democratizes the ability to perform tasks around topic modeling.

Description

Topic Modeling, is a popular task for Natural Language Proccesing (NLP) workloads. Getting started however has a high barrier of entry, due to the complexity of setting up the NLP pipeline.

In this Talk I will introduce TopicBlob a community built library that provides a simple API for diving into common natural language processing (NLP) tasks around topic modeling such as finding similar documents and providing a list of topics given input text.

I will brake down how the topic modeling works, how to define issues to keep community members engaged, and ways to highlight the project.