Ozgur Yilmazel, Ph.D.
Center for Natural Language Processing
Syracuse University
335 Hinds Hall
Syracuse, New York 13244-4100
e-mail: oyilmaz@syr.edu

EDUCATION:


Syracuse University Electrical Engineering Ph.D. 2006
Dissertation Topic: "Empirical Selection of NLP-Driven Document Representations for Text Categorization."
Advisors: Dr. Can Isik, Dr. Elizabeth Liddy

Syracuse University Electrical Engineering M.Sc. 2002
GPA: 4.00 "How search engines really work ?"

Osmangazi University Electrical Engineering B.Sc. 1996

PROFESSIONAL EXPERIENCE:
Appointments:

2007- present Assistant Research Professor, School of Information Studies, Syracuse University

1999- present Chief Software Engineer, Center for Natural Language Processing, Syracuse University

Lead a team of software engineers in various government and commercial projects, in order to build natural language processing (NLP) based information access solutions for clients. Lead the design and implementation of a rule based NLP Information Extraction system, TextTagger™, that many of CNLP's applications depend on. Designed and lead development on various Question Answering, Information Retrieval and Visualization Systems.
Implemented software development processes that lead the CNLP to turn research into technology products. Participated in writing grant proposals to government and commercial entities.
Oversaw and reviewed technical activities conducted by engineers. Technical writing for internal and external software process documentation. Technical interaction with clients.

Recent Projects:
•  Designed and lead development on eQuery Information Extraction, Information access system.
•  Designed and developed LiVIA (Linguistic and Visual Information Access) 2-stage information retrieval system with Natural Language query interface, and visual summarization of results. (livia.equery.org)
•  Designed and lead development on Question Answering Module for a toolkit to provide CRM solutions for Fortune-500 companies.
•  Designed and lead development KAAS: Question Answering system used by Engineering students on collaborative projects.

1998-1999  Software Engineer, Syracuse Language Systems, Syracuse, NY

Designed and implemented a distance learning infrastructure in a team of engineers. Focused on the networking and data storage aspects while investigating emerging protocols/ specifications like IMS. Worked on design of multi-tier course delivery architecture for language instruction. Implemented Data Services Tier using Oracle database and Rogue Wave Libraries in C++.

1996-1997  Research Assistant, Department of Computer Engineering, Osmangazi University, Eskisehir, Turkey

Worked on image processing projects both on Unix and MS Windows 95 systems using C++. Used X-windows for Unix platform. Taught courses on programming and Advanced Mathematics.

1993-1995 Systems Engineer, Mikrokom Computer Company, Istanbul, Turkey

Analyzed and designed installation of LAN's in three hospitals and two supermarket chains. Installed WAN technology for some supermarket chains. Implemented specific software applications for system and network management on multi platform networks.

1993-1995 Software Engineer, Computer Aided Education Unit of Anadolu University, Eskisehir, Turkey

Worked as a programmer, on a part of a big project that focused on Distant Education. Wrote programs and made decisions in order to meet the goals of an online university supported by the government. Wrote utilities for the product like Toolbox, Help and Functional calculator, which eliminates chopping errors. Implemented security features like restricting access to the operating system from the clients. Worked on Speech Recognition Systems for students with hearing problems.

COMPUTING SKILLS:

PUBLICATIONS:
Yilmazel, Ozgur (2008) NLP-Driven Document Representations for Text Categorization,VDM Verlag Dr. Mueller e.K. ISBN: 3836488418

Diekema, Anne R., Yilmazel, Ozgur, Bailey, Jennifer, Harwell, Sarah C.,Liddy, Elizabeth D. Standards Alignment for Metadata Assignment. Proceedings of the 7th ACM/IEEE Joint Conference on Digital Libraries. Vancouver, British Columbia, Canada, June 18-23, 2007. pp. 398-399.

Ingersoll, G.I, Yilmazel, O. Liddy, E.D. (2006) Finding Questions, 2007 IEEE 23rd International Conference on Data Engineering,ICDE'07, Istanbul.

Yilmazel, O., Balasubramanian, N., Harwell , S.C. , Bailey, J., Diekema, A.R., Liddy, E.D., (2006) Text Categorization for Aligning Educational Standards. To appear in the Proceedings of the HICSS 2007, Hawaii .

McCracken , N.J. , Diekema, A.R., Ingersoll, G., Harwell , S.C. , Allen, E.E., Yilmazel, O., Liddy, E.D. Modeling Reference Interviews as a Basis for Improving Automatic QA Systems. In Proceedings of HLT-NAACL 2006 Workshop on Interactive Question Answering, New York City , NY

Yilmazel, O., Symonenko, S., Balasubramanian, N., Liddy, E.D. (2006) Leveraging One-class SVM in Semantic Analysis for Anamalous Content Detection. To appear in Reid, E. (Ed) Terrorism Infomatics

Elizabeth D. Liddy , Jiangping Chen, Christina M. Finneran , Anne R. Diekema , Sarah C. Harwell, Ozgur Yilmazel . A Retrospective on Generating & Evaluating Automatic Metadata for Educational Resources: A Holistic Program (poster). 9th European Conference on Research and Advanced Technology for Digital Libraries (ECDL 2005) September 18-23, 2005 Vienna , Austria .

Yilmazel, O. Symonenko, S., Balasubramanian, N., Liddy, E.D. (2005). Leveraging One-Class SVM and Semantic Analysis to Detect Anomalous Content. ISI 2005 381-388

Yilmazel, O. Symonenko, S., Balasubramanian, N., Liddy, E.D. (2005).Improved Document Representation for Classification Tasks for the Intelligence Community. In the Proceedings of the 2005 AAAI Spring Symposium Series.

Liddy, E.D., Diekema, A.R., & Yilmazel, O. (2004). Context-Based Question-Answering Evaluation. In Proceedings of the 27th Annual ACM-SIGIR Conference. Sheffield, England.

Diekema, A.R., Yilmazel, O., & Liddy, E.D. (2004). Evaluation of Restricted Domain Question-Answering Systems. In Proceedings of EACL Workshop on Question Answering in Restricted Domains. Barcelona, Spain.

Yilmazel, O., Finneran, C.M. & Liddy, E.D. (2004). MetaExtract: An NLP System to Automatically Assign Metadata. Proceedings of the 2004 Joint Conference on Digital Libraries .

Symonenko, S., Liddy, E.D., Yilmazel, O., DelZoppo, R., Brown, E. & Downey, M. (2004). Semantic Analysis for Monitoring Insider Threats. In Proceedings of 2 nd Symposium on Intelligence and Security Informatics . Tucson, Arizona.

Liddy, E.D., Diekema, A.R., Yilmazel, O., Chen, J., Harwell, S., and He, L. (2003). Finding Answers to Complex Questions. In Maybury, M. (Ed.) New Directions in Question Answering . AAAI-MIT Press.

A. R. Diekema, O. Yilmazel, J. Chen, S. Harwell, L. He, E.D. Liddy,. (2003) What Do You Mean? Finding Answers to Complex Questions. Presented at AAAI Spring Symposium: New Directions in Question Answering. Palo Alto, California. 2003

A. R. Diekemia, J. Chen,N. McCracken, O. Yilmazel,E.D. Liddy, (2002). Question answering: CNLP at the TREC-11 question answering track. Notebook of 11th Text REtrieval Conference.

J. Chen, A.R. Diekemia, O. Yilmazel, E.D. Liddy, (2002). Automatic question and answering in aerospace domain. Presented at the 4th International VRD Conference, Chicago, Illinois, November 2002.

E.D. Liddy, E. Allen, S. Harwell, S. Corieri, O. Yilmazel, N. Ozgencil, A. Diekema, N. McCracken, J. Silverstein, S.A. Sutton. Automatic metadata generation & evaluation SIGIR 2002 401-402.

Chen, J., A.R. Diekema, M.D. Taffett, N. McCracken, N. Ozgencil, O. Yilmazel, E.D. Liddy. Question Answering: CNLP at the TREC-10 Question Answering Track. In: Notebook of the Tenth Text Retrieval Conference (TREC-10) . E.M. Voorhees and D.K. Harman (Eds.). Gaithersburg, MD: Department of Commerce, National Institute of Standards and Technology, 2001.

A.R. Diekema, X. Liu, H. Wang, N. McCracken, O. Yilmazel, and E.D. Liddy, Question Answering: CNLP at the TREC-9 Question Answering Track. In: Notebook of the Ninth Text Retrieval Conference (TREC-9) . E.M. Voorhees and D.K. Harman (Eds.). Gaithersburg, MD: Department of Commerce, National Institute of Standards and Technology, 1999.

CURRENT RESEARCH INTERESTS:
•  Open source Information Retrieval - Lucene
•  Evidence Extraction
•  Machine Learning
•  Information Visualization Technologies
•  Text Classification using Natural Language features

GRANTS RECEIVED:
2006-2007 Software Engineering Leader, Understanding the Connotative Meaning of Text. Disruptive Technologies Office.

2006-2009 Project Leader, Improving Public Health Grey Literature Access for the Public Health Workforce. National Institute of Medicine.

2005-2006 Project Leader, Phase III LiVIA (Linguistic and Visual Information Access) System, Syracuse Research Corporation

2003-2006 Project Leader . Revolutionary Learning Environment. NASA.

2004-2005 Project Leader, Intelligent Information Retrieval and Extraction using Natural Language Processing Phase - II. Syracuse Research Corp.


2003-2005 Software Engineering Leader, Question Answering capability for intelligent customer relations toolkit. MySentient, Boulder, Co.

2002-2004     Project Leader, MetaTest. NSF. National Science Digital Library Project.

2002-2003 Project Leader, Intelligent Information Retrieval and Extraction using Natural Language Processing. Syracuse Research Corp.

2001-2004  Project Leader, Advanced Capabilities for Evidence Extraction. DARPA.

2001-2003 Software Engineering Leader, Standard Connection: Mapping Educational Objects to Content Standards. NSF-NSDL.

2000-2002 Software Engineering Leader, Breaking the Metadata Generation Bottleneck. NSF-NSDL

2000-2001 Project Leader, Revolutionary Learning Environment. NASA

2000-2001 Software Engineer, Scouting Study of Natural Language Processing for Unilever Corporation.

2000 Software Engineer, Information Retrieval & Information Extraction. BabbleArt.

1999-2000  Project Leader eQuery. In-Q-Tel

1999-2001 Software Engineer/Researcher, Seedling Project for Evidence Extraction and Link Discovery. DARPA.

OPEN SOURCE PROJECTS PARTICIPATED

Lucene: open source information retrieval library
Zemberek: Platform independent text processing library for Turkish. C
Weka: Machine learning platform and library
LibSVM:support vector machines implemented in java, also supports one-class classification
myObjects: object relational mapping for php


TRAINING AND CERTIFICATIONS:

i2 The Analyst's Notebook 6 Workshop, Washington D.C. March 2003
Visual Basic . NET , ACM Syracuse,NY April 2003

HONORS AND AWARDS:
Phi Beta Delta - Honor Society for international scholars