Rescheduled! PDX Speech and Language Processing Happy Hour is an informal gathering of individuals working in computational linguistics, speech, and natural language processing in the Portland metro area. No talks, just socializing, but shop talk encouraged. Some folks will be around 7-10, so drop in as your schedule permits. At Orenco Taphouse.

PDX Speech and Language Processing Happy Hour is an informal gathering of individuals working in computational linguistics, speech, and natural language processing in the Portland metro area. No talks, just socializing, but shop talk encouraged. Some folks will be around 7-10, so drop in as your schedule permits. At the Lucky Labrador Beer Hall.

PDX Speech and Language Processing Happy Hour is an informal gathering of individuals working in computational linguistics, speech, and natural language processing in the Portland metro area. No talks, just socializing, but shop talk encouraged. Some folks will be around 7-10, so drop in as your schedule permits. See you at EastBurn!

This group is meant as a round table for anyone interested in conversational/intelligent agents (chatbots) whether voice or text driven. Feel free to bring your questions no matter how basic, technical, academic or business or design related.

We'll get together and talk about the group, what we want from it and what we are working on and interested in doing.

I'll give an overview of basic voice agent (Alex / Google home) development as I see and understand it designed to get us sharing information.

Let me know if you are interested in presenting something or leading a discussion.

Afterwards some of us will go to a local bar/restaurant to continue the conversation.

Join us June 13 for the first meetup in our new format, featuring Zach Babb, Principal Technologist from Daimler's moovel divison sharing a view into their Conversational Experiments. Following Babb will be a tour of Cognigy's Conversational UI platform.

Doors will open at 5:30pm for beer by Baerlic Brewing, soda, pizza and conversation

6:30pm – 7:00pm Zach Babb, Principal Technologist at Daimler moovel will share a view into their lab efforts specific to conversational interfaces such as Alexa and Facebook Messenger, why they shelved them and why now might be the perfect time to pick them up again. Checkout the latest news about the Daimler/BMW mobility merger which includes moovel, Reach Now and many more https://www.nytimes.com/2018/03/28/business/daimler-bmw-car-sharing.html

7:00pm – 7:30pm Demonstration of Cognigy’s Conversational AI platform http://www.cognigy.com which allows for rapid development and deployment of experiences across Slack, Alexa, Facebook Messenger and more

7:30pm – 8:00pm Discuss topics and interesting presenters for future meetings

We'll get together to discuss questions you may have about deep learning. So don't be shy. Let us know what you are working on, what you've learned and what you'd like help with.

I also propose we read and discuss "A Survey of the Usages of Deep Learning in Natural Language Processing" https://arxiv.org/abs/1807.10854 Note: There is no single person presenting this paper we'll all read it and discuss what we learned and what we didn't understand.

Start your new year off right with other deep learning enthusiasts. Bring your questions and insights related to DL.

We'll also discuss PyText the new NLP framework from Facebook built on PyTorch. This will be a discussion topic not a formal presentation so review the package if you can.

https://github.com/facebookresearch/PyText

Join us for a demo of analyzing and plotting Twitter sentiment using Python and Natural Language Processing. I'll demo how to use techniques such as tokenizing, lemmatizing, corpora, wordnet, and building a machine learning classifiers such as Logistic Regression, SVC, and SGDC.

I wonder what the Twitter sentiment will be on our president on demo day?

If you would like to join the discussion check us out on Zoom https://zoom.us/j/7891236789.

Do you want to learn and share your passion in a supportive community? Knowledge Mavens is an ethos of sharing, creativity, and inspiration.

Our Meetup provides an opportunity to "Show and Tell" followed by feedback and Q&A. You'll have the opportunity to share with our channels such as Meetup, GitHub, YouTube, and Facebook to connect with more passionate people.

The second half of our session we'll collaborate on new topics. The winner wins an award for the most interesting topic and the opportunity to share in an upcoming session.

Un-Redacting the Mueller Report and Abstracting the News with NLP By Hobson Lane and Al Kari

Hobson will show you how to write a python "mad-libber" that can unredact the Mueller Report. The first person to correctly predict the next word better than the mad-libber will win an autographed copy of Natural Language Processing in Action, a book produced through open collaboration among Portland Python User Group Members, led by Cole Howard and Hannes Hapke. Then Hobson and Al Kari will show you how they use this same state-of-the-art language model to generate meaningful abstractive summaries of technical documents like clinical medical records.

About our speakers: Hobson Lane's first Python apps were built with the help of friends at the Portland Python User Group almost a decade ago. Since then he's been using Python for everything from chatbots to building energy consumption forecasting. He's now CTO at Deep Canopy where they build smart cameras for industry. In his spare time Hobson teaches Python and data science on Springboard.com, Thinkful.com, and Totalgood.com and preaches crackpot ideas for harnessing the pending AI explosion for the greater good.

Al Kari is a Google Developer Expert (GDE) in Machine Learning, organizer of the TensorFlow-Northwest meetup group and CEO of Manceps, an engineering company focused on providing intelligent automation solutions to innovative businesses.

Join us afterward at Bailey's Upper Lip Upstairs Taproom 213 SW Broadway to continue the discussion over a beverage.

Do you have something you'd like to share?

PDX Python on Twitter (http://twitter.com/pdxpython)

Portland Python Web Site (http://pdxpython.io/)

Presented by Joachim Rahmfeld, Ph.D Lecturer at UC Berkeley

Today’s vast volumes of language-based, unstructured, electronic data found in various form factors such as blogs, email, social media, or web sites, promises competitive advantages for those who can extract business-relevant information most effectively and efficiently. Natural Language Processing (NLP) holds the key in leveraging this type of data in order to answer and respond to important questions such as, “What is the perception of my company in the Twittersphere?”, “Are these reviews largely positive or negative?”, “What is the translation of this in Spanish?”, “This document has the answer to my question somewhere… but where?”, “Are these products similar?”

Particularly over the last five years, revolutionary advances in NLP-related Deep Learning algorithms combined with dramatically increased compute resources have created unprecedented opportunities to not only answer natural language questions with greater accuracy and speed, but often also while requiring significantly less training data.

In this session, we will provide an overview of these advances and how you can make use of them. A particular focus will be transfer learning where large, pretrained models, such as Google’s BERT model, can be leveraged for a broad set of NLP use cases delivering excellent results, and enabling you to answer questions that were not possible to answer just a few years ago.

So this is a great time to learn about recent NLP developments and go through explicit examples.

About the Speaker

Joachim started his career in theoretical physics before leaving academia and joining the IT industry. For over a decade, he held various leadership positions in professional services, business development and sales at Sun Microsystems, VMware, and Hitachi Data Systems. In 2015, Joachim returned to his quantitative roots and obtained a Master of Information and Data Science from UC Berkeley. Most recently, Joachim managed a Data Science research team at Edison Software. He currently lectures at UC Berkeley on Natural Language Processing with Deep learning and is working on various NLP projects.

When

Sept 19th, 2019 (Chapter meetings held on third Thursday of the month)

Schedule

8:30 – 9:00 am – Sign In 9:00 – 10:15 am – Presentation 10:15 – 10:30 am – Break, Chapter Announcements 10:30 – 11:30 am – Presentation continued

Standard Insurance Tower Atrium (900 SW 5th, please note Standard Ins. has multiple downtown locations)

Cost

Free for members (including ALL employees of corporate members) $15 for non-members $5 for students with valid student ID

Standard Insurance Center, 900 SW 5th Ave, Portland, OR 97204, USA