Shubhanshu Mishra will share their insight on information extraction (IE) which enables the usage of existing database techniques for extracting further knowledge from a text corpora.
This tutorial will focus on the usage of python-based, open source tools and practices from reproducible research on sharing of data and code. Shubhanshu will also introduce participants to various semantic and syntactic information extraction tasks commonly used for Twitter data. Additionally, participants will be familiarized with the landscape of publicly available training data for tweets and methods for collecting them. Lastly, participants will be trained to use a suite of open source tools (SAIL, TwitterNER, and SocialMediaIE) which utilize advanced machine learning techniques (e.g. deep learning, active learning with human-in-the-loop, and multi-task learning) to perform information extraction on their own data-sets. The tools introduced in the tutorial will focus on the three stages of information extraction, namely, collection of data (including annotation), information extraction from data, and visualization of the extracted information.
Registration for this event is required. Please RSVP here.
Please utilize the following link to visit the workshop tutorial page before the workshop: https://socialmediaie.github.io/tutorials/.
Please bring a laptop with Python installed and note that some previous experience is Python is neccessary for the workshop. Additionally, some familiarity with Twitter and FaceBook is preferred.
If you have questions and/or need accommodations for this event, please email Cathy McArthur at firstname.lastname@example.org.