Skip to content

Latest commit

 

History

History
34 lines (23 loc) · 2.29 KB

README.md

File metadata and controls

34 lines (23 loc) · 2.29 KB
Raw

Business Glossary using NLP

Members:

  • Paras Gandhi (Team Leader)
  • Het Brahmbhatt
  • Chinmay Sanjay Kamerkar
  • Poorna Srinivas Gutta

Detailed Explanation

Create domain specific business glossary using NLP

Introduction to the topic:

Vertical taxonomies such as an e-commerce taxonomy for retailers, telecom taxonomy for Telecom. Businesses will be able to bring their domain specific private documents and the NLP based AI system will create a well formed taxonomies ingestible into a common catalog.The project will eventually help a particular enterprise in accurate decision making with the comprehensive view of all the business terms . With the data being organised in one place, this project helps the enterprise to save a lot of time by automatically cataloging the data.

Abstract:

What is the cost of developing glossaries for a given set of business documents? How reusable is a business glossary for the processes carried out on average in a Company? Impact of developing a glossary/taxonomy for a company/business? Correlation between assimilating new employees and strength of data catalogs.

Approach:

The project will have business enterprises as their users. Once they upload a document, the document will be scanned using python’s famous libraries like document-scanner or py-tesseract tool . After that , once the data is retrieved from the document, Natural Language Processing will be rendered on it and it will extract all the business-related terms . The end-product will be deployed on the dashboard.

Persona

Majorly there will be two types of personas. One will be the end user who will use the system to acquire information from the business glossary. This user will use the glossary to understand business processes from upper management or lower management. This user can also use this tool for on-boarding process to learn about company functions The second type of user will use the tool but also submit the corpuses(documents) through which the tool will develop taxonomies. This user has the ability to update the corpuses and thus update the glossaries.

RESULTS

We developed an end-to-end application using Python, Flask and ReactJS for client side. The project repository can be found here

ARCHITECTURE