NLP Community Day 2016 (Austin)

This event was originally scheduled for Fall 2015, but we were unable to secure a large enough venue for the scheduled date, and our goto venue (the AT&T Conference Center) was already booked, so we had to postpone the event. If you purchased tickets previously, you have received an email with your free ticket code.

Why NLP Community Day Austin?

There are easily 400 people in Austin with an interest in Natural Language Processing and related topics: Computational Linguistics, Text Mining/Analysis, Sentiment Analysis, etc. Most of these folks haven't yet met each other. We thought it would be good to invite everyone for an afternoon of short and micro talks, where people could take turns on the stage sharing their work. Our goal is for everyone to walk away at the end of the afternoon with new connections, new friends, and fresh ideas. We've invited all the original speakers, and are re-opening the submissions for those who weren't available the first time. If you'd like to present at NLP Community Day, send us a proposal at If your company would like to sponsor, send a note to

Who's speaking at NLP Community Day?

KEYNOTE: Michelle Casbon (San Francisco / San Antonio) @texasmichelle

Michelle Casbon is the Director of Data Science at Qordoba, where she is working on a platform that uses machine learning to create a better experience for users and make localization less painful for engineers. Previously, Michelle was a Senior Data Science Engineer at Idibon, where she contributed to the goal of bringing language technologies to all the world’s languages. Michelle's development experience spans more than a decade across various industries, including media, investment banking, healthcare, retail, and geospatial services. Michelle completed a Masters at the University of Cambridge, focusing on NLP, speech recognition, speech synthesis, and machine translation. She loves working with and contributing to open source projects. Michelle will also be speaking at the upcoming Data Day Seattle.
Check out our recent interview with Michelle

Michelle will be giving the keynote at 12:30 (see the full schedule)

Melanie Tosik (Austin) @meltomene

Melanie Tosik (linkedin) is an NLP research engineer at WayBlazer. Her team focuses on developing complex, real-world applications of natural language processing and machine learning. Melanie spends most of her time designing and implementing semantic microservices which accurately extract context, intent and relevant concepts from natural language queries. In addition, Melanie employs a variety of machine learning algorithms to enrich user queries with vast amounts of previously unstructured data. Before she came to Austin, Melanie studied computational linguistics at the University of Potsdam. Rowing and gardening are her favorite free time pursuits..

Melanie will be giving the following talk at 1:15: (see the full schedule)
Generating personalized travel recommendations from natural language queries
Travel planning can be very time-consuming. At WayBlazer, we are striving to provide travelers with a single platform to dynamically deliver personalized hotel recommendations. All that is left to the user is to describe their desired travel experience in natural language. For example, you could ask "Where are the best hotels in the Caribbean for my honeymoon in June", or "I want a pet-friendly hotel in Ireland with access to a great golf course". In order to generate recommendations that are most relevant to the user query, WayBlazer leverages a number of internal and external NLP services. Specifically, we are developing semantic microservices which are designed to address the main aspects of any trip: who, what, when and where. As opposed to a traditional tf-idf search (a statistical measure to evaluate how important a word is to a document in a given corpus), our discovery tool is powered by a graph database similar to ConceptNet 5. This talk will give the audience an overview of WayBlazer's basic NLP stack, as well as a deep dive into our NL search technology.

Jonathan Mugan (Austin) @jmugan

Jonathan Mugan is Co-Founder and CEO at Deep Grammar. Dr. Mugan specializes in artificial intelligence and machine learning. His current research focuses in the area of deep learning, where he seeks to allow computers to acquire abstract representations that enable them to capture subtleties of meaning. Dr. Mugan received his Ph.D. in Computer Science from the University of Texas at Austin. His thesis was centered in developmental robotics, which is an area of research that seeks to understand how robots can learn about the world in the same way that human children do. Dr. Mugan also held a post-doctoral position at Carnegie Mellon University, where he worked at the intersection of machine learning and human-computer interaction. He is also the author of The Curiosity Cycle: Preparing Your Child for the Ongoing Technological Explosion.

Jonathan will be giving the following talk at 2:00: (see the full schedule)
Deep Learning for Natural Language Processing
Deep Learning represents a significant advance in artificial intelligence because it enables computers to represent concepts using vectors instead of symbols. Representing concepts using vectors is particularly useful in natural language processing, and this talk will elucidate those benefits and provide an understandable introduction to the technologies that make up deep learning. The talk will outline ways to get started in deep learning, and it will conclude with a discussion of the gaps that remain between our current technologies and true computer understanding.

Brent Schneeman (Austin) @schnee

Brent Schneeman joined HomeAway in 2010 and focuses on strengthening the data science muscle in the Technology Office. As Director of Data Science, he serves as an internal consultant on a diverse set of analytic projects such as multi-variate testing, customer website behavior and applying natural language processing techniques to unstructured data. A storyteller, Brent has presented at South By Southwest and has given many technological talks. Prior to joining HomeAway, Brent worked at PayPal and Visa. He has one degree in Mathematics and another in Electrical Engineering and lives in Austin Texas with his wife and three kids and spends most of his free time mowing the lawn.

Brent will be giving the following talk at 2:45: (see the full schedule)
HomeAway, the Competition, and NLP
HomeAway attracts millions of vacationers to its millions of listings every year. The company has also attracted worthy competition and uses various means to keep track of those competitors. Examining unstructured data such as text reveals good signal that can is used to estimate relative inventory overlap in the industry. We'll look at comparing property descriptions via TF-IDF vectors and topic models, and discuss various distance metrics used to detect similarities.

Dan Tecuci (Austin) @dantecuci

Dan Tecuci graduated from UT Austin with a PhD in Artificial Intelligence. During that time he contributed to the development of several large scale AI projects: Project Halo - knowledge acquisition and question answering in scientific domains (funded by Paul Allen), RKF, and Calo (precursor of Siri). He then moved to Siemens Corporate Research where he led the development and deployment of a natural language QA system for Siemens Energy Service. Also at Siemens, he developed a prototype system for accurately diagnosing heart diseases from patient data. Dan joined IBM Watson in 2014, where he led the development of Question Answering from tables and then moved onto fixing recipes for IBM ChefWatson. His main areas of expertise are knowledge representation and reasoning, question answering, NLP, and complex knowledge indexing and retrieval. He now works for Watson Health where he is applying learning and reasoning techniques to problems in the Life Sciences domains.

Dan will be giving the following talk at 3:30:
Teaching ChefWatson not to 'skewer the tequila'

(see the full schedule)

Dave Schneider (Austin)

Dave Schneider, NLP lead at Cycorp, Inc., has been working at the conjunction of language and logic for many years, concentrating on the translation from natural language to precise logical representations, but also branching out into related areas such as generation of NL from logical representations and interfaces between humans and logical systems.

Dave will be giving the following talk at 4:15:
Cyc ( is a very large Knowledge Base and Inference Engine, continuously under development in Austin for three decades. The content of Cyc is available for research use under a cost-free licence; inference and content are available via open source APIs. Additionally, the Cyc term set and taxonomy is available at no cost. Dave will describe Cyc generally, and then talk about Cyc's Semantic Construction grammar, a means of mapping from NL text into the inferentially productive logical representations used by Cyc. In part, this may allow talk attendees to think about how they might use Cyc content in their own NLP tasks. Finally, Dave will show some examples of how Natural Language Generation is done within Cyc applications.

The NLP Community Day Schedule

12:30 - Michelle Casbon (Qordoba) - Keynote
1:15 - Melanie Tosik (WayBlazer) - Generating personalized travel recommendations from natural language queries (Slides)
2:00 - Jonathan Mugan (Deep Grammar) - Deep Learning for Natural Language Processing (Slides)
2:45 - Brent Schneeman (HomeAway) - HomeAway, the Competition, and NLP (Slides)
3:30 - Dan Tecuci (IBM) - Teaching Watson not to 'skewer the tequila'
4:15 - Dave Schneider (Cycorp) - Cyc
5:00 - happy hour / meet and greet at Caffe Medici

We'll finish off the afternoon with a happy hour/meet and greet across the street at the Caffe Medici.

Special thanks to the authors of the upcoming Haskell Programming book for their financial support. Follow them at @haskellbook.