CURRICULUM VITAE
FERHAN TURE
A.V. Williams Building #3126
Address
Department of Computer Science, University of Maryland
College Park MD 20742
+1-301-***-**-** (Office)
Tel
*****@**.***.***
http://www.cs.umd.edu/~fture
Web
EDUCATION
Ph.D., Computer Science, University of Maryland at College Park, 2008 Present.
Advisor: Jimmy Lin
M.Sc., Computer Science, Sabanci University, 2006 2008.
Thesis: A Hybrid Machine Translation System from Turkish to English.
Advisor: Kemal Oflazer
B.Sc., Computer Engineering, KoC University, 2006.
Graduation Project: A Learning-based Turkish Morphological Disambiguation System.
Advisor: Deniz Yuret
B.Sc., Mathematics, KoC University, 2006.
RESEARCH INTERESTS
Cross-Lingual Information Retrieval, Machine Translation, Large-scale Text Processing.
PUBLICATIONS
Refereed Conference Papers
5.
Esra Erdem, Ozan Erdem, and Ferhan Ture. HAPLO-ASP: Haplotype Inference
using Answer Set Programming. To appear in Proceedings of 10th International
Conference on Logic Programming and Nonmonotonic Reasoning (LPNMR 09),
2009.
4. Elvin Coban, Esra Erdem, and Ferhan Ture. Comparing ASP, CP, ILP on two
Challenging Applications: Wire Routing and Haplotype Inference. In Proceedings
of the Second International Workshop on Logic and Search (LaSh 2008), 2008.
3. Esra Erdem and Ferhan Ture. Efficient Haplotype Inference with Answer Set
Programming. In Proceedings of the Twenty-Third AAAI Conference on Artificial
Intelligence (AAAI-08), pages 436-441, 2008.
2. Merve Cayli, Ayse GUl Karatop, Emrah Kavlak, Hakan Kaynar, Ferhan Ture, and Esra
Erdem. Solving Challenging Grid Puzzles with Answer Set Programming. In
Proceedings of the Fourth International Workshop on Answer Set Programming
(ASP 07), pages 175-190, 2007.
1. Deniz Yuret and Ferhan Ture. Learning Morphological Disambiguation Rules for
Tu rkish . In Proceedings of the Human Language Technology Conference - North
American chapter of the Association for Computational Linguistics (HLT-NAACL
2006), pages 328-334, 2006.
Other
Tamer Elsayed, Ferhan Ture, and Jimmy Lin. Brute-Force Approaches to Batch
Retrieval: Scalable Indexing with MapReduce, or Why Bother? Technical Report
HCIL-2010-23, University of Maryland at College Park, October 2010.
Ferhan Ture. A Hybrid Machine Translation System from Turkish to English.
Masters Thesis, Sabanci University, Turkey, July 2008.
Esra Erdem and Ferhan Ture. Efficient Haplotype Inference with Answer Set
Programming. Presented at the International Symposium on Health Informatics and
Bioinformatics (HIBIT 08), Sabanci University, Turkey, May 2008.
RECENT PROJECTS2011-Present
Using Translation Models to Improve CLIR
Joint work with Jimmy Lin and Doug Oard.
Translation models can provide better translations for the task of CLIR by using larger
translation units (e.g. phrases) and wider context. We explore ways that a translation
grammar
and decoder can improve effectiveness and efficiency of CLIR systems.
2
2010-Present
Exploring Discourse-level Features in MT Systems
Joint work with Doug Oard and Philip Resnik.
We explore collection and document-level features to improve the quality of Machine
Translation systems. The idea that phrases are translated in a single way throughout a
document is the equivalent of the one-sense-per-discourse heuristic in the context of the
Word
Sense Disambiguation problem. Our approach takes advantage of discourse-level statistics
to
score translation units in a way that encourages consistent translations.
2009-Present
Cross-Lingual Pairwise Similarity Computation in Large Collections of Documents
Joint work with Jimmy Lin and Tamer Elsayed.
Pairwise similarity is the task of finding similar pairs of documents in a large
collection
efficiently. We can extend this to cross-lingual domains such as Wikipedia, to detect
similar
documents written in different languages. We explore an approach based on locality-
sensitive
hashing and show its scalability and effectiveness on German and English Wikipedia
datasets.
2009-2010
Parallel Conditional Random Field (CRF) Training for Machine Translation Systems
Joint work with Chris Dyer, Jimmy Lin, and Philip Resnik.
Our goal is to parallelize CRF training, a discriminative, supervised learning method
that has
many advantages over generative approaches. The feature set that can be used in a CRF
model is very flexible and it can be trained using an EM-like approach. Scalability of
CRF
models is necessary in MT applications, which is the motivation to parallelize the
process
with MapReduce.
2009-2010
Scalable Indexing Approaches using MapReduce
Joint work with Tamer Elsayed and Jimmy Lin.
We explore how MapReduce cluster-based environments may change the traditional IR
workflow: First create an inverted index, then perform retrieval. We introduce a brute
force
approach that performs retrieval directly from documents, and compare its performance and
scalability to indexed IR algorithms.
TEACHING
? University of Maryland
o
Programming Language Technologies Undergraduate-level
and Paradigms
o
Object-oriented Programming I Undergraduate-level
3
? Sabanci University
o
Artificial Intelligence Undergraduate-level
o
Logic in Computer Science Graduate-level
o
Introduction to Probability and Statistics Undergraduate-level
? KoC University
o
Numerical Methods Undergraduate-level
o
Structure & Interpretation of Computer Programs Undergraduate-level
WORK EXPERIENCE
?
Research Intern at IBM T. J. Watson Research Center, Data Analytics Group, Yorktown
Heights, NY.
Mentor:
Amol Ghoting
Manager: Edwin Pednault
From June 6 until August 27, 2010
Intern at Yapi Kredi Insurance, R&D Department, Istanbul Turkey.
Manager: Burak Sayin
From August 15 until September 9, 2005
Intern at Avrupa Software, Istanbul Turkey.
Manager: Murat TUre
From August 16 until September 10, 2004.
PROFESSIONAL ACTIVITIES
?
ACCOMPLISHMENTS
? University of Maryland Graduate Assistantship, 2008-2013.
? University of Maryland Graduate Fellowship, 2008-2010.
? Sabanci University Graduate Fellowship, 2006-2008.
? KoC University Full Scholarship for Undergraduate Education, 2002-2006.
? KoC University Vehbi KoC Scholar Award (SPA > 3.70/4.0) in Spring 2003, Fall 2004
? TUBITAK (Scientific and Technological Research Council of Turkey) Graduate
Scholarship.
th
? Ranked 348 among 105,505 in Postgraduate Education Entrance Exam (LES), 2005.
4
SKILLS
Languages Turkish (Native), English (Advanced)Programming Tools Java, MapReduce/Hadoop, Perl, Python, C/C++, SQL, Matlab, Lparse,
MIT Scheme (Lisp), Lex-Yacc, OPL, Fortran.
Operating Systems Windows, Unix-based.
Software MS Office, 2D Autocad.References are available on request.
5