Deniz Yuret
Associate Professor of Computer Engineering
Koc University
Rumeli Feneri Yolu
34450 Sariyer, Istanbul, Turkey
Tel: +90 (212) 338-1724
Fax: +90 (212) 338-1548
E-Mail: dyuret@ku.edu.tr
Homepage: http://www.denizyuret.com
 
Background Koc University 2002-curr.
Associate Professor of Computer Engineering at Koc University College of Engineering. Served as the director of the Computer Information Technology Department during 2009-2011 and 2013.

InQuira, Inc. 2000-2002
Co-founded InQuira - a company that leverages my patented natural language processing technology to provide human interaction solutions for large enterprises. Served as Chief Scientist and VP of Research and Development. InQuira was acquired by Oracle in 2011.

Ascent Technology, Inc. 1999
Worked as a Development Scientist at Ascent - A company founded by Patrick Winston and other members of the MIT AI Lab to apply the results of advanced research to the solution of complex resource planning, scheduling, allocation, and situation-assessment problems. Developed Java applications for airport resource planning incorporating Queuing Theory.

Massachusetts Institute of Technology
Department of Electrical Engineering and Computer Science
1988-1999

Postdoctoral Research Associate
1999
Worked with Boris Katz and the Infolab Group on the development of the START question answering system.

Doctor of Philosophy in Computer Science
1998
PhD dissertation: Discovery of Linguistic Relations Using Lexical Attraction. Advisors: Patrick Winston, Marvin Minsky, and Boris Katz. Minor in Brain and Cognitive Sciences. Area exam concentration on the Cyc knowledge based system.

Master of Science in Electrical Engineering and Computer Science
1994
Master's thesis on genetic algorithms and optimization. Developed the numerical optimization algorithm Dynamic Hill Climbing .

Bachelor of Science in Electrical Engineering
1992
Bachelor's thesis on genetic algorithms. Research projects in computer vision, digital design and artificial intelligence. Minor in Economics . Worked as an undergraduate research assistant at the AI Lab on genetic algorithms, mobile robotics and machine vision.

Research Natural Language Processing
Current work focused on grounded language acquisition and understanding using deep learning models supported by one Tubitak and one EU project. Previous work includes supervised and unsupervised approaches to syntax, morphology, lexical semantics, language acquisition and machine translation. Developed the Lexical Attraction Theory of linguistic knowledge for my dissertation. The theory attempts to explain how an agent without prior linguistic knowledge can learn to identify linguistic relations using information theoretic measures in example sentences. My program was able to achieve the best unsupervised language learning results published to date. Worked on the START question answering system developed by Boris Katz. Developed Omnibase, an information extraction system that can respond to database queries using arbitrary knowledge sources on the Web.


Machine Learning
Developed Knet.jl, Koc University deep learning framework. Current focus on novel deep learning architectures optimized for learning natural language in a grounded setting.


Numerical Optimization
Studied Genetic Algorithms with Patrick Winston analyzing population diversity and the problem of local optima. The result was the numerical optimization algorithm Dynamic Hill Climbing, which has found practical applications ranging from medical imaging to neural network training, satellite positioning, molecular energy minimization and regression in econometric models.

Computational Economics and Finance
Founded Redfire Capital Management Group with Michael de la Maza in 1995 with the purpose of developing agent-based computational models in economics and finance based on artificial intelligence techniques. The company currently has an active research contract in computational economics. Organized two workshops in 1998: Artificial Life VI Workshop on Agent-based Economics and the First Workshop on Agent-based Modeling of Financial Markets.

Other
Machine Vision: Worked in the machine vision group of Berthold Horn as an undergraduate research assistant developing image processing utilities. Had a short term position in the University of Hawaii to develop X windows utilities for vision research with Shahriar Negahdaripour.
Mobile Robotics: Worked in the mobile robot group of Rodney Brooks designing the TV circuitry for the robot Attila. Attila was a precursor of Sojourner, the robot NASA sent to Mars in 1997.
Computer Chess: Worked with David McAllester developing the ABC-Search chess algorithm. The world champion chess program Socrates used some of our techniques successfully.

Teaching Comp200 Structure and Interpretation of Computer Programs
Comp541 Deep Learning
Comp301 Programming Languages
Engr200 Probability and Statistical Methods for Engineers
Comp131 Introduction to Programming
Comp542 Natural Language Processing
Ecoe554 Machine Learning
Comp341 Artificial Intelligence
Math101 Finite Mathematics
Comp100 Computer Applications
Math102 Calculus

Students Basak Mutlum, M.S. Koc University, 2005
Volkan Kurt, M.S. Koc University, 2005
Bengi Mizrahi, M.S. Koc University, 2006
Ahmet Engin Ural, M.S. Koc University, 2008
Ergun Bicici, Ph.D. Koc University, 2011
Enis Sert, M.S. Koc University, 2013
Mehmet Ali Yatbaz, M.S. 2007, Ph.D. 2014
Emre Unal, M.S. Koc University, 2014
Volkan Cirik, M.S. Koc University, 2014
Osman Baskaya, M.S. Koc University, 2015
Onur Kuru, M.S. Koc Uniersity, 2016

Projects CHIST-ERA (215E201) 2016-2018
Partner in the Chist-Era Project: "Relational symbol grounding using affordance learning".
Tubitak 1001 (114E628) 2016-2018
Researcher in the Tubitak Project: "Learning navigational language from linguistic and visual cues".
Tubitak 1001 (113F092) 2013-2015
Researcher in the Tubitak Project: "A new method for determining critical regions of allosteric proteins based on dynamical analysis of mode coupling".
Tubitak 1001 (112E277) 2013-2015
Principle Investigator in the Tubitak Project: "Natural Language Processing Applications of Unsupervised Word Categorization".
ICT-PSP (270915) 2011-2013
Partner in the European Commision ICT Policy Support Programme Project: "Bologna Translation Service".
Tubitak 1507 (7110376) 2011-2012
Researcher in the Tubitak Project: "Semantic Analysis and Orthographic Normalization in Turkish Legal Informatics".
Tubitak 1001 (108E228) 2009-2012
Principal Investigator in the Tubitak Project: "Word Sense Disambiguation and Semantic Relation Identification Using Statistical Language Models in Natural Language Processing".
Tubitak 1002 (108E257) 2009-2010
Principal Investigator in the Tubitak Project: "The Regression Model for Machine Translation".
Tubitak 1507 (7080848) 2008-2009
Researcher in the Tubitak Project: "Turkish Legal Informatics and Online Legal Search Engine"
Tubitak 1001 (106T553) 2007-2010
Researcher in the Tubitak Project: "Modelling of the Transcriptional Regulatory Network of the Yeast (Saccharomyces Cerevisiae) and Investigation of its Dynamics".

Editorial Computational Linguistics Journal, member of the editorial board. 2009-2011
SemEval3 Semantic Evaluation Exercise, co-organizer. 2010-2012
ACL Semantics Area, co-chair. 2011
Semeval-2010 task 12: Parser evaluation using textual entailments, organizer. 2010
The CoNLL 2007 shared task on dependency parsing, co-organizer. 2007
Semeval-2007 task 04: Classification of semantic relations between nominals, co-organizer. 2007

Invited Talks Knet.jl: Beginning deep learning with 100 lines of Julia. JuliaCon. Berkeley University. June 21, 2017.
Learning to follow navigational instructions. International Symposium on Brain and Cognitive Science. Hacettepe University. April 30, 2017.
The third deep learning revolution. GIF Young Scholars Seminar. Istanbul. June 4, 2017.
Julia ve Knet ile derin ogrenmeye giris. Data Istanbul. December 21, 2016.

Publications Computational Linguistics
Hasim Sak, Dilek Hakkani-Tur, Deniz Yuret and Gokhan Tur. 2017.
Morphological Disambiguation for Turkish. In Studies in Turkish Language Processing. Springer Verlag.
Enis Berk Çoban, Deniz Yuret and Didem Unat. 2017.
Multidimensional Broadcast Operation on the GPU. In 5. Ulusal Yüksek Başarımlı Hesaplama Konferansı, İstanbul, September.
Ömer Kırnap, Berkay Furkan Önder and Deniz Yuret. 2017.
Parsing with Context Embeddings. In Proceedings of the CoNLL 2017 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies, pp 80--87, Vancouver, Canada, August. Association for Computational Linguistics.
Laura Antanas, Ozan Arkan Can, Jesse Davis, Luc De Raedt, Amy Loutfy, Andreas Persson, Alessandro Saffiotti, Emre Ünal, Deniz Yuret and Pedro Zuidberg dos Martires. 2017.
Relational Symbol Grounding through Affordance Learning: An Overview of the ReGround Project. In Grounding Language Understanding (GLU 2017) ISCA Satellite Workshop of Interspeech 2017, August. Stockholm University.
Ozan Arkan Can and Deniz Yuret. 2017.
Learning to Follow Navigational Instructions. In International Symposium on Brain and Cognitive Science (ISBCS), Ankara, April. Hacettepe University. (invited talk).
Onur Kuru, Ozan Arkan Can and Deniz Yuret. 2016.
CharNER: Character-Level Named Entity Recognition. In COLING, December.
Mehmet Ali Yatbaz, Volkan Cirik, Aylin Küntay and Deniz Yuret. 2016.
Learning grammatical categories using paradigmatic representation: Substitute words for language acquisition. In COLING, December.
Xing Shi, Kevin Knight and Deniz Yuret. 2016.
Why Neural Translations are the Right Length. In Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, pp 2278--2282, Austin, Texas, November. Association for Computational Linguistics.
Barret Zoph, Deniz Yuret, Jon May and Kevin Knight. 2016.
Transfer Learning for Low-Resource Neural Machine Translation. In Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, pp 1568--1575, Austin, Texas, November. Association for Computational Linguistics.
Yonatan Bisk, Deniz Yuret and Daniel Marcu. 2016.
Natural Language Communication with Robots. In Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp 751--761, San Diego, California, June. Association for Computational Linguistics.
Ergun Biçici and Deniz Yuret. 2015.
Optimizing Instance Selection for Statistical Machine Translation with Feature Decay Algorithms. IEEE Transactions on Audio, Speech and Language Processing, vol 23, no 2, pp 339--350, February. IEEE.
Mark A. Finlayson, Floris Bex, Pablo Gervas and Deniz Yuret, editors. 2014.
Literary and Linguistic Computing: Special Issue on Computational Models of Narrative, vol 29, no 4, December. Oxford University Press.
Mehmet Ali Yatbaz, Volkan Cirik, Aylin Küntay and Deniz Yuret. 2014.
Paradigmatic representations outperform syntagmatic representations in distributional learning of grammatical categories. In BUCLD, November.
Deniz Yuret, Mehmet Ali Yatbaz and Enis Sert. 2014. Unsupervised
Instance-Based Part of Speech Induction Using Probable Substitutes. In Proceedings of COLING 2014, the 25th International Conference on Computational Linguistics: Technical Papers, pp 2303--2313, Dublin, Ireland, August. Dublin City University and Association for Computational Linguistics.
Volkan Cirik and Deniz Yuret. 2014.
Context-Aware Word Vectors using Substitute Word Distributions. In The LTI Student Research Symposium, August.
Volkan Cirik, Husnu Sensoy and Deniz Yuret. 2014.
Parsing Without Words or POS Tags: Dense Word Vectors Capture Sufficient Syntactic Information. In The LTI Student Research Symposium, August.
Oren Melamud, Ido Dagan, Jacob Goldberger, Idan Szpektor and Deniz Yuret. 2014.
Probabilistic Modeling of Joint-context in Distributional Similarity. In Proceedings of the Eighteenth Conference on Computational Natural Language Learning, pp 181--190, Ann Arbor, Michigan, June. Association for Computational Linguistics.
Mark A. Finlayson, Floris Bex, Pablo Gervás and Deniz Yuret. 2014.
Special Issue: Computational Models of Narrative. Literary and Linguistic Computing, vol 29, no 4, pp 465-466.
Emre Unal and Deniz Yuret. 2013.
A Language Visualization System. In The Second Workshop on Games and NLP (GAMNLP-13), Istanbul, November.
Osman Başkaya, Enis Sert, Volkan Cirik and Deniz Yuret. 2013.
AI-KU: Using Substitute Vectors and Co-Occurrence Modeling For Word Sense Induction and Disambiguation. In Second Joint Conference on Lexical and Computational Semantics (*SEM), Volume 2: Proceedings of the Seventh International Workshop on Semantic Evaluation (SemEval 2013), pp 300--306, Atlanta, Georgia, USA, June. Association for Computational Linguistics.
Deniz Yuret. 2012.
FASTSUBS: An Efficient and Exact Procedure for Finding the Most Likely Lexical Substitutes Based on an N-gram Language Model. Signal Processing Letters, IEEE, vol 19, no 11, pp 725-728, November. IEEE Signal Processing Society.
D. Yuret, L. Rimell, and A. Han (2012)
Parser evaluation using textual entailments. In Language Resources and Evaluation. Vol 47, No 3, pp. 639-659.
E. Bicici and D. Yuret (2011)
RegMT System for Machine Translation, System Combination, and Evaluation. Proceedings of the Sixth Workshop on Statistical Machine Translation. pp. 323-329. Edinburgh, Scotland. July, 2011.
E. Bicici and D. Yuret (2011)
Instance Selection for Machine Translation using Feature Decay Algorithms. Proceedings of the Sixth Workshop on Statistical Machine Translation. pp. 272-283. Edinburgh, Scotland. July, 2011.
M.A. Yatbaz and D. Yuret (2010)
Unsupervised part of speech tagging using unambiguous substitutes from a statistical language model. In Proceedings of the 23rd International Conference on Computational Linguistics (COLING-2010).
D. Yuret, A. Han and Z. Turgut (2010)
SemEval-2010 Task 12: Parser evaluation using textual entailments. In Proceedings of the 5th International Workshop on Semantic Evaluation.
E. Bicici and D. Yuret (2010)
L-1 regularized regression for reranking and system combination in machine translation. In Proceedings of the Joint Fifth Workshop on Statistical Machine Translation and MetricsMATR.
M. A. Yatbaz and D. Yuret (2010)
Preprocessing with Linear Transformations that Maximize the Nearest Neighbor Classification Accuracy. In 1st CSE Student Workshop (CSW'10).
E. Bicici and D. Yuret (2010)
L-1 Regularization for Learning Word Alignments in Sparse Feature Matrices. In 1st CSE Student Workshop (CSW'10).
Deniz Yuret and Mehmet Ali Yatbaz (2009)
The Noisy Channel Model for Unsupervised Word Sense Disambiguation. Computational Linguistics. 36 (1): 111-127, March, 2010.
Mehmet Ali Yatbaz and Deniz Yuret (2009)
Unsupervised morphological disambiguation using statistical language models. In NIPS 2009 Workshop on Grammar Induction, Representation of Language and Language Learning.
Deniz Yuret and Ergun Biçici (2009)
Modeling Morphologically Rich Languages Using Split Words and Unstructured Dependencies. ACL-IJCNLP.
A. Engin Ural, Deniz Yuret, et.al. (2009)
Morphological cues vs. number of nominals in learning verb types in Turkish: Syntactic bootstrapping mechanism revisited. Language and Cognitive Processes. 24 (10): 1393-1405, December, 2009.
Roxana Girju, Deniz Yuret, et.al. (2009)
Classification of Semantic Relations between Nominals. Language Resources and Evaluation. 43 (2): 105-121, June, 2009.
Deniz Yuret, A. Engin Ural, et.al. (2008)
Morphological cues vs. number of nominals in learning verb types from child-directed speech. In Boston University Conference on Language Development (BUCLD33)
Deniz Yuret, Mehmet Ali Yatbaz and Ahmet Engin Ural (2008)
Discriminative vs. Generative Approaches in Semantic Role Labeling. In Conference on Computational Natural Language Learning (CoNLL).
Deniz Yuret (2008)
Smoothing a tera-word language model. In ACL-2008.
Roxana Girju, Deniz Yuret, et.al. (2007)
SemEval-2007 Task 04: Classification of Semantic Relations between Nominals. In SemEval-2007: 4th International Workshop on Semantic Evaluations.
Deniz Yuret (2007)
KU: Word Sense Disambiguation by Substitution. In SemEval-2007: 4th International Workshop on Semantic Evaluations
Joakim Nivre, Deniz Yuret, et.al. (2007)
The CoNLL 2007 Shared Task on Dependency Parsing. In EMNLPP-CoNLL 07
Deniz Yuret (2006)
Dependency Parsing as a Classification Problem. In Proceedings of the Tenth Conference on Computational Natural Language Learning (CoNLL-X)
Deniz Yuret and Ferhan Türe (2006)
Learning Morphological Disambiguation Rules for Turkish. In HLT-NAACL 06
Ergun Biçici and Deniz Yuret (2006)
Clustering Word Pairs to Answer Analogy Questions. In Proceedings of the Fifteenth Turkish Symposium on Artificial Intelligence and Neural Networks (TAINN 2006).
Deniz Yuret (2004)
Some Experiments with a Naive Bayes WSD System. ACL 2004 Senseval-3 Workshop July 2004, Barcelona, Spain.
Boris Katz, Sue Felshin, Deniz Yuret, et al. (2002)
Omnibase: Uniform access to heterogeneous data for question answering. Lecture Notes in Computer Science 2553: 230-234 Springer-Verlag.
Boris Katz, Deniz Yuret, et al. (1999)
Integrating Large Lexicons and Web Resources into a Natural Language Query System. Proceedings of the IEEE International Conference on Multimedia Computing and Systems.
Özlem Uzuner, Boris Katz, Deniz Yuret (1999)
Word sense disambiguation for information retrieval. In Proceedings of the 1999 16th National Conference on Artificial Intelligence (AAAI-99)
Deniz Yuret (1998)
Discovery of Linguistic Relations Using Lexical Attraction, PhD thesis, MIT.
Boris Katz, Deniz Yuret, et al. (1998)
Blitz: A Preprocessor for Detecting Context-Independent Linguistic Structures. In Proceedings of the 5th Pacific Rim International Conference on Artificial Intelligence.
Machine Learning
Saman Zia, Yücel Yemez and Deniz Yuret. 2017.
RGB-D Object Recognition Using Deep Convolutional Neural Networks. In 28th British Machine Vision Conference, September.
Barış Bozkurt, Ozan Baysal and Deniz Yuret. 2017.
A Dataset and Baseline System for Singing Voice Assessment. In The 13th International Symposium on Computer Music Multidisciplinary Research (CMMR), September.
Deniz Yuret. 2016.
Knet: beginning deep learning with 100 lines of Julia. In Machine Learning Systems Workshop at NIPS 2016, December.
Ergun Biçici and Deniz Yuret (2007)
Locally Scaled Density Based Clustering. In ICANNGA 2007, Part I, LNCS 4431, Springer-Verlag.
Deniz Yuret and Michael de la Maza (2006)
The Greedy Prepend Algorithm for Decision List Induction. In ISCIS 2006, LNCS 4263, Springer-Verlag.
Computational Biology
Onur Varol, Deniz Yuret, Burak Erman and Alkan Kabakcioglu. 2015.
Functionally Important Residues from Mode Coupling during Short-Time Protein Dynamics. Biophysical Journal, vol 108, no 2, pp 377a. Elsevier.
Alkan Kabakcioglu, Onur Varol, Deniz Yuret and Burak Erman. 2015.
Functionally important residues from mode coupling during short-time protein dynamics. In APS Meeting Abstracts, vol 1, pp 48009. [ai.ku] google scholar
Onur Varol, Deniz Yuret, Burak Erman and Alkan Kabakçıoğlu. 2014.
Mode coupling points to functionally important residues in myosin II. Proteins: Structure, Function, and Bioinformatics, vol 82, no 9, pp 1777--1786, September.
A. Kabakcioglu, D. Yuret, M. Gur and B. Erman (2010)
Anharmonicity, mode-coupling and entropy in a fluctuating native protein. Physical Biology 7 046005, October, 2010.
Ersin Yurtsever, Deniz Yuret and Burak Erman (2006)
Quantum Mechanical Calculations of Tryptophan and Comparison with Conformations in Native Proteins. J. Phys. Chem. A. 110 (51): 13933-13938, December, 2006.
Özlem Keskin, Deniz Yuret, et al. (2004)
Relationships between amino acid sequence and backbone torsion angle preferences. Proteins: Structure, Function and Bioinformatics 55 (4): 992-998, June 1, 2004.
Numerical Optimization
Michael de la Maza and Deniz Yuret (1995)
Seeing clearly: Medical imaging now and tomorrow. In Clifford A. Pickover, editor, Future Health: Computers and Medicine in the 21st Century. St. Martin's Press.
Deniz Yuret (1994)
From genetic algorithms to efficient optimization. Technical Report 1569, MIT AI Laboratory.
Michael de la Maza and Deniz Yuret (1994)
Dynamic hill climbing. AI Expert.
Deniz Yuret and Michael de la Maza (1993)
Dynamic hill climbing: Overcoming the limitations of optimization techniques. In The Second Turkish Symposium on Artificial Intelligence and Neural Networks.
Computational Economics and Finance
Ayla Oğuş, Michael de la Maza, and Deniz Yuret (1999)
Modeling the Economics of Internet Companies. Computing in Economics and Finance, Proceedings of the Fifth International Conference of the Society for Computational Economics.
Michael de la Maza, Ayla Oğuş, and Deniz Yuret (1998)
How do firms transition between monopoly and competitive behavior? An Agent-based Economic Model. In Proceedings of the Sixth International Conference on Artificial Life.
Michael de la Maza and Deniz Yuret (1995)
A model of stock market participants. In Jörg Biethahn and Volker Nissen, editors, Evolutionary Algorithms in Management Applications. Springer.
Michael de la Maza and Deniz Yuret (1995)
Neural network applications: A critique. The Magazine of Artificial Intelligence in Finance, 2(1).
Michael de la Maza and Deniz Yuret (1994)
A futures market simulation with non-rational participants. In Rodney A. Brooks and Pattie Maes, editors, Proceedings of the Fourth International Workshop on the Synthesis and Simulation of Living Systems.
Deniz Yuret and Michael de la Maza (1994)
A genetic algorithm system for predicting the OEX. Technical Analysis of Stocks & Commodities.
Michael de la Maza and Deniz Yuret (1994)
Experimenting with a market simulation. The Magazine of Artificial Intelligence in Finance, 1(3).
Game Theory
David McAllester and Deniz Yuret (2002)
Alpha-beta-conspiracy search. ICGA Journal, Vol. 25, No. 1, pp. 16--35
Deniz Yuret (1994)
The principle of pressure in chess. In The Third Turkish Symposium on Artificial Intelligence and Neural Networks.

Patents
Deniz Yuret, et al. (2013)
Ontology for use with a system, method, and computer readable medium for retrieving information and response to a query. United States Patents 8,612,208 and 9,747,390. December 17, 2013.
Deniz Yuret (2005)
Method of utilizing implicit references to answer a query. United States Patent 6,957,213 October 18, 2005.

Academic
Honors
Perfect 800 scores in GRE quantitative and analytical exams. 1992
Top 100, Putnam mathematics competition, MIT team member. 1989
Bronze medal, 29th International Mathematical Olympiad. 1988
Perfect 800 scores in CBAT math and physics. 1988
Top 50 out of 600,000, Turkish National University Exam. 1988
1st place out of 200,000, Science High School Exam. 1985
1st place in Tübitak math competitions. 1985, 1988

References Patrick Winston, Ford Professor of Artificial Intelligence and Computer Science, former director of the MIT Artificial Intelligence Laboratory. Address: MIT Stata Center, 32-251, Cambridge, MA 02139, USA. Telephone: 1-617-253-6754. Email: phw@csail.mit.edu.

Boris Katz, Principal Research Scientist at the MIT Computer Science and Artificial Intelligence Laboratory and head of the Laboratory's InfoLab Group. Address: Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, The Stata Center, 32-G430, 32 Vassar Street, Cambridge, MA 02139. Email: boris@mit.edu.

Kevin Knight, Research Director and Fellow, Information Sciences Institute (ISI). Professor in the Department of Computer Science of the University of Southern California. Address: USC/Information Sciences Institute, 4676 Admiralty Way, Marina del Rey, CA 90292, e-mail: knight@isi.edu.