Upload
noah-bryan
View
217
Download
0
Tags:
Embed Size (px)
Citation preview
SEASR – Software Environment for the Advancement of Scholarly Research
OverviewUniversity of Illinois
June 2007
Michael Welge, Loretta Auvil, John UnsworthData Intensive Technologies and Applications/IGB
Automated Learning Group, and GSLISUniversity of Illinois, Urbana-Champaign
Structured Data “Rush”
• Provides scalable environment from the Desktop to Web Services to Grid Services
• Employs a visual programming system for data/work flow paradigm
• Provides capability to build custom applications
• Provides capability to access data management tools
• Contains data mining algorithms for prediction and discovery
• Provides data transformations for standard operations
• Integrated environment for models and visualization
• Supports an extensible interface for creating one’s own algorithms
• Provides access to distributed computing capabilities
D2K- Framework for Data Analysis
D2K Components
• D2K Infrastructure• Itinerary Execution engine
• D2K-Driven Applications• Applications that make use of the D2K
Infrastructure• Toolkit is a D2K-Driven app
• D2K Server• Special kind of D2K-Driven app• Wraps the infrastructure to provide remote
itinerary and module execution• Used by the Toolkit to distribute module
execution• D2K Web Service
• Provides a generic programmatic interface for executing itineraries
• Communicates with D2K Servers over socket connections using D2K Specific protocols.
PredictionIndustrial ManufacturerComputed customer buying propensitiesAchieved 25% conquest customer sales lift by executing directed cross/upsell resulting in $65 million in incremental revenue
DiscoveryAutomotive manufacturerIdentified patterns of inappropriate warranty work in dealer channelTargeted $200M+ of potentially unnecessary annual expense
MonitoringDepartment store retailerWatched POS transaction flow for unusual variationsDeterred inappropriate behavior and fraudulent transactionsResulted in savings of over $125 million
Creating Customer Value
Applications Examples
Harris A. Lewin explains that Evolution Highway allows one to look " . . . at the whole genome at once - multiple chromosomes across multiple species. The insights wouldn't have come so quickly if we couldn't throw the data at this framework from NCSA.”
Nicholas M. Ball, Robert J. Brunner, Adam D. Myers, and David Tcheng, Robust Machine Learning Applied to Astronomical Data Sets. I. Star-Galaxy Classification of the Sloan Digital Sky Survey DR3 Using Decision Trees, The Astrophysical Journal, Vol. 650, Part 1, Pages 497–509, 2006
Comparative Genomics
Science, Vol. 309, Issue 5734, Pages 613-617, 22 July 2005
Music AnalysisJ. Stephen Downie, The Scientific Evaluation of Music Information Retrieval Systems: Foundations and Future, Computer Music Journal, Vol. 28, No. 2, Pages 12-23 Summer 2004
Astronomy
Research, Development, & Technology Transfer Model
SEASR: The Data ProblemStructured Vs. Unstructured
1999
GIG
AB
YTES
Cave paintings,Bone tools 40,000
BCEWriting 3500 BCE
0 C.E.
Paper 105
Printing 1450
Electricity, Telephone 1870
Transistor 1947
Computing 1950Internet (DARPA) Late 1960s
The Web 1993
20% 20% Structured Structured DataData
80%80% Unstructured Unstructured DataData
Today, 80% of business is conducted Today, 80% of business is conducted on unstructured informationon unstructured information– – Gartner Group
80% of the information 80% of the information needed needed is in the Open Sourceis in the Open Source– – NIA
Workers spend 80% of the Workers spend 80% of the time gathering time gathering informationinformation– – STIC, EMF
Source: www.fastsearch.com
-15 Years
Database
The Internet
Today
Unstructured Information
email / Word / HTML / PDF / etc
Semi-structured InformationDoc Mgt / XML
• Today, 80% of business is conducted on unstructured information
Gartner Group
• 80% of the information needed is in the Open Source
NIA
• Workers spend 80% of the time gathering information
STIC, EMF
Unstructured Data “Rush”
The issue is getting worse...
Now
Other forms of Unstructured Information
Affecting every Industry Sector
Video
+
Voice
Multiple Devices
+
Hail SEASR!
Software Environment for the Advancement of Scholarly Research (SEASR)
– addresses the challenges of transforming information into knowledge by constructing
the software bridges that are required to move from the unstructured and semi-
structured data world to the structured data world.
– aims to make collections more useful by integrating two well-known research and
development frameworks NCSA’s Data-To-Knowledge (D2K) and IBM’s Unstructured
Information Management Architecture (UIMA) into an easily usable environment that
researchers in any discipline can easily learn and adapt for their own unstructured
data analysis.
UIMA Lineage
• Developed over 5 years
– Funded by DARPA (GALE)
– Companies: BBN, MITRE, SAIC
– Universities: Carnegie Mellon, Columbia, UMass/Amherst
– 100 Developers from IBM World Wide
• UIMA Enables ….– Part of Speech Detectors– Document Structure Detectors– Tokenizers, Parsers, Translators– Named-Entity Detectors– Sentiment Detectors– Relationship Detectors
SEASR: Architecture
SEASR’s advanced informatics tools will expand the technical capabilities of what is now available in the field by:
• connecting data sources that are currently incompatible, whether due to different formats or protocols
• offering all project components as open source, to enable users to modify and add to tools
• allowing users to write analytic engines in their programming language of choice
• installing on all hardware footprints, so that the tools can be brought to data sets where they are housed
• creating a repository for components that will support sharing and publishing among users
• enabling scalability so that components may run on a large variety of hardware footprints, including shared memory processors and clusters
SEASR: Research, Development, & Technology Transfer Model
Research Areas
• Focused Data Retrieval and Data Integration: Given a target topic (Iran’s nuclear program) or an entity (University of Tehran), how do we locate, retrieve, and integrate all relevant data-both structured (databases) and observational (sensory data, textual data, image data)?
• Semantic Data Enrichment: How to handle the overwhelming array of different data formats, how to understand the layout of data and infer metadata for a variety of text sources and images, and how to infer semantic markup and construct/augment knowledge bases.
• Entity and Relationship Discovery: How can we match ambiguous mentions of entities across both structured data and text? How do we discover relationships among entities? How do we related new collected data to existing knowledge bases?
IACAT, Dan Roth and Jiawei Han, CS, UIUC
Research Areas
• Knowledge Discovery and Hypotheses Generation: How to exploit the rich semantic structure generated by identifying entities and relationships among them to promote knowledge discovery and to generate hypotheses that emerge from “surprising” correlations or structural events?
• Intelligent Human-Computer Interactions for Information Access: How to devise effective interaction models and interfaces for accessing multimodal data, interactive annotation and discovery models, and support hypotheses suggestion and verification?
• Mathematical and Computational Foundations: The research described above builds on our team members’ work on key mathematical and algorithmic questions underlying progress in the Data Sciences, and serves to motivate further theoretical questions.
IACAT, Dan Roth and Jiawei Han, CS, UIUC
Getting the “Band” Together
• June 2007 – Band formation– Project start date– More use ideas and framework discussions
• December – First ‘gig”– Framework and data app demonstration
• Vocals - Research Technology– John Unsworth, Stephen Downie, Tim Wentling– Dan Roth, Jiawei Han, Kevin Chang, Cheng Xiang Zhai
• Percussions & Bass - SEASR Development– Loretta Auvil, Tara Bazler, Duane Searsmith, Andrew Shirk, Students
• Lead – Designers/Developer/Applications Areas– Humanities – M2K, Nora/Monk and Others (we heard about
yesterday/today))• Need Groupies! (Advisors, Researchers, Developers, and Application
Drivers) – Loretta Auvil
SEASR: How can I participate?
• Collaborate on application development or ontology creation
• Contribute to component development for analytics or data access
• Participate in visualization and UI design
• Serve as an advisor
Contact Loretta Auvil ([email protected])
SEASREngineering Knowledge for the Humanities
Thank You
Lincoln Papers Project
• A Model for Digital Humanities Scholarship • Collaboration between I-CHASS, and the Lincoln Presidential
Museum and Library in Springfield, Illinois– UIUC permanent home of digital archive of all Lincoln
materials held by Lincoln Library
• Opportunities for Discovery from the Lincoln Papers– Provides ability to explore many technologies of interest
to humanities scholars, including:• Digitization and OCR• Information Extraction and Analysis of text- and
image-based information• Social Networking Tools• Geo-spatial Analysis
– Solutions can be transferred to other digital collections, such as Founding Father’s Papers
Vernon Burton, History Department, UIUC
Research Project and Consequence of Digital Analysis
• Scholar interested in development of Lincoln’s concept of “Liberty”– Data extraction tools identify all instances of “liberty” and related
concepts– Social networking tools trace with whom, when, and how frequently
Lincoln corresponded on the subject– Geo-spatial analysis can reveal regional differences in support for
emancipation• Scholar is able to
– Easily identify and retrieve all key materials from a collection numbering hundreds of thousands--or even millions--of documents
– Gain insight into development and strength of Lincoln’s commitment to emancipation
– Identify key correspondents--some of whom might have previously been overlooked--who helped shape Lincoln’s public policy
Vernon Burton, History Department, UIUC
Other Example Research
• Voice mining (DH 2006 Poster )– Scholar is interested in development of models that can analyze characters’
utterances in plays. – Scholar is able to construct analytical models that can successfully identify the
socio-economic class or status of the character which uttered a given line of play text.• Criticism mining (DH 2006)
– Scholar is interested in development of tools that can automatically analyze critical reviews on humanities objects.
– Scholar is able to easily construct text categorization models predict positive and negative reviews; predict the genre of the work being reviewed; and differentiate fiction and non-fiction book reviews
• Differentiating Editorial and Customer Critiques of Cultural Objects Using Text Mining (DH 2007)
– Scholar is interested in development of tools that can automatically differentiate critiques written by scholars and professional editors versus ordinary readers.
– Scholar is able to use text mining tools to differentiate these two kinds of critiques as well as to see what features makes them different.
J. Stephen Downie, GSLIS, UIUC
Conceptual Analytical Architecture
SEASR Architecture
Structured Data for Analysis
• Low Volume Data
– Wire services
– Call Detail Records
– Phone directories
– Badge access tracking
– Customer lists
– Account histories
– Supplier network data
– Biometric access data
• High Volume Data– Stock transactions– Web pages– News Wire feeds– Audits– CRM databases– Web access logs– Net logs– Mutual Fund validation– Credit/Debit transactions– RFID tracking logs
Unstructured Data for Analysis
• Low Volume Data– Email, Chat and IM– Internal documents– Call Center data logs– Pager data– External reports and
data– Publicly accessible
records– Calendars– RF monitoring– Print stream monitoring
• High Volume Data– VOIP phone calls– Broadcast media– Web cam data– Deep web crawl data– Surveillance cameras– Videoconferences– Voice mail– Satellite data
Current SEASR Team
• PI: Michael Welge, NCSA• Co-PI: John Unsworth, GSLIS; Loretta Auvil, NCSA• Technical Lead: Duane Searsmith, NCSA• Use Cases and Communities Involvement: Loretta Auvil, NCSA• Usability Evaluator: Tara Bazler, Indiana University• Software and Application Developers
– Bernie Acs, NCSA– Vered Goren, NCSA– Amit Kumar, NCSA– Xavier Llora, NCSA– Mary Pietrowicz, NCSA– Andrew Shirk, NCSA– David Tcheng, NCSA
• Humanities Domain and Communications Consultant– Kelly Searsmith, NCSA
• Community Advisors– Tim Cole, Mathematics Librarian, UIUC