Primer on Natural Language Processing (NLP)

What's the connection between language and data?

In this Meetup recent graduate Lanhao Chen will cover some of the foundational tasks involved with language processing and data science.

At it's core this Meetup, will provide you with an overview of the major tasks and methods as they relate to natural language processing.

These include a high-level overview of how to extract information and classify text in the Python programming language using the NLTK (natural language tool kit) library.

The lecture will also provide core examples for processing and classifying unstructured natural language text.

By the end of the lecture you should expect to have an understanding of how language tagging and classification models works along with a set of take-home hands-on examples.

=== SPEAKER ===
Lanhao Chen is a Graduate of George Washington University Master's in Business Analytics. He recently completed an internship as a data scientist at Harvard University's Institute for Quantitative Social Science. His specialties include predictive analytics, business intelligence and machine learning.

http://photos1.meetupstatic.com/photos/event/3/8/8/a/600_447434474.jpeg

=== TENTATIVE COVERAGE====

1. Natural Language Pipeline
   a) Major Tasks
   b) Pipeline Steps
2. Information Extraction
   a) Part-of-Speech Tagging
   b) Chunking
   c) Named Entity Recognition
   d) Relation Extraction
3. Text classification
   a) Generative / Discriminative Models (time-permitting)
   b) Feature extraction (typical features)

==== WHAT YOU'LL NEED ====
Just yourself!

=== AGENDA ===:

6:30 - 7:00 Mix and Mingle (Meet new people! )
7:00 - 7:05 Intros and announcements
7:05 - 8:10ish Presentation/Q&A
Then socializing!!!