Almost 80% of the world’s data is unstructured. Unstructured data can be found in emails, speech transcripts, briefings, social media posts, news reports, and many other places. Much of this unstructured data has a location tied to it (text origin or locations described within). How can you integrate this data into spatial analysis workflows such as, analyzing police reports to understand a changing crime landscape or, mining news articles to understand disease spread?
ArcGIS has new Natural Language Processing (NLP) capabilities that can help you extract insights from unstructured text.
Join this webinar to gain a spatial understanding of where places, events, or people may relate to a given phenomenon using text.
Topics discussed:
• Introduction to artificial intelligence (AI), machine learning (ML), and deep learning (DL) [3:05]
• Introduction to NLP [5:15]
• Challenges with NLP [9:18]
• How to integrate unstructured data into ArcGIS [14:05]
• Using ArcGIS LocateXT to extract locations from unstructured data [15:53]
• EntityRecognition with ArcGIS API for Python [20:31]
• Steps to train an EntityRecognition [24:09]
• Demo: Labeling data with Doccano [26:24]
• Demo: Training with EntityRecognition [29:33]
• Demo: Inferencing [33:23]
• Integration with 3rd party NLP frameworks [41:55]
• Overview of ArcGIS Notebooks [44:05]
• Processing unstructured data using ArcGIS and Microsoft Azure [46:20]
• Resource [55:37]
For more information on ArcGIS spatial analysis and data science tools, please visit https://bit.ly/2xt5z4Y
---------------------------------------------------------------------------------------------------
Follow us on Social Media!
Twitter: https://twitter.com/Esri
Facebook: https://facebook.com/EsriGIS
LinkedIn: https://www.linkedin.com/company/esri
Instagram: https://www.instagram.com/esrigram
The Science of Where: http://www.esri.com
- Tags
-