When: 23 Aug 2017 | 10:00 AM PST (10:30 PM IST)
Presenter: Yash Badiani – Practice Lead – CIGNEX
Abstract: We have been cataloging and indexing documents and texts since the dawn of the Roman Empire. In the information age, from large enterprises to bloggers leverage classification to segment their content effectively. The scale of data created by enterprises has today raised a challenge as enterprises invest on resources to ensure high accuracy.
At CIGNEX, we have created an end to end (document acquisition to classification) solution leveraging leading Open Source Technologies (including Machine Learning) tools to create a model which automatically classifies the documents into a growing number of categories. The solution is scalable to support millions of documents and distributes the classification for better performance. Join us for a webinar where we would share our approach, technologies, best practices, learnings & recommendations to build a scalable, accurate and high performance document classification system.
Duration: Webinar – 40 Minutes, Q&A – 20 minutes