Learn various ways to bootstrap a custom corpus for training highly accurate natural language processing models. Real world examples will be presented with Python code samples using NLTK. Each example will show you how, starting from scratch, you can rapidly produce a highly accurate custom corpus for training the kinds of natural language processing models you need.
by Richard Taylor
Do you want to write less code and get more done? This tutorial will demonstrate a natural language parsing technology to extract entities from all kinds of text using massively parallel clusters. Attendees will gain hands-on experience with the newly-released, data-centric cluster programming technology from HPCC Systems to extract entities from semi-structured and free-form text data. Students will leave with all the data and code used in the class along with the latest HPCC Client Tools installation, HPCC documentation, and HPCC’s VMware installation. Prizes, give-aways and a raffle is included.
This session is sponsored by HPCC
28th February to 1st March 2012