addressalign-toparrow-leftarrow-rightbackbellblockcalendarcameraccwcheckchevron-downchevron-leftchevron-rightchevron-small-downchevron-small-leftchevron-small-rightchevron-small-upchevron-upcircle-with-checkcircle-with-crosscircle-with-pluscontroller-playcrossdots-three-verticaleditemptyheartexporteye-with-lineeyefacebookfolderfullheartglobegmailgooglegroupshelp-with-circleimageimagesinstagramFill 1light-bulblinklocation-pinm-swarmSearchmailmessagesminusmoremuplabelShape 3 + Rectangle 1ShapeoutlookpersonJoin Group on CardStartprice-ribbonprintShapeShapeShapeShapeImported LayersImported LayersImported Layersshieldstartickettrashtriangle-downtriangle-uptwitteruserwarningyahoo

Natural Language Processing Basics with NLTK Workshop

A vast amount of the world’s data (and your own) is text and the key to unlocking its value is in a series of standard natural language processing steps that we must make on raw text to ensure that it is understandable to machines. This workshop will teach you how to transform strings to machine usable data and discuss how to apply each step to your application. We’ll be using Python’s NLTK - a professional grade Natural Language Toolkit that is free and open source.

The price per attendee is $150.  

What To Bring:

- Your laptop

- Printed copy of your ticket

 

Prior to the Event:

Please take our survey so that we can get a feel for the make up of the class. Although, I'd ask only folks who are registered to take the survey-- this will allow us to customize the class to the group.

NLP Workshop Questionnaire

 

Abstract:

Many of the largest and most difficult to process data sets that we encounter tend not to be from well structured logs or databases, but rather unstructured bodies of text. In recent years, Natural Language Processing techniques have accelerated our ability to stochastically mine data from unstructured text but require large training data sets themselves to produce meaningful results.

The most popular open source tool for NLP is NLTK and it embraces these techniques, while providing a powerful interface in Python for us to quickly add NLP to our applications.

 

Outline:

  1. Organizing large bodies of text (corpora)

  2. Task: tokenization and segmentation;Motivation: cross-document language statistics

  3. Task: tagging and stemming; Motivation: information extraction

  4. Task: parsing for treebanks; Motivation: discovering crucial concepts

 

We will provide a virtual machine (vmware) containing an NLP development environment with all required software preinstalled and preconfigured for this workshop.


If you have text that you would like to process, please bring your data along. If not, we will be using corpora from Project Gutenberg.


Instructor

Benjamin Bengfort, Data Science Consultant, Full Stack Data Science

Benjamin Bengfort is a Data Science consultant at Full Stack Data Science, and has used Machine Learning and Natural Language Processing techniques to determine textual complexity in large literary corpora. He is a PhD candidate in Computer Science, with a focus on NLP, at the University of Maryland, Baltimore County, and has a MS in Computer Science from North Dakota State University.

Join or login to comment.

  • Tommy J.

    I think the class plan was very ambitious. In the time allotted, we probably only could've gotten through half the material in the time. No worries. I'll just follow up myself at home!

    July 31, 2013

  • Peter

    The workshop gave a high-level overview of both NLP theory and how to implement basic NLP analysis with NLTK. Overall the theoretical discussion was stronger than the technical tutorial.

    July 29, 2013

  • Mike R.

    I thought today's workshop was a little disorganized, but I did get a clearer picture on how to proceed with language processing, specifically near the end with grammar training. Wish you would have created a project(code) from start to finish that illustrated the concepts you were trying to illustrate instead of fragmenting everything.

    July 28, 2013

  • A former member
    A former member

    This was a good intro to terminology and techniques. However, it was almost 3 hours into the workshop, when we finally wrote the first lines of Python code.. It would have been better if concise, without the philosophical questions being thrown to the presenters..The very first code example had issues ...

    July 27, 2013

  • Jacqueline J.

    I'm happy. The material was presented well with plenty of Python nltk examples to illustrate the NLP concepts. Frankly, it would take me a long time (even with the internet and a few tomes) to get such a good start. It was a great use of a few hours. The code typos were very minor, and I got past those. I can see what to do with the rest, because the presentation is online.

    1 · July 27, 2013

  • Joshua T.

    I was mostly happy with this meetup; it got me going with terminology and techniques I can pursue. My only beef was in having difficulty hearing the presents over the myriad separate conversations going on around me.

    1 · July 27, 2013

  • Charles W.

    While I concede there were problems, the presenters intentions were sterling, DC *really* needs folks willing to be pioneers teaching this stuff, and it still could be a tremendously useful hands-on practical introduction to NLP w/python. It could have been better, but I got my money's worth. I learned a lot from fixing typos, though I know that is a backhanded compliment. I hope to hear it's taught again. And generates reviews it has the potential to garner. Again, DC needs people who are willing to take risks sharing NLP/comp ling expertise. Yes, it could have been better, let's still give it a chance to be that. #JustMyPersonalOpinion

    1 · July 27, 2013

  • A former member
    A former member

    This was a waste of time and money - $150. The code samples did not work and the trainer was theoretical. No hands on coding.

    July 27, 2013

  • Steven W.

    Inadequately prepared -- the hands-on portion was inadequately scripted and the code samples had typos with the result that chaos broke out. The slides were poorly developed--these consisted of bullet points without many particulars or sufficient use of graphics to illustrate the points and the presentation frequently lost focus.

    July 27, 2013

  • A former member
    A former member

    Awesome workshop, thanks guys!

    July 27, 2013

  • Sumeet V.

    The real value was in the labs and using the nltk which didn't have adequate time devoted to it. For $150, very little value for money

    July 27, 2013

  • Jacqueline J.

    I'm at the front

    July 27, 2013

  • Charles W.

    At front door building, how to get in?

    July 27, 2013

  • Charles W.

    Pizza? Learning? Interfere? :)

    July 27, 2013

  • A former member
    A former member

    Is there a lunch-break .. I know time is tight, so what is planned/recommended?

    July 26, 2013

    • Tony O.

      I'm having pizzas delivered. Would like to keep lunch to a half hour so that it doesn't interfere too much with learning.

      July 27, 2013

  • A former member
    A former member

    Can you also make a list of tools/environment setups so that we can use it for future projects, instead of replying on VMs? Thanks

    June 7, 2013

    • A former member
      A former member

      I use a multi-boot Ubuntu laptop. If you provide a VMware player image, then my personal setup would be Windows + VMWare.

      June 14, 2013

    • A former member
      A former member

      Mint is an ubuntu flavor ... its derived from Ubuntu. I use mint.

      July 26, 2013

  • Joshua T.

    Minor issue; I have the email receipt having bought registration for this, but no link to go to to print out a ticket. Help?

    July 26, 2013

    • Tony O.

      When you go to the meetup event page, under the title, there should be an option that says Print Ticket. If you can't find it, don't worry. I'll have a list of names registered tomorrow and you can just give me your name.

      July 26, 2013

  • Tony O.

    Look forward to seeing all of you on Saturday! For those that are driving to the workshop, make sure to give yourselves some extra time to find parking in the area. We recommend using http://www.parkme.com to see what's available and at what rates. They have mobile apps as well. For Apple: https://itunes.apple.com/us/app/parkme-parking-find-cheapest/id417605484?mt=8

    For Android: https://play.google.com/store/apps/details?id=com.parkme.consumer

    July 24, 2013

  • A former member
    A former member

    looking forward to learning natural language processing...

    June 26, 2013

  • A former member
    A former member

    Looking forward to this. Mostly a Ruby dev but will brush up on python. Would he interested in hearing how cloud computer platforms can be leveraged to speed up analysis

    June 25, 2013

  • Benjamin B.

    I just posted a quick questionnaire to get a feel for who's bringing what to the class and what's needed for things like creating virtual machines. It should only take five minutes of your time. If you're attending, you can fill it in here: https://docs.google.com/forms/d/1nF5wYXZyvRee7Q2lRwQK35M_50rW_tgxzpaBBQ5-YCI/viewform

    June 14, 2013

    • A former member
      A former member

      How can I book 2 seats to this workshop.

      June 24, 2013

    • Tony O.

      Hi Vijay. Each person should RSVP individually through their own Meetup account. This helps us keep track of who has paid and is coming to the event. You can pay with the same payment method for each seat when you get to the PayPal screen, but from the Meetup end of things each should have their own account.

      June 24, 2013

  • Joshua T.

    I mean to attend, but will have to wait 'til mid next week to pay the fee; hopefully it won't have booked up by then

    June 20, 2013

  • Andrew M.

    Are there any prerequisites?

    June 7, 2013

    • Benjamin B.

      NLTK is written in Python- so some knowledge of Python would be very good. The course work will also be in English -- so a good knowledge of the syntax of English would be helpful (basic grammatical rules).

      June 7, 2013

    • Andrew M.

      sounds good, thanks!

      June 7, 2013

32 went

Your organizer's refund policy for Natural Language Processing Basics with NLTK Workshop

Refunds offered if:

  • the Meetup is cancelled
  • you can cancel at least 7 day(s) before the Meetup

Payments you make go to the organizer, not to Meetup. You must make refund requests to the organizer.

Regardless of the refund policy set by the organizer, Meetup may issue refunds on an organizer's behalf if we determine that Meetup's Payment Policies have been violated.

Our Sponsors

People in this
Meetup are also in:

Sign up

Meetup members, Log in

By clicking "Sign up" or "Sign up using Facebook", you confirm that you accept our Terms of Service & Privacy Policy