Georgia Koutrika
- Palo Alto, CA, USA
Bio
A computer scientist, software developer, and inventor, Georgia Koutrika is a Senior Research Scientist at HP Labs. Her research and passion span user analytics and profiling, personalization, recommender systems, and content understanding with applications including online learning systems, social data applications, and automated publishing.
Georgia's work brings together elements and methods from databases, information retrieval, information extraction, entity resolution, information integration, recommendations, machine learning, data mining, and big data processing. Her work has been incorporated in many commercial products. She holds 4 issued patents and has filed over 20 patent applications in the US and worldwide.
She has authored and co-authored more than 80 research papers in peer-reviewed conferences (including ACM SIGMOD, PVLDB, and IEEE ICDE) and journals (including ACM TODS and IEEE TKDE). She is also actively serving the scientific community. She is currently a General Co-Chair for ACM SIGMOD 2016, an Industrial Track PC Chair for EDBT 2016, and a Workshop and Tutorial Co-Chair for IEEE ICDE 2016. She has served in the PC of several conferences like ACM SIGMOD, PVLDB, ACM SIGKDD, WWW, IEEE ICDE, EDBT, etc.
Positions
- Present2012Senior Research ScientistHewlett Packard, HP Labs
- 20122010Postdoc ResearcherIBM, IBM Almaden Research Center
- 20092007Research VisitorHewlett Packard, HP Labs
- 20092006Postdoc ResearcherStanford University, Infolab, Computer Science Dept.
Education
- Ph.D.Ph.D., Computer Science
Dissertation: 'Query Personalization based on User Preferences'
University of Athens
- M.Sc.M.Sc., Advanced Information Systems
Thesis: 'Searching and displaying medical DICOM images'
University of Athens
- B.Sc.B.Sc., Computer Science
University of Athens
Awards and Grants
- 2012Best ACM SIGMOD Demonstration Award
Received the Best Demo Award for 'Logos: A System for Translating Queries into Narratives' - 2009Best ACM SIGMOD Demonstration Award Received the Best Demo Award for 'CourseRank: A Social System for Course Planning.'
- 2004DELOS Network of Excellence Fellowship
Excellence Fellowship for young researchers for participation in the DELOS summer school in “User-Centered Design in Digital Libraries - 2002Onassis Foundation Fellowship
Fellowship for participation in the 2002 Lectures in Computer Science devoted to “The Data Avalanche: Reducing Information Overload” in Heraklion, Crete - 2003 - 2001First Award Scholarship
Prestiguous scholarship from the Greek State Scholarship’s Foundation (IKY) for PhD studies
Selected Publications
Georgia has authored and co-authored more than 80 research papers and articles in the areas of databases, information retrieval, information extraction, entity resolution, information integration, recommendations, machine learning, data mining, and big data processing.
For a complete list of her publications, please visit DBLP . Citations of Georgia's work can be found in Google Scholar .
- JournalMeta-Blocking: Taking Entity Resolution to the Next Level.
G. Papadakis, G. Koutrika, T. Palpanas, W. Nejdl.
In IEEE Transactions on Knowledge and Data Engineering, 26(8),1946-1960, 2014.
- JournalPrefDB: Supporting Preferences as First-Class Citizens in Relational Databases.
A. Arvanitis, G. Koutrika.
In IEEE Transactions on Knowledge and Data Engineering, 26(6), 1430-1446, 2014.
- JournalA Survey on Representation, Composition and Application of Preferences in Database Systems.
K. Stefanidis, G. Koutrika, E. Pitoura.
In ACM Transactions on Database Systems, 36(4), 2011.
- JournalInformation Seeking: Convergence of Search, Recommendations and Advertising.
H. Garcia-Molina, G. Koutrika, A. Parameswaran.
In Communications of ACM, 54(11): 121-130, 2011.
- JournalPersonalizing Queries based on Networks of Composite Preferences.
G. Koutrika, Y. Ioannidis.
In ACM Transactions on Database Systems, 35(2), 2010.
- JournalPrécis: From Unstructured Keywords as Queries to Structured Databases as Answers.
A. Simitsis, G. Koutrika, Y. Ioannidis.
In VLDB Journal, 17(1): 117-149, 2008.
- JournalCombating Spam in Tagging Systems: An Evaluation.
G. Koutrika, F. Effendi, Z. Gyöngyi, P. Heymann, H. Garcia-Molina.
In ACM Transactions on the Web, 2(4), 2008.
- JournalRule-based query personalization in digital libraries.
G. Koutrika, Y. Ioannidis.
In International Journal on Digital Libraries, Springer-Verlag, 4(1), 60-63, 2004.
- ConferenceSchema-agnostic vs Schema-based Configurations for Blocking Methods on Homogeneous Data.
G. Papadakis, G. Alexiou, G. Papastefanatos, G. Koutrika.
In PVLDB, Vol 9, 2015.
- ConferenceGenerating Reading Orders over Document Collections.
G. Koutrika, L. Liu, S. Simske.
In 31st Int’l Conference on Data Engineering, ICDE, 2015.
- ConferenceTo Print or Not to Print: Hybrid Learning with METIS Learning Platform.
J. Hailpern, R. Vernica, M. Bullock, U. Chatow, J. Fan, G. Koutrika, J. Liu, L. Liu, S. Simske, S. Wu.
In 7th ACM SIGCHI Symposium on Engineering Interactive Computing Systems, EiCS, 2015.
- ConferenceLearningAssistant: A Novel Learning Resource Recommendation System.
L. Liu, G. Koutrika, Shanchan Wu.
In 31st Int’l Conference on Data Engineering, ICDE, 2015.
- ConferenceSupervised Metablocking.
G. Papadakis, G. Papastefanatos, G. Koutrika.
In PVLDB, 7(14), 2014.
- ConferenceLearn2Learn: A Visual Analysis Educational System for Study Planning.
J. Wei, G. Koutrika, S. Wu.
In 17th Int’l Conference on Extending Database Technology, EDBT, 2014.
- ConferenceUser Analytics with UbeOne: Insights into Web Printing.
G. Koutrika, Q. Lin, J. Liu.
In 39th Int’l Conference on Very Large Data Bases, VLDB, 1382-1385, 2013.
- ConferenceThe Farm - where Pig Scripts are bred and raised.
C. Sayers, A. Simitsis, G. Koutrika, A. Guerrero Gonzalez, D. Tamez Cantu, M. Hsu.
In ACM SIGMOD, 1025-1028, 2013.
- ConferenceHIL: A High-Level Scripting Language for Entity Integration.
M. Hernández, G. Koutrika, R. Krishnamurthy, L. Popa, R. Wisnesky.
In 16th Int’l Conference on Extending Database Technology, EDBT, 549-560, 2013.
- ConferenceMirror mirror on the Wall, what is the query the fairest of them all?.
G. Koutrika, A. Simitsis.
In 7th Biennial Conference on Innovative Data Systems Research, CIDR, 2013.
- Conference
- ConferenceSurfacing Time-critical Insights from Social Media.
B. Alexe, M. Hernandez, K. Hildrum, R. Krishnamurthy, G. Koutrika, M. Nagarajan H. Roitman, M. Shmueli-Scheuer, I. Stanoi, C. Venkatramani, R. Wagle.
In ACM SIGMOD, 657-660, 2012.
- ConferencePrefDB: Bringing Preferences closer to the DBMS.
A. Arvanitis, G. Koutrika.
In ACM SIGMOD, 665-668, 2012.
- ConferenceTowards Preference-aware Relational Databases.
A. Arvanitis, G. Koutrika.
In 28th Int’l Conference on Data Engineering, ICDE, 426-437, 2012.
- ConferenceOn the selection of tags for tag clouds.
P. Venetis, G. Koutrika, H. Garcia-Molina.
In 4th ACM Int’l. Conference on Web Search and Data Mining, WSDM, 835-844, 2011.
- ConferenceRecsplorer: Recommendation Algorithms based on Precedence Mining.
A. Parameswaran, G. Koutrika, B. Bercovitz, H. Garcia-Molina.
In ACM SIGMOD, 87-98, 2010.
- ConferenceConversational Databases: Explaining Structured Queries to Users.
G. Koutrika, A. Simitsis, Y. Ioannidis.
In 26th Int’l Conference on Data Engineering, ICDE, 333-344, 2010.
- ConferenceFlexRecs: Expressing and Combining Flexible Recommendations.
G. Koutrika, B. Bercovitz, H. Garcia-Molina.
In ACM SIGMOD, 745-758, 2009.
- ConferenceEntity Resolution with Iterative Blocking.
S. Whang, D. Menestrina, G. Koutrika, M. Theobald, H. Garcia-Molina.
In ACM SIGMOD, 219-232, 2009.
- ConferenceCourseRank: A Social System for Course Planning.
B. Bercovitz, F. Kaliszan, G. Koutrika, H. Liou, Z. Mohammadi Zadeh, H. Garcia-Molina.
In ACM SIGMOD, 1107-1110, 2009. Best SIGMOD Demo Award
- ConferenceCourseRank: A Closed-Community Social System through the Magnifying Glass.
G. Koutrika, B. Bercovitz, F. Kaliszan, H. Liou, H. Garcia-Molina.
In 3rd Int'l AAAI Conference on Weblogs and Social Media, ICWSM (best paper nominee), 2009.
- ConferenceData Clouds: Summarizing Keyword Search Results over Structured Data.
G. Koutrika, Z. Mohammadi Zadeh, H. Garcia-Molina.
In 12th Int’l Conference on Extending Database Technology, EDBT, 391-402, 2009.
- ConferenceCourseCloud: Summarizing and Refining Keyword Searches.
G. Koutrika, Z. Mohammadi Zadeh, H. Garcia-Molina.
In 12th Int’l Conference on Extending Database Technology, EDBT, 1132-1135, 2009.
- ConferenceSocial Systems: Can We Do More Than Just Poke Friends?
G. Koutrika, B. Bercovitz, R. Ikeda, F. Kaliszan, H. Liou, Z. Mohammadi Zadeh, H. Garcia-Molina.
In 5th Biennial Conference on Innovative Data Systems Research, CIDR, 2009.
- ConferenceFlexible Recommendations for Course Planning.
G. Koutrika, B. Bercovitz, R. Ikeda, F. Kaliszan, H. Liou, H. Garcia-Molina.
In 25th Int’l Conference on Data Engineering, ICDE, 1467-1470, 2009.
- ConferenceFlexible Recommendations over Rich Data.
G. Koutrika, R. Ikeda, B. Bercovitz, H. Garcia-Molina.
In 2nd ACM Int’l Conference on Recommender Systems, RecSys, 203-210, 2008.
- ConferenceSynthesizing Structured Text from Logical Database Subsets.
A. Simitsis, G. Koutrika, Y. Alexandrakis, and Y. Ioannidis.
In 11th Int’l Conference on Extending Database Technology, EDBT, 428-439, 2008.
- ConferenceCan Social Bookmarks Improve Web Search?
P. Heymann, G. Koutrika, H. Garcia-Molina.
In 1st ACM Int’l. Conference on Web Search and Data Mining WSDM, 195-206, 2008.
- ConferenceGeneralized Précis Queries for Logical Database Subset Creation.
A. Simitsis, G. Koutrika, Y. Ioannidis.
In 23rd Int’l. Conference on Data Engineering, ICDE, 1382-1386, 2007.
- ConferenceEnhanced Search Interface for Information Discovery from Digital Libraries based on Précis Queries.
G. Koutrika, A. Simitsis.
In 10th European Conference on Research and Advanced Technology For Digital Libraries ECDL, 87-98, 2006.
- ConferenceComprehensible Answers to Précis Queries.
A. Simitsis, G. Koutrika.
In 18th Conference on Advanced Information Systems Engineering, CAiSE, 142-156, 2006.
- ConferencePrécis: The Essence of a Query Answer.
G. Koutrika, A. Simitsis, Y. Ioannidis.
In 22nd Int’l Conference on Data Engineering, ICDE, 69-78, 2006.
- ConferenceConstrained Optimalities in Query Personalization.
G. Koutrika, Y. Ioannidis.
In ACM SIGMOD, 73-84, 2005.
- ConferencePersonalized Queries under a Generalized Preference Model.
G. Koutrika, Y. Ioannidis.
In 21st Int’l Conference on Data Engineering, ICDE, 841-852, 2005.
- ConferencePersonalization of Queries in Database systems.
G. Koutrika, Y. Ioannidis.
In 20th Int’l Conference on Data Engineering, ICDE, 597-608, 2004.
- WorkshopExploratory Search in Databases and the Web.
G. Koutrika, L. V. S. Lakshmanan, M. Riedewald, K. Stefanidis.
In ACM 2015, ISBN 978-1-4503-3740-3, 2015.
- WorkshopExploratory Search in Databases and the Web.
G. Koutrika, L. V. S. Lakshmanan, M. Riedewald, K. Stefanidis.
In EDBT/ICDT Workshops, 158-159, 2014.
- WorkshopMulti-Engine Search and Language Translation.
S. Simske. I. M. Boyko, G. Koutrika.
In EDBT/ICDT Workshops, 188-190, 2014.
- WorkshopCoping with the Persistent Coldstart Problem.
S. Bykau, G. Koutrika, Y. Velegrakis.
In PersDB in conj. with VLDB, 2013.
- WorkshopOn Principles of Egocentric Person Search in Social Networks.
S. Cohen, B. Kimelfeld, G. Koutrika and J. Vondrak.
In VLDS in conj. with VLDB, 3-6, 2011.
- WorkshopA Survey of Context-Aware Cross-Digital Library Personalization.
A. Nika, T. Catarci, Y. Ioannidis, A. Katifori, G. Koutrika, N. Manola, A. Nürnberger, M. Thaller.
In AMR (Adaptive Multimedia Retrieval) Workshop, 16-30, 2010.
- WorkshopOLAP Cubes for Social Searches: Standing on the Shoulders of Giants?
K. Morfonios, G. Koutrika.
In WebDB in conj. with SIGMOD, 2008.
- WorkshopQuestioning Yahoo! Answers. Int'l Workshop on Question Answering on the Web,
Z. Gyongyi, G. Koutrika, J. Pedersen, H. Garcia-Molina.
In QAWeb in conj. with WWW, 2008.
- WorkshopCombating Spam in Tagging Systems.
G. Koutrika, F. Effendi, Z. Gyöngyi, P. Heymann, H. García-Molina.
In AIRWEB in conj. with WWW, 2007.
- WorkshopPersonalization of Structured Queries with Personal and Collaborative Preferences.
G. Koutrika.
In Multidisciplinary ECAI Workshop about Advances on Preference Handling, 2006.
- WorkshopPattern-Based Query Answering.
A. Simitsis, G. Koutrika.
In Current Trends in Database Technology - EDBT Workshops, LNCS 4254, March 26-31, 2006. (revised selected papers), 2006.
- WorkshopPattern-Based Query Answering.
A. Simitsis, G. Koutrika.
In 2nd Intl. Workshop on Pattern Representation and Management (PaRMa), in conj. with EDBT, 2006.
- WorkshopA Unified User-Profile Framework for Query Disambiguation and Personalization.
G. Koutrika, Y. Ioannidis.
In New Technologies for Personalized Information Access in conj. with UM, 2005.
- WorkshopPersonalization of Queries Based on User Preferences.
G. Koutrika, Y. Ioannidis.
In Preferences: 2004, Dagstuhl, Germany, 2004.
- MagazineReport on the 2nd Int’l Workshop on Exploratory Search in Databases and the Web (ExploreDB 2015).
G. Koutrika, L. V. S. Lakshmanan, M. Riedewald, Mohamed A. Sharaf, K. Stefanidis.
In ACM SIGMOD Record, 2015.
- MagazineReport on the 1st Int’l Workshop on Exploratory Search in Databases and the Web (ExploreDB).
G. Koutrika, L. V. S. Lakshmanan, M. Riedewald, K. Stefanidis.
In ACM SIGMOD Record 43(2): 49-52, 2014.
- MagazineExtracting, Linking and Integrating Data from Public Sources: A Financial Case Study.
D. Burdick, M. A. Hernández, H. Ho, G. Koutrika, R. Krishnamurthy, L. Popa, I. Stanoi, S. Vaithyanathan, S. R. Das.
In IEEE Data Eng. Bull. 34(3): 60-67, 2011.
- MagazinePersonalized DBMS: an Elephant in Disguise or a Chameleon?
G. Koutrika.
In IEEE Data Eng. Bull. 34(2): 27-34, 2011.
- MagazineGuest editorial: Special issue on collective intelligence.
E. Kapetanios, G. Koutrika.
In Information Sciences, Volume 180, Issue 1, 1-3, 2010.
- MagazineSocial Sites Research Through CourseRank.
B. Bercovitz, F. Kaliszan, G. Koutrika, H. Liou, A. Parameswaran, P. Venetis, Z. Mohammadi Zadeh, H. Garcia-Molina.
In ACM SIGMOD Record, Vol. 38(4), 29-34, 2009.
- MagazineThird Int'l Workshop on ‘Personalized Access, Profile Management, and Context Awareness in Databases’ (PersDB 2009).
S. Amer-Yahia, G. Koutrika.
In ACM SIGMOD Record, Vol. 38(4), 43-45, 2009.
- MagazineFighting Spam on Social Websites: A Survey of Potential Approaches and Future Challenges.
P. Heymann, G. Koutrika, H. Garcia-Molina.
In IEEE Internet Computing, Special Issue on Social Search, 11(6): 36-45, 2007.
- ChapterData Personalization.
G. Koutrika.
In Data Management in Pervasive Systems. Eds: Francesco Colace, Massimo De Santo, Vincenzo Moscato, Antonio Picariello, Fabio A. Schreiber, Letizia Tanca. Springer, 2015.
- ChapterHigh-Level Rules for Integration and Analysis of Data: New Challenges.
B. Alexe, D. Burdick, M. A. Hernández, G. Koutrika, R. Krishnamurthy, L. Popa, I. Stanoi, R. Wisnesky.
In Search of Elegance in the Theory and Practice of Computation, Lecture Notes in Computer Science, 36-55, 2013.
- ChapterPreference-Based Query Personalization.
G. Koutrika, E. Pitoura, K. Stefanidis.
In Advanced Query Processing, B. Catania, L.C. Jain (eds), pages 57-81, Springer, 2013.
- ChapterA Survey on Proximity Measures for Social Networks.
S. Cohen, B. Kimelfeld, G. Koutrika, J. Vondrak.
In Search Computing. Stefano Ceri, Marco Brambilla (Eds), Lecture Notes in Computer Science, Vol 7538, 191-206, Springer, 2012.
- ChapterThe Digital Library Manifesto.
L. Candela, D. Castelli, Y. Ioannidis, G. Koutrika, P. Pagano, S. Ross, H.-J. Schek, H. Schuldt.
In DELOS, ISSN 1818-8044, ISBN 2-912335-24-8, 2006.
- ChapterDatabase Systems: A Personalized Perspective.
G. Koutrika.
In Encyclopedia of Database Technologies and Applications, L. Rivero, J. Doorn, V. Ferraggine Ed(s), Idea Group Inc, 2005.
- TutorialGoals in Social Media, Information Retrieval and Intelligent Agents.
D. Papadimitriou, Y. Velegrakis, G. Koutrika, J. Mylopoulos.
In 31st Int’l Conference on Data Engineering, ICDE, 2015.
- TutorialRepresentation, Composition and Application of Preferences in Databases.
G. Koutrika, K. Stefanidis, E. Pitoura.
In 26th Int’l Conference on Data Engineering, ICDE, 2010.
- TutorialPersonalized Systems: Models and Methods from an IR and DB Perspective.
Y. Ioannidis, G. Koutrika.
In 23rd Intl. Conference on Data Engineering, ICDE., 2007.
- TutorialPersonalized Systems: Models and Methods from an IR and DB Perspective.
Y. Ioannidis, G. Koutrika.
In 31st Intl. Conf. on Very Large Databases, VLDB, 2005.
- TutorialPersonalization: Methods and Models.
Y. Ioannidis, G. Koutrika.
In DELOS Summer School (ISDL) in “User-Centered Design in Digital Libraries”, 2004.
- OtherPreference profile integration in digital library federations, or how to fuse scores with orders
P. Georgiadis, V. Christophides, G. Koutrika, Y. Ioannidis, C. Meghini, N. Spyratos.
In Second DELOS Conference on Digital Libraries, 2007.
- OtherSetting the foundations of Digital Libraries: The DELOS Manifesto.
L. Candela, D. Castelli, Y. Ioannidis, G. Koutrika, P. Pagano, S. Ross, H.-J. Schek, H. Schuldt, C. Thanos.
In D-Lib Magazine 13(3/4)., 2007.
- OtherThe DELOS Digital Library Reference Model.
L. Candela, D. Castelli, N. Ferro, G. Koutrika, C. Meghini, P. Pagano, S. Ross, D. Soergel, M. Agosti, M. Dobreva, V. Katifori, H. Schuldt.
In Foundations for Digital Libraries. ISTI-CNR at Gruppo ALI, Pisa, Italy, 2007.
- OtherHeterogeneity in Digital Libraries: Two Sides of the Same Coin.
G. Koutrika.
In http://www.delos.info/newsletter/issue3/feature2/, Available: 2005.08., 2005.
- Blog
- Blog
- BlogBlog Interview
G. Koutrika.
In Innovation @ HP Labs, 16-Feb-12.
Patents
Georgia holds 4 issued patents and has filed over 20 patent applications in the US and worldwide on topics including user analytics and profiling, personalization, recommender systems, and content understanding with applications including online learning systems, social data applications, automated publishing, and so on.
Professional Activities
Georgia has organized and served in the PC of several international conferences and workshops in various roles. Below there is a partial list of selected professional activities.
- Chair
ACM SIGMOD: 2016 General co-chair
EDBT: 2016 Industrial PC chair
IEEE ICDE: 2016 Workshop and Tutorial co-chair
DBRank: 2013, 2012 PC co-chair
PersDB: 2009, 2008 PC co-chair
NLDB Doctoral Symposium: 2008 PC co-chair
PersDL: 2007 PC co-chair
- Steering
ExploreDB: 2015, 2014
PersDB: 2013, 2012, 2011, 2010
- Editorial
ACM SIGMOD: Present - 2012 Associate Information Director
- PC
ACM SIGMOD: 2015 (Demo), 2014 (Undergrad Research), 2011
PVLDB: 2017, 2015, 2010
ACM KDD: 2016 (Industrial), 2015 (Industrial), 2014 (Industrial), 2013, 2010
WWW: 2014, 2013, 2012, 2011, 2010, 2009, 2008
EDBT: 2015 (Industrial), 2014 (Industrial), 2013, 2012, 2011, 2010, 2009, 2008
IEEE ICDE: 2015, 2013, 2009
IJCAI: 2016 (Special Track on AI and the Web)
ACM CIKM: 2015, 2014
ACM WSDM: 2014, 2013, 2012, 2011, 2010
ACM RecSys: 2013, 2012, 2011, 2010, 2009
ADBIS: 2015, 2014, 2013
SOFSEM: 2016
HP TechCon: 2014
- Journal
TKDE: 2015, 2014, 2013, 2010
TODS: 2012, 2010
VLDB Journal: 2016, 2012
Information Systems: 2010
IEEE Internet Computing: 2012, 2009
Research Summary
Finding the right piece of information for the right person at the right time has been a central concept in Georgia's research. Georgia has worked on modeling user preferences and developing personalization methods over structured and unstructured data that focus query results to users.
On the other hand, recommender systems help users sort out options. Georgia is interested in recommendation approaches that look into novel sources of data in novel ways. Finding ways for defining, executing and optimizing recommendation strategies is also very important.
Enormous amounts of user data are collected in several systems. User data analytics can shed light into many aspects of a system (e.g., its operation and usability), and can help understand its users. Leveraging this knowledge can help build better systems (and more protected against malicious users). Georgia has been working on a variety of systems including an educational platform, course planning tool, community forums, and print applications.
Handling information overload is a war fought on multiple fronts. Georgia is building smart user interfaces over structured data. She has developed keyword search and natural language interfaces (supporting queries and answers in NL), data exploration and summarization methods. One of her recent works involves finding reading orders over document collections.
Georgia's work has been incorporated into commercial products and has been described in patent applications and research publications. She has given several talks and tutorials on these topics.
Interests
- User modeling, personalization
- Recommender systems
- User analytics, social data analytics
- Smart query interfaces, keyword search and summarization, textual answer composition
- Information extraction, entity resolution, information integration
- Smart content selection with structured and unstructured data
- Online learning
- Automated publishing
Selected Research Projects
- Present 2012Senior Research ScientistPrinting and Content Delivery Lab, HP Labs, Palo Alto, USAInventing, developing, and commercializing innovative technologies in user analytics, personalization, and recommendations for applications including print, automated publishing, customer care, and education. Leading teams of developers and researchers in different projects.Systems and tools implemented (technology used: Java, REST, Ajax, JS, jQuery, D3, SQL, JSON, Vertica, MySQL, Mallet, GATE):
- HP METIS
Educational Platform
Leading the development of behavior analysis technologies for online learning, including algorithms for user learning behavior and performance analysis, recommendations as well as analytics dashboards for educators and students. [ IP: 11 patent appl., 1 paper, 2 demos ]
- HP Social Reach
Social Data Analytics
Leading the development of new customer reach technologies for HP Forums, including core analytics to support customer insights applications, analytics dashboards as well as product recognition and post recommendation technologies. [ IP: 2 patent appl. ]
- TopicSelect
Publishing platform
Developed automated content selection technologies that are used for assembling interesting content for printed publications. [ IP: 1 patent appl. ]
- HP Smart Print Insights Tool
Developed a tool for monitoring, visualizing, and providing insights into web print consumption based on web print logs. [ IP: 1 patent ]
- UBeOne
User Analytics Platform
Led the development of a system for analyzing user actions (such as prints and posts), extracting user related facts (e.g., trips, purchases, locations), user sentiment, entities (e.g., products, brands), topics, criticality (e.g., of a review), and so forth. [ IP: 1 patent, 3 patent appl., 1 demo ]
- CLASP
Cloud-based service platform
Developed NLP techniques for automatically generating human readable descriptions of scripts for sharing code as services over the cloud. [ IP: 3 patent appl., 1 demo ]
2012 2010Post-doctoral ResearcherInformation Integration Group, ΙΒΜ Almaden, San Jose, USAWorked on big data technologies for information extraction, entity resolution, integration, and social data analysis.Systems and tools implemented (technology used: Java, JavaCC, IBM AQL, Hadoop, Velocity, JSON):- IBM Accelerator for Big Data
Social Data Analytics
Developed social media processing mechanisms that provide views into customer-facing activities. These include mechanisms for extracting micro-segmentation attributes (e.g., gender, location, parental status, marital status, occupation), interests, and products owned as well as mechanisms for monitoring buzz, sentiment, and intent to buy or start service, and mechanisms for entity resolution across different social media sources. [ IP: 1 demo ]
- HIL
Entity resolution and integration
Designed and built a declarative entity resolution language that enables a programmer to write rules that express the matching and linking of entities. These rules are compiled into optimized runtime code that is executed over Hadoop. [ IP: 1 patent appl., 1 paper, 1 chapter ]
- MIDAS
Financial application
Built entity resolution methods for resolving entities such as companies and people across different documents as part of a complex data processing system that extracts and aggregates facts from a large collection of structured and unstructured documents into a set of unified, clean entities and relationships for financial companies. [ IP: 1 article ]
- Logos
Natural Language for SQL
Co-designed the model and algorithms for a prototype for translating SQL queries and query results into NL descriptions. [ IP: 3 papers, 1 demo, 1 award ]
- PrefDB
Preference-aware DB
Co-designed a preference-aware relational query answering system that transparently and efficiently evaluates queries with preferences. [ IP: 2 papers, 1 demo ]
2009 2006Post-doctoral research fellowComputer Science Dept., Stanford University, USAWorked on data exploration, recommendations, web spam, and entity resolution. Supervised PhD and grad students.Systems and tools implemented (technology used: Java, JavaScript, MySQL):- CourseRank
Social course planning site
Invented and contributed to the implementation of novel recommendation and exploration schemes for finding courses for students to take for the CourseRank project at Stanford. (CourseRank was launched as a startup company in 2010, and then acquired by Chegg. The CourseRank technology is being used at over 500 universities in the United States.) [ IP: 2 papers, 1 article, 1 demo, 1 award ]
- DBClouds
Data exploration
Invented data clouds and supervised their implementation into CourseCloud that was integrated into CourseRank. Data clouds are tag clouds that summarize the results of keyword searches over structured data and enable search refinement. [ IP: 1 paper, 1 demo ]
- FLEXRecs
Recommendations
Invented operators that can be combined with standard relational operators and enable expressing recommendation algorithms as high-level query workflows over relational data and led the implementation of a recommendation engine over an RDBMS. [ IP: 2 papers, 1 demo ]
- SERF
Entity Resolution
Contributed to the design of iterative blocking algorithms that increase the recall of the ER result as part of the SERF project, which involved designing efficient, generic, ER algorithms. [ IP: 1 paper ]
2009 2007Visiting collaboratorHP Labs at Palo Alto, USAWorked on user profiling from user logs for building personalized search and dissemination services.Systems and tools implemented (technology used: Java):- Live Information Management
Online news dissemination
This is a system for the real-time management and distribution of live information feeds.
2006 2000Research engineerDept of Informatics and Telecommunications, Univ. of Athens, GreeceWorked on personalization and data extraction in a number of European-funded and national projects.Systems and tools implemented (technology used: VB, C++, Oracle):- BRICKS
Developed a personalized search module as part of a digital library management system in the context of an EU-funded project for Building Resources for Integrated Cultural Knowledge Services.
- EmfaSys
ETL
Led and contributed to the development of an ETL execution engine, which was transferred to Unixfor S.A. Greece.
- Meta-Volcano
ETL
Supervised and contributed to the design of the requirements specification of an ETL System for Unixfor S.A. Greece.
Contact
Feel free to reach out through email or the social media.
