Agenda

Over two days, attendees will be treated to hands-on workshops, inspiring keynotes, peer-to-peer discussions and 15+ action-packed talks.
Don’t forget to stay hydrated during the welcome reception and networking breaks!

DAY 1, Tuesday, June 21, 2016
(All track sessions will take place in Mobley)

8:00-8:45AM

REGISTRATION & COFFEE

Join us for breakfast in the Exhibit Hall and start the day off right

8:50-9:10AM

WELCOME REMARKS

Steven Ramirez
CEO
Beyond the Arc

Welcome Remarks

9:10-10:00AM

KEYNOTE

Steven Ramirez
CEO
Beyond the Arc


Innovative Trends in Capturing Business Value from Text and Speech Analytics

Fueled by recent innovations in big data and deep learning, text analytics capabilities have made tremendous advances. Not only can our devices understand what we’re saying, they can classify and assess our human emotions and make recommendations based on how we feel.

In this keynote session, TAW Program Chair Steven Ramirez will discuss how text and speech analytics are currently being deployed in a diverse range of fields, including financial services and retail. The discussion will highlight how innovators like Amazon, Apple, and Google are powering new digital experiences for Tesla, USAA, and others.

10:00-10:30AM

NETWORKING BREAK

Mingle with fellow attendees on the exhibit floor.

10:30-11:05AM

TRACK SESSION

Michael Tamir
Intertrust – Chief Data Scientist
Skymind


Insights on Item-Text Parallels and New Techniques for Recommender Algorithms

Neural text embedding algorithms have transformed how Data Scientists now work with natural language data. One reason these algorithms are so successful is that they offer an efficient information preserving methodology to highly compress native features (word frequencies) to the dimensions of the embedded vector space. This is particularly effective in the sparse data context of word count frequencies. Recently word embedding algorithms have been generalized to generic graph networks contexts. In this talk we review results of applying this generalization to alternative sparse data contexts such as User-based as well as Item-based recommender algorithms.

11:05-11:40AM

TRACK SESSION

Chris Bowman
President
Educational Analytics and Logistics


Case Study: Educational Analytics and Logistics
Using Text Analytics and Data Mining to Survey Discipline Referrals

Kindergarten to twelfth grade public schools struggle with discipline problems on a daily basis. Some of this effort becomes unproductive since there is no way to go through the thousands of referrals that are generated in an average size school system. Using text analytics it becomes possible to take unstructured data and find patterns, trends, and tendencies that may cause problems. Blending structured and unstructured data was a key component in this analysis to glean information in order shape and influence discussions and policies concerning the welfare of students and administrators in schools today.



 

11:45-12:05PM

TRACK SESSION

Alice Chung
Sr. Manager
Genentech


 
Hsing-Chien Kao
Data Consultant
Incendo


Case Study: Genentech
Utilize Text and Predictive Analytics to Generate Insights

Room: Salon A2 (Co-located with PAW)

We designed a few experiments to explore the methods of utilizing text and predictive analytics models to provide insightful guidance for research purpose. We conducted network analysis to identify influential institutes and potential research population, automate the process of combining internally collected profile/survey data and external data sources from the internet and vendors, and then utilize text mining tools to extract correlation, attribute and sentiment information of words for answering key business questions. The results help improve the efficiency and effectiveness of generating insights, provide precise guideline for the accuracy and completeness of data organization, and propose strategic recommendations.

12:05-1:30PM

LUNCH

Join us for lunch and networking breaks in the Main Hall


 
 

1:30-2:15PM

TRACK SESSION

Michael Dessauer
Data Scientist
The Dow Chemical Company

 
Justin Kauhl
Computational Linguistics Expert
The Dow Chemical Company


Case Study: The Dow Chemical Company
Understanding our Customers’ Customers’ Customers’ Needs – Text Analytics for B-to-B Businesses

The Dow Chemical Company is positioned upstream in the value chain which poses a challenge in understanding end market needs. Dow’s Advanced Analytics team has developed collection, organization, analysis, and visualization methodologies that unlock insight from business-relevant internal and external text sources. Our text-driven quantitative insights have empowered businesses to strengthen value propositions and generate new opportunities. In this talk, we will provide examples of our successful approaches to consumer sentiment and market trend analysis through a combination of open source and vendor tools.

2:20-3:05PM

TRACK SESSION

Razieh Niazi
CEO
Kaypok Inc.


Exploring the Hidden Unknown Using Self-Learning Text Analytics

With an increasing volume of data flowing into enterprises, complexity in understanding customers is increasing. Currently, users identify the search, but are unable to uncover the plethora of relevant and useful information. Brand management relies on an application that requires maintenance in the form of tags, rules and upkeep of predefined dictionaries while searching for brand related products. By automating the discovery process and using self-learning text analytic technology, users are able to explore hidden values in their data in real-time. In our presentation, we view case studies that illustrate the discovery process using self-learning text analytic practices.

3:05-3:35PM

NETWORKING BREAK

Mingle with fellow attendees on the exhibit floor.


 
 

3:35-4:20PM

TRACK SESSION

Pengchu Zhang
Computer Scientist
Sandia National Laboratories

 
John Herzer
Enterprise Search Project Lead
Sandia National Laboratories


Case Study: Sandia National Laboratories
Enhancing search results relevance using Word2Vec Language Models

Learn how Sandia National Laboratories has applied neural network algorithms to enhance customer queries and improve the relevance of search results. In this case study, we will review our use of models such as Word2Vec to better understand and profile our unstructured content. We will discuss how our search application integrates these models with the Apache Solr search engine and describe how queries are improved with term expansion and phrase identification.

4:20-5:30PM

PANEL


FAQ Live: Top Tips and Best Practices in Text Analytics

Here’s your chance to learn from industry thought leaders, and share your own practical insights. In this moderated discussion, we’ll cover key success factors for deploying text analytics, what to look for in vendor offerings, the quantifiable business results companies are capturing from text analytics, and the impact text analytics can have on your career. This session will be guided by your questions. Feel free to raise additional issues of both your peers and experts.

5:30-7:00PM

NETWORKING RECEPTION

Mingle with fellow attendees on the exhibit floor.

DAY 2, Wednesday, June 22, 2016
(All track sessions will take place in Mobley)

8:00-8:45AM

REGISTRATION & COFFEE

Join us for breakfast in the Exhibit Hall and start the day off right

8:50-9:40AM

KEYNOTE

Boris Evelson
Vice President, Principal Analyst
Forrester


Keynote
Expand Your Big Data Capabilities With Unstructured Text Analytics

Without the insights buried in petabytes of unstructured data, your customer view will never be complete. But most of the axioms, best practices, and technologies used for structured data do not apply to data mining and analysis of unstructured data. In his keynote presentation, Boris Evelson, VP and Principal Analyst at Forrester Research, helps demystify text analytics processes for technology and business professionals. Attendees will also gain insight on mapping your business requirements to vendor capabilities in the text analytics vendor selection process.

9:40-10:00AM

TRACK SESSION

Frédérick Guillot
Manager, Research and Innovation
Co-operators General Insurance Company


Case Study: Co-operators General Insurance Company
Leveraging Hands on Approaches to Identify Actionable Topics in Property Insurance

The insurance business is a very complex world, where many types of interactions with clients are involved, each generating plenty of structured and unstructured data. One consequence of this phenomenon is that most of the data work in insurance involve getting hands on approaches, and taking iterative deep dives into detailed records to identify patterns. The presentation will highlight how we leveraged this hands on approach, combined with predictive modeling, to identify rapidly relevant actionable topics for our business stakeholders, and to generate simple identification rules to automatically flag these topics within our CRM text fields.

10:00-10:30AM

NETWORKING BREAK

Mingle with fellow attendees on the exhibit floor.

10:30-11:05AM

TRACK SESSION

Bryan Bell
Vice President of Global Marketing
Expert System


What is in Your Business Requirement? Searching or Finding

It is a commonly known fact that locating and sharing the right information at the right time is critical to the success of organizational business. The problem is that information often arrives faster and from a larger variety of sources than any company or department can reasonably manage, organize and utilize a meaningful way. Join industry leaders and learn how some of the world’s leading organizations are exploiting deep linguistic analysis, combined with semantics to turn any knowledge management platform into a smart find platform!

11:05-11:40AM

TRACK SESSION

Richard Lanza
CEO
Cash Recovery Partners, LLC


Using Letter Analytic Techniques to Pinpoint Textual Deviations

Textual analytics always produces something interesting, yet the tools being used can take too long or outright miss the subtleties in the data. Wordles, for example, provide a useful image of the words yet are not effective in identifying deviations over time. To supplement this need, a new letter approach can quickly identify deviations in word usage over time and to established English usage benchmarks. Using a variety of case examples and new visualizations, this new letter approach called letter analytics will improve textual analytic efficiency and allow the analyst more time for drafting improved conclusions.

11:40-12:05PM

TRACK SESSION

Jayakrishna Venkatesh
Head of Analytics & Digital Practice
Motivity Labs Inc & Naya Ventures


Case Study: Target Corp, Geman Sports Garment Manufacturer
Using Sentiment Analytics to Build Feedback Response Systems

In the world where importance to “Customer Centricity” is key, customer feedbacks and responses are crucial for a brand’s growth and perception. A low FB,Yelp or Glassdoor score indicates that something is wrong with the brand or employer but the verbatim/feedback from the customer/employer holds the key to explain what was wrong and what he/she expects. It’s critical to put someone on such hearing roles and it might take too much human resource to respond to all comments and react- A text analytics approach to this problem would mean faster responses, lesser human resources and actionable insights to increase CSAT.

12:05-1:30PM

LUNCH

Join us for lunch and networking breaks in the Main Hall

1:30-2:15PM

TRACK SESSION

Mike Moran
Senior Strategist
Revealed Context


Challenges and Solutions for Social Media Listening for Market Research

Social media listening doesn’t always need fancy tools, when spotting trends is all you need to do, such as for crisis management. But when conducting market research, you must aggregate the conversation and draw broad conclusions on sentiment and other categories, highlighting huge challenges that don’t always have easy answers. Semi-supervised machine learning, relevance feedback, crowdsourcing, and other techniques can provide some answers to these challenges to allow customized categorization of social conversations and even the hope of predictive levels of accuracy.

2:20-3:05PM

TRACK SESSION

Emrah Budur
Senior Software Engineer
Garanti Technology


Case Study: Global Banking Industry
Tips and Tricks on Developing High-Performance Fuzzy Name Search Engine to Prevent Terrorism Financing

The increasing number of sanctioned entities enforced by the governmental units threatens the reputation and security of world class financial institutions. In particular, the banks are in charge of preventing terrorism financing by precisely detecting inappropriate transactions out of large amount of legitimate money transfers in real time. In this session, we will explore the tips and tricks of developing high precision&recall fuzzy name search engine. We will also present the benchmark results that compare in-house developed solution against the solutions of the market leaders.

3:05-3:30PM

NETWORKING BREAK

Mingle with fellow attendees on the exhibit floor.



 

3:30-4:00PM

TRACK SESSION

Dirk Van Hyfte
Senior Advisor for Biomedical Informatics
InterSystems Corp

Mikhail Tsatsulin
Senior Software Developer
InterSystems Corp


Personalized Medicine and Text Analytics

Today healthcare has been transformed into industrial behemoth treating a patient as an assembly on a conveyor belt. Transition (back) to Personalized Medicine became a popular buzzword.

In this talk we concentrate on a gap between feature engineering based on a free text and the modeling used in health IT, and the fact that texts are structurally and grammatically are different in different domains. We will analyze three healthcare related domains: EPRs (Electronic Patient Records), PubMed abstracts and health related Social Media posts. We will show how different technologies can extract different type of information out of them.

4:00-4:15PM

CLOSING REMARKS

Steven Ramirez
CEO
Beyond the Arc

Closing Remarks/Wrap Up