Page not found - Text Analytics World Page not found - Text Analytics World

No Results Found

The page you requested could not be found. Try refining your search, or use the navigation above to locate the post.

Tuesday, March 31, 2015

8:00-8:40am

Registration & Networking Breakfast – Room: Grand Assembly


8:40-8:45am

Conference Chair Welcome RemarksRoom: Salon 10/11

Speaker: Tom Reamy, Chief Knowledge Architect, KAPS Group

[ Top of this page ] [ Agenda overview ]


8:45-9:05am

Diamond Sponsor PresentationRoom: Salon 10/11
Augmented Intelligence: Machine Learning, Human Curation and the User Experience
Brainspace

The text analytics landscape is evolving. We are moving from simple, transactional interfaces, largely driven by search, to more dynamic, connected, visual experiences driven by machine learning. In our near future—indeed the present possibility—is an experience in which the reason, judgment and knowledge of an individual is augmented by large-scale machine learning and the collective intelligence of the world.

Speaker: Ravi Sathyanna, Vice President of Technology, Brainspace

[ Top of this page ] [ Agenda overview ]


9:05-9:50am
Keynote
The Architecture of Understanding
Room: Salon 10/11

If we hope to move forward, the UX community must go deep. We’ve been seduced by surface at the expense of understanding. We think we’re designing software, websites, and experiences. But we’re not. We are agents of change. Until we accept this mission, we will forever repeat our mistakes. How can we work together when we’re divided by silos? How will we innovate while blinded by cultural illiteracy? The things we make are reflections of the language we use and the ways we organize ourselves. It’s time to stop twittering about unicorns and start shaping strategy. It’s time to be architects of understanding.

In this spirited tour of information architecture, organizational strategy, and systems thinking, Peter Morville draws from his new book, Intertwingled, to reveal how everything is connected from code to culture. It’s a trip into the wilderness of cognition and complexity that delivers a simple message: the UX community can change the world, but only if we have the courage to go deep.

Speaker: Peter Morville, President, Semantic Studios

[ Top of this page ] [ Agenda overview ]


9:50-10:15am

Exhibits & Morning Coffee Break – Room: Salon 8/9

[ Top of this page ] [ Agenda overview ]


10:15-10:45am

Case Study: Baader Bank AG
Real-Time Text Analytics for Event Detection in the Financial World
Room: Salon 10/11

Baader Bank is one of the leading investment banks in the German speaking region. Its traders have to read 500.000 news per day. This information overflow has often caused relevant news to be overseen. Clueda implemented a text analytics software for Baader Bank, detecting market-moving events with a processing speed of 50 milliseconds per news. In his session, Volker Stümpflen will introduce the concept of associative text analytics, which combines methods from NLP, statistics and neuronal networks. He will also explain how the systemic mood algorithm and the systemic stability indicator propagate mood and predict price fluctuations in real-time.

Speaker: Volker Stuempflen, CEO, Clueda AG

[ Top of this page ] [ Agenda overview ]


10:50-11:20am

Mining Text and Structure for Real Estate IntelligenceRoom: Salon 10/11

We explore how a combination of relatively simple text-mining techniques such as entity extraction and text categorization combined with human input can enhance structured analytical methods for real estate intelligence. We present examples for tasks such as home price estimation and market analysis for residential real estate in San Francisco.

Speaker: Catherine Baudin, Chief Technology Officer, Grokcity Inc.

[ Top of this page ] [ Agenda overview ]


11:25-11:55am

Case Study: A.T. Kearney
Human And Machine: Applying Knowledge Skills To Solve Big Data Problems
Room: Salon 10/11

This session describes the emergence of text analytics within A.T. Kearney’s Procurement & Analytic Solutions Practice based on our two-part approach to text mining comprising human and machine elements. Although text mining projects can be deployed with little human involvement, the Practice believes that even better results can be obtained by a two-lever approach.

Lever one utilizes the expertise of a professional knowledge worker to train the machine; lever two utilizes machine power to interrogate the big dataset using the taxonomy. The presentation demonstrates three case examples of how we have delivered actionable insights through text analytics and big data.

Speaker: Helen Clegg, Knowledge Director, A.T. Kearney

[ Top of this page ] [ Agenda overview ]


12:00-12:30pm

Case Study: Educational Analytics and Logisitics
Improving School Discipline through Text Analytics
Room: Salon 10/11

In today’s public school there has been a growth in disciplinary problems among children of all ages. These problems diminish the time on task for students and teachers compromising learning. The analysis of these records through text analytics provided an explanation facing each school in particular and the system in general. The trends and patterns revealed themselves to administrators so that the unstructured data could yield the true source of the problem. This session focuses on what was done and what should have been done to produce better outcomes.

Speaker: Chris Bowman, President, Educational Analytics and Logistics

[ Top of this page ] [ Agenda overview ]


12:30-1:30pm

Lunch

[ Top of this page ] [ Agenda overview ]


1:30-2:00pm
Mini-Workshop
Using Text Analytics as a Tool Set
Room: Salon 10/11

Big data inferences are increasingly used to mine huge heaps of data. The applications are endless. However, those inferences do not work well when many lines go to a single bubble. The lines and relationships must be drawn between concepts not simply between words. Using the text analytics is a powerful tool, but it is a means to an end not the end itself. The important work is in the interpretation of the data. If the basic data has not been properly harnessed then erroneous conclusions are drawn. This paper outlines a highly accurate and efficient approach and provides a case study of the application. Using taxonomies and increasing number of synonyms allows building quickly on the data gathered via text analytic means. The data gathered from inferential approaches to the data by mining content using n-grams, Levenson distances, stemming and other methods is then further refined via a rule based approach. 80% of the rules are built automatically. Conceptually redundant tag clouds are cured by synonyms and near matches are treated and inclusionary rules built to insure that the data mined is focused and items are not missed because they are differently stated conceptual duplicates. we can use text analytics to data mine for the words and take care of metaphors with rules. People wonder why we choose the rule based approach – the cost benefit analysis of an editor versus a bag of words. The hybrid approach of using traditional analytic means for gathering, shifting and then maintaining the term base combined with the rules based approach for speed and accuracy builds on complementary technologies for an agile, flexible deployment. Finally, a cost and accuracy comparison is given showing why the combination is the strongest solution.

Speaker: Marjorie Hlava, President, Access Innovations, Inc. and Data Harmony

[ Top of this page ] [ Agenda overview ]


2:05-2:35pm

Case Study: Elsevier
Large Scale Text Analysis using Apache Spark
Room: Salon 10/11

Elsevier Labs has developed an internal text analysis system, which runs a variety of standard Natural Language Processing steps over our archive of XML documents. We are now extending that basic system by using Spark and other parts of the Berkeley Data Analytics Stack for additional analyses, including ones at interactive speeds. We expect this to let us prototype new features more easily, and/or look at making current features more efficient. This talk will cover the architecture of the system and our experiences with Spark and other BDAS components

Speaker: Ron Daniel, Director, Elsevier

[ Top of this page ] [ Agenda overview ]


2:40-3:10pm

Connecting Human Behavior and Patterns in Data for the EnterpriseRoom: Salon 10/11

First, apply statistical methodologies with relevant language (like Python or R) to process, analyze, and validate. Next, report the analysis with visualizations… this is a solid strategy! Advanced methods and technologies expose unlimited gems connecting human behavior and patterns in data. Recognizing these connections has brought about the evolution of the data scientist and an upswing in jobs.

Effectively utilizing data and behavior connections requires the strategy provided by an Information Governance (IG) plan to facilitate the path for successful enterprise application of following those connections. Strategic IG facilitates the balance of data, technology and business value.

Speaker: Sarah Ann Berndt, Sr. Associate Forensic Technology Solutions, PricewaterhouseCoopers LLP

[ Top of this page ] [ Agenda overview ]


3:10-3:40pm

Exhibits & Afternoon Break- Room: Salon 8/9

[ Top of this page ] [ Agenda overview ]


3:45-4:15pm

Knowledge Discovery through Topic ModelingRoom: Salon 10/11

Knowledge sharing is a goal of every organization. At NASA, knowledge is captured for reuse in a many different methods, from Storytelling to Case Studies to Lessons Learned. This knowledge is accessible through web sites and countless databases. As the level of information grows, so does the time to find the most relevant information for your particular needs. In this session we will explore the use of Topic Modeling to organize the documents over an underlying set of topic probabilities, allowing users to uncover pertinent knowledge quicker. A visualization technique will be demonstrated to view the grouping of the topics as well as the importance of the relevant terms to the topic.

Speaker: David Meza, Operational Excellence Program Manager, Johnson Space Center

[ Top of this page ] [ Agenda overview ]


4:15-4:45pm

Case Study: GSA – Google Search Appliance
What is in Your Business Requirement? Searching or Finding
Room: Salon 10/11

Internal and external information comes at us faster than we can keep up with. And business expectations for deploying solutions, using enterprise search and content navigation systems to capture the hidden value of strategic information have not changed. By deploying an automated text analytics platform to dynamically enrich content with the right metadata, forward thinking corporations are enhancing the effectiveness of their existing platforms and deploying a defined systems as the heart of any knowledge management applications. Join industry leaders and get the latest on exploiting deep linguistic analysis, combined with semantics to turn your search engine into a find engine!

Speaker: Bryan Bell, Executive Vice President, Expert Systems

[ Top of this page ] [ Agenda overview ]


4:50-5:35pm
Ask the ExpertsRoom: Salon 10/11

Session description Coming soon.

Speakers:
Bryan Bell, Executive Vice President, Expert Systems
Catherine Havasi , CEO & Co-founder, Luminoso
Richard Mallah, Director of Unstructured and Big Data Analytics , Cambridge Semantics, Inc.

[ Top of this page ] [ Agenda overview ]



5:35-7:00pm
Networking ReceptionRoom: Salon 8/9

[ Top of this page ] [ Agenda overview ]



7:00-10:00pm
Dinner with StrangersStop by the eZone to sign up in advance! Located at Booth 316

[ Top of this page ] [ Agenda overview ]

Wednesday, April 1, 2015

8:00-8:45am

Registration- Room: Grand Assembly


8:00-8:45am

Networking Breakfast- Room: Salon 8/19


8:45-9:30am
Keynote
Future Directions of Text Analytics: Smarter, Bigger, and Better
Room: Salon 10/11

Text analytics as a field has been strongly growing for a number of years, but still suffers from a lot of confusion about just what it is, what kinds of technologies are involved, and what kinds of applications can be built with it. Now that confusion can finally be resolved with the publication of a new book on text analytics by the chair of this conference, Tom Reamy.

The book covers all aspects of text analytics from technology to applications, from how to get started to how to develop the most advanced features, from business benefits of text analytics to the future directions of the field. This keynote will focus on the last item – future directions that hold the most promise for the use of text analytics in a wide range of industries and applications.

As an extra treat, at the end of the talk, we will have a drawing to win a free copy of the book – open to all attendees.

Speaker: Tom Reamy, Chief Knowledge Architect, KAPS Group

[ Top of this page ] [ Agenda overview ]


9:35-10:05am

Case Study: Sony
Bringing Coherence to Chaos – Automated Analysis on Large-Scale Social Data for the 2014 World Cup
Room: Salon 10/11

Twitter has changed. The growth and worldwide success of Twitter has surfaced natural limitations of hashtags and keyword searches. What was once a mechanism for organizing information for efficient consumption is now often rendered obsolete by overwhelming volume and diversity of discussion. Listening to a large number of posts on a given hashtag becomes unproductive, as the conversations spawned within and around these hashtags are indistinct and drowned. Luminoso restored the ability to understand, consume, and participate in large-scale social media discussions by automatically eliminating spam, removing duplicates, clustering thematically similar conversation, and surfacing meaningful discussion. Sony harnessed Luminoso’s.

Speaker: Catherine Havasi, CEO & Co-founder, Luminoso

[ Top of this page ] [ Agenda overview ]


10:10-10:40am

5 Creative Search Solutions based on Text AnalyticsRoom: Salon 10/11

Too many organizations continue to struggle to deliver effective search for their users. Text Analytics is a critical tool to help turn search from a simple text based query tool to a product that provides meaningful insights to its users. As part of this presentation we will share 5 unique search solutions that use Text Analytics to deliver real knowledge from unstructured documents. These solutions will be based on real world case studies that illustrate best practices for harnessing text analytics to amplify search.

Speaker: Joseph Hilger, Principal, Enterprise Knowledge, LLC

[ Top of this page ] [ Agenda overview ]


10:40-11:10am

Exhibits & Morning Coffee Break- Room: Salon 8/9

[ Top of this page ] [ Agenda overview ]


11:10-11:40am

Big Metadata Toolkits: Pattern Analysis and Categorization ComponentsRoom: Salon 10/11

The exploding volume, complexity and velocity of structured and unstructured data, especially from all sorts of interactions with it, presents challenges and opportunities to derive valuable insights. Among the challenges of managing massive data sets are gathering, validating, preserving, analyzing and maintaining linkages from those analyses to the source data set. Identifying patterns in data sets using information retrieval methods and writing out the results, as metadata is a well established information management process that should be adopted by organizations working with today’s big data sets. This presentation provides an overview of pattern analysis and categorization methods.

Speaker: Joseph Busch, Principal, Taxonomy Strategies

[ Top of this page ] [ Agenda overview ]


11:45-12:15pm

Case Studies: KPMG, JWG
Automating compliance processes using Content Intelligence
Room: Salon 10/11

This session takes a detailed look at how text analysis and content intelligence is used to automated compliance processes that involve large volumes of text-based information. This is a practical walk through of two case studies implemented in financial services. The first use case is client on boarding compliance including FATCA and KYC; the second is Dodd Frank compliance.

These case studies are drawn from projects that Smartlogic have implemented, and although financial in nature, are relevant to any one interested in automating business processes involving complex and varied content-based information.

Speaker: Anne Lapkin, SVP, Global Strategy, Smart Logic

[ Top of this page ] [ Agenda overview ]


12:15-1:30pm

Lunch in the Exhibit Hall- Room: Salon 8/9

[ Top of this page ] [ Agenda overview ]


1:30-2:00pm

Using Text Analytics to Drive Richer DataRoom: Salon 10/11

Customers today expect near-perfect execution in real-time. The only way to know if you’re hitting the mark is to ask them to tell you. Text analytics allow companies to listen to their customers, and use those insights to change the way they do business. Innovative applications of text analytics can move companies beyond just aggregate listening; to completely reinvent the way customers tell their stories.

Speaker: Spencer Morris, Vice President Text Analytics and Lead Experience Engineer, InMoment

[ Top of this page ] [ Agenda overview ]



2:05-2:35pm

Case Studies: CFPB, Capital One, Citibank, Bank of America
What Doesn’t Kill You Makes You Stronger: Resolving Customer Complaints with Text Analytics
Room: Salon 10/11

With the increasing popularity of digital channels, such as Facebook and Twitter, social media has morphed into a sounding board for consumers to broadcast positive and negative experiences with businesses. While positive responses often capture the most attention from organizations, businesses can gain unheard of insight into emerging customer issues before they become full-fledged complaints through the use of text analytics.

Based on his analysis of the CFPB’s Consumer Complaint Database, Brandon Purcell of Beyond the Arc will share first-hand experiences with complaint management and shed light on best practices for leveraging text analytics to successfully resolve emerging customer issues.

Speaker: Brandon Purcell, Data Science Team Lead, Beyond the Arc, Inc.

[ Top of this page ] [ Agenda overview ]


2:40-3:10pm

Powering the Digital Economy Using Cognitive ComputingRoom: Salon 10/11

Utilities around the world are deploying situational intelligence applications to correlate, analyze, and visualize business, operational and IoT data, spatially, over time and across network nodes. The resulting 360-degree view of the enterprise provides many benefits for their work in powering the digital economy.

Our situational intelligence applications use cognitive computing, based on Kolmogorov Complexity, for real-time analysis of time series and text from connected devices.

This presentation features three use cases from utilities: diagnosing smart meters in real time, predicting power outages and optimizing spare part replacement on wind turbines.

Speaker: Paul Hofmann, CTO, Space-Time Insight

[ Top of this page ] [ Agenda overview ]


3:10-3:40pm

Exhibits & Afternoon Break- Room: Salon 8/9

[ Top of this page ] [ Agenda overview ]


3:40-4:20pm

Forensic Relationship Exploration In Financial ComplianceRoom: Salon 10/11

Investigating fraud, insider trading, and other financial misconduct requires tying together long chains of often subtle and deeply buried information, much of which is unstructured. See how the technique of semantic overlay lets us make multiple diverse NLP technologies cooperate without prior coordination. Richard describes how complex relationships undetectable by any single technology are mined from chats, emails, and call transcripts against a backdrop of analyst reports, news articles, and social media.

Speaker: Richard Mallah, Director of Unstructured and Big Data Analytics, Cambridge Semantics, Inc.

[ Top of this page ] [ Agenda overview ]


4:25-4:55pm

Expert PanelRoom: Salon 10/11

Session description coming soon.

Speakers:
Joseph Busch, Principal, Taxonomy Strategies
Paul Hofmann, CTO, Space-Time Insight
Anne Lapkin, SVP, Global Strategy, Smart Logic

[ Top of this page ] [ Agenda overview ]