I/P Engine, Inc. v. AOL, Inc. et al

Filing 336

Memorandum in Support re 335 MOTION in Limine Plaintiff I/P Engine, Inc.'s Third Motion in Limine to Exclude Improper Prior Art Evidence filed by I/P Engine, Inc.. (Attachments: # 1 Exhibit 1, # 2 Exhibit 2, # 3 Exhibit 3, # 4 Exhibit 4, # 5 Exhibit 5, # 6 Exhibit 6, # 7 Proposed Order)(Sherwood, Jeffrey)

Exhibit 2 

UNITED STATES DISTRICT COURT
EASTERN DISTRICT OF VIRGINIA
NORFOLK DIVISION
I/P ENGINE, INC.
Plaintiff,

Civil Action No. 2:11-cv-512

v.
AOL, INC., et al.,
Defendants.

DEFENDANTS’ IDENTIFICATION OF EXPERT WITNESSES
Defendants AOL, Inc., Google Inc., IAC Search & Media, Inc., Target Corp., and
Gannett Co., Inc. (collectively “Defendants”), by counsel, provide the following list of expert
witnesses:
1. Lyle Ungar, Ph.D.
Address:

Occupation:
Field of Expertise:

Computer & Information Science Department
University of Pennsylvania
504 Levine, 200 S. 33rd St., Philadelphia, PA 19104-6309
Professor
Computer science, information retrieval and filtering, and text
mining.

Dr. Ungar may testify about the background of search engines, content-based filtering,
and collaborative filtering. Dr. Ungar may additionally testify about the level of ordinary skill in
the field of the Asserted Patents, the knowledge possessed by a person of ordinary skill in this
field, the prior art to the Asserted Patents, the invalidity of the Asserted Patents based on the
prior art, and the invalidity of the Asserted Patents based on indefiniteness, lack of enablement,
and/or lack of written description. Dr. Ungar’s CV is attached hereto as Exhibit A.

01980.51928/4815334.1

Dated: June 18, 2012

By: /s/ David A. Perlson
David A. Perlson
QUINN EMANUEL URQUHART &
SULLIVAN LLP
50 California Street, 22nd Floor
San Francisco, CA 94111
Telephone: [phone]
Facsimile: [phone]
By: /s/ Stephen E. Noona
Stephen E. Noona
KAUFMAN & CANOLES, P.C.
150 West Main Street
Post Office Box 3037
Norfolk, VA 23514
Telephone: [phone]
Facsimile: [phone]
Counsel for Defendants GOOGLE INC., IAC
SEARCH & MEDIA, INC., TARGET CORP., and
GANNETT COMPANY, INC.

By: /s/ Robert L. Burns
Robert L. Burns
FINNEGAN, HENDERSON, FARABOW,
GARRETT & DUNNER, LLP
Two Freedom Square
11955 Freedom Drive
Reston, VA 20190
Telephone: [phone]
Facsimile: [phone]
By: /s/ Cortney S. Alexander
Cortney S. Alexander
FINNEGAN, HENDERSON, FARABOW,
GARRETT & DUNNER, LLP
3500 SunTrust Plaza
303 Peachtree Street, NE
Atlanta, GA 94111
Telephone: [phone]
Facsimile: [phone]
Counsel for Defendant AOL, INC.

01980.51928/4815334.1

2

EXHIBIT A

Lyle H. Ungar
Dept. of Computer and Information Science
University of Pennsylvania
200 S. 33rd St., Philadelphia, PA 19104-6389
[e-mail]
[phone]
FAX: [phone]
http://www.cis.upenn.edu/∼ungar

Education
1979-84

Massachusetts Institute of Technology
PhD in Chemical Engineering

Boston, MA

1975-79

Stanford University
BS in Chemical Engineering (with distinction).

Stanford, CA

Experience
1990-2012

University of Pennsylvania
Philadelphia, PA
Associate Professor of Computer and Information Science
Associate Professor of Chemical and Biomolecular Engineering
Associate Professor of Bioengineering (2010-12)
Associate Professor of Electrical and Systems Engineering (1996-2012)
Associate Professor of Operations and Information Management, Wharton (2000-12)
Associate Professor of Genomics and Computational Biology, SOM (2002-12)

2007
1999

Google (on leave)
CMU (sabbatical)

1984-90

University of Pennsylvania
Philadelphia, PA
Assistant Professor of Chemical Engineering
Assistant Professor of Computer and Information Science (1987–90)

1982
(summer)

Boston Consulting Group
Associate: Strategic business analysis.

1979
(summer)

Shell Oil, Westhollow Research Center
Houston, TX
Engineer: Developed computer model for catalytic cracking plant.

1976-78
(summers)

Chevron USA, Richmond Refinery
Design Engineer (three summer co-op program).

New York, NY
Pittsburgh, PA

Awards
• Presidential Young Investigator
• National Science Foundation (NSF) Graduate Fellow
• F.E. Terman Award
1

Boston, MA

Richmond, CA

Research interests
Machine Learning and Database Mining
• Methods: machine learning, data mining, text mining
• Applications: information extraction, recommender systems, computational biology

Recent Administration at Penn
• Assoc. Director of the Penn Center for Bioinformatics (PCBI) (2004-12)
• Executive Committee, Genomics and Computational Biology (2002-8)
• Admissions Committee, Genomics and Computational Biology (2002-4)
• Director, Executive Masters in Technology Management (EMTM), SEAS and Wharton (1996-2004)
• Director, CIS Graduate Admissions (2000-2)

Public Service
Conferences Chaired
• International Conference on Knowledge Discovery and Data Mining (ACM SIG-KDD), 2006.
• Gordon Research Conference on Statistics in Chemistry and Chemical Engineering, 1997.
Associate Editor
• Journal of Machine Learning Research
Program committees served on (last three years only)
• American Association for Artificial Intelligence (AAAI)
• ACM Knowledge Discovery and Data Mining (KDD)
• World Wide Web (WWW)
• IEEE International Conference on Data Mining (ICDM)
• International Conference on Machine Learning (ICML)
• SIAM International Conference on Data Mining (ICDM)

Courses taught
Undergraduate
ChE 231
ChE 350
CIS 140/
CSE 120
CSE/ChE 270
CSE 391
EAS 410
Graduate
ChE 500

Thermodynamics
Fluid Mechanics
Cognitive Science
Programming Languages and Techniques
Expert Systems
Artificial Intelligence
Model Building with Modern Statistics
Applied Mathematics I
2

ChE 501
ChE 640
ChE 641
ChE 700
CIS 520
CIS/GCB 535
CIS 620
CIS 700
EMTM 554
EMTM 605
MGMT 560
MGMT 732

Applied Mathematics II
Fluid Dynamics
Heat and Mass Transfer
Bifurcation Theory
Machine Learning / Artificial Intelligence
Introduction to BioInformatics
Machine Learning
Machine Learning in Bioinformatics
Data Mining
Advances in Artificial Intelligence
Management of Technology
Technology for Managers

Masters Students
2009
2003

Paramveer Dhillon
Alex Vasserman

”Transfer Learning using Feature Selection.”
“Identifying Chemical Names in Biomedical Text:
An Investigation of the Substring Co-occurrence Based Approaches”

1988

Michael R. Weinstein
Kodak

“Process scheduling using artificial intelligence”

Doctoral Students
current Paramveer Dhillon (CIS)

“TBA”

current Weichen Wu (CIS)

“TBA”

2010

Perry Evans (GCB)

“Modeling virus-host networks”

2010

Ted Sandler (CIS)

“Regularization and Model Selection with Networks of Features”

2009

Bill Kandylas (CIS)

“Online clustering and citation analysis using Streemer”

2008

Gary Morris (CIS)

“Active relational learning for kinship analysis”

2006

Jing Zhou (ESE)
Microsoft
Andrew Schein
Amaranth LLC
Sasha Popescul
Yahoo

“Streaming Feature Selection”

2005
2004

“Active learning using A-optimality”
“Statistical Learning from Relational Databases”

2004

Panos Markopoulos
McKinsey

“The Information Gap: Understanding
Product Information Dissemination”

2003

Eugene Buehler
Merck

“Statistical Models for the analysis
of heterogeneous biological data sets”

3

2002

Roy Kwon
U. of Toronto

“Approximate Mechanisms and Algorithms for Combinatorial Auctions”
(with G. Anandalingam)

2000

David Parkes
Harvard U.

“Iterative Combinatorial Auctions:
Achieving Economic and Computational Efficiency”

1999

Rinaldo Jose
Oregon

“On the optimal coordination of profit maximizing
divisions using auctions and price theory”

1995

Evi Gazi
“Verification of controllers for incompletely-known
Chem. Ind. Inst. Toxicology chemical plants” (with W.D. Seider)

1995

Jack Vinson
Pharmacia

“Automated first principles reasoning using
qualitative and quantitative models”

1993

Bill Foster
BMS

“The significance of neuronal ionic conductances
in the cardiorespiratory nucleus of the solitary
tract of the rat and in Hodgkin-Huxley models”

1993

Catherine Catino
Air Products

“Automated modeling of chemical plants with
application to hazard and operability studies”

1993

Dimitris Psichogios
JP Morgan
Stephen Grantham
Merck

“Process control using structured neural networks”
“Automated reasoning from first principles using
qualitative physics”

1989

Charles X. Ling
U. Western Ontario

“Inductive learning and invention in domains with
primitive recursive structures”

1989

Paul P. Durand
Exxon-Mobil

“Percolation and transport in random media with
application to high temperature superconductors”

1989

Thomas J. Balsano
Amoco
Ralph Gonzales
U. Rutgers, Camden

“Unidirectional solidification of an anisotropic binary alloy”

1990

1989

1988
1988

Steven J. Weinstein
Kodak
Francis X. Kelly
Exxon-Mobil

“Learning by progressive subdivision of state space”

“The low flow rate limit for immiscible fluid systems
in narrow gaps”
“Growth morphologies in rapid solidification”

Publications – Refereed Publications
• medpie: An information extraction package for medical message board posts A. Benton; J.H. Holmes;
S. Hill; A. Chung; L. Ungar Bioinformatics 20, 2012.
• VIF Regression: A Fast Regression Algorithm For Large Data D. Lin, D.P and Foster, and L.H. Ungar,
Journal of the American Statistical Association, 106(493), 232–247, 2011.

4

• Limitations of Threshold-Based Brain Oxygen Monitoring for Seizure Detection, Soojin Park, Alexander Roederer, Ram Mani, Sarah Schmitt, Peter D. LeRoux, Lyle H. Ungar, Insup Lee, and Scott E.
Kasner, Neurocritical Care 15(3), 469-476, 2011.
• Natural Supplements for H1N1 Influenza: Retrospective Observational Infodemiology Study of Information and Search Activity on the Internet, Shawndra Hill, Jun Mao, Lyle Ungar, Sean Hennessy,
Charles E Leonard, and John Holmes, J Med Internet Res, 13(2), e36, 2011.
• Minimum Description Length Penalization for Group and Multi-Task Sparse Learning. Paramveer S.
Dhillon, Dean Foster and Lyle Ungar. Journal of Machine Learning Research (JMLR), 12, 525–564,
2011.
• Extracting templates from radiology reports using sequence alignment. Shengyang Wu, Curtis Langlotz, Paras Lakhani, Lyle Ungar. International Journal of Data Mining and Bioinformatics, in press,
2011.
• Dementia induces correlated reductions in white matter integrity and cortical thickness: A multivariate
neuroimaging study with sparse canonical correlation analysis. Brian B. Avants, Philip A. Cook, Lyle
Ungar, James C. Gee and Murray Grossman NeuroImage 50(3), 1004-1016, 2010
• Sequence alignment reveals possible MAPK docking motifs on HIV proteins. Perry Evans Ahmet
Sacan, Lyle Ungar, Aydin Tozeren PLOS ONE, 5(1) e8942, 2010.
• Positioning Knowledge: Schools of Thought and New Knowledge Creation, S. Phineas Upham, Lori
Rosenkopf and Lyle H. Ungar, Scientometrics, 83(2) 555-581, 2010.
• Innovating knowledge communities - An analysis of group collaboration and competition in science and
technology. Phineas Upham, Lori Rosenkopf, Lyle H. Ungar: Scientometrics 83(2): 525-554, 2010.
• Information Markets for Product Attributes: A Game Theoretic, Dual Pricing Mechanism. P.M.
Markopoulos and R. Aron and L.H. Ungar Decision Support Systems 49, 187199, 2010.
• Analyzing knowledge communities using foreground and background clusters, V. Kandylas, S. Upham,
and L.H. Ungar,, ACM Transactions on Knowledge Discovery from Data (TKDD), 4(2), 1-35, 2010.
• Prediction of HIV-1 virus-host protein interactions using virus and host sequence motifs. Perry Evans,
Will Dampier, Lyle Ungar and Aydin Tozeren BMC Medical Genomics 2:27, 2009.
• Host sequence motifs shared by HIV predict response to antiretroviral therapy. William Dampier,
Perry Evans, Lyle Ungar and Aydin Tozeren BMC Medical Genomics 2:47, 2009.
• A predictive model for identifying mini-regulatory modules in the mouse genome. Mahesh Yaragatti,
Ted Sandler and Lyle Ungar Bioinformatics 25(3): 353-357, 2008; doi: 10.1093/bioinformatics/btn622
• Finding cohesive clusters for analyzing knowledge communities. Vasileios Kandylas, S. Phineas Upham
and Lyle H. Ungar, IEEE Knowledge and Information Systems 17(3) 335-354, 2008.
• A Model of Market Power and Efficiency in Private Electronic Exchanges. Ravi Aron , Lyle Ungar,
Annapurna Valluri, European Journal of Operational Research, (EJOR) 187, 922-942, 2008.
• MetaProm: a neural network based meta-predictor for alternative human promoter prediction. Junwen
Wang, Sridhar Hannenhalli and Lyle H Ungar BMC Genomics 8:374, 2007.
• Active Learning for Logistic Regression: An Evaluation. A. Schein and L. Ungar, Machine Learning
Journal, 68(3): 235-265, 2007.

5

• Streaming Feature Selection. J. Zhou, D. Foster, R. Stine, and L. Ungar Journal of Machine Learning
Research (JMLR) 7(Sep):1861–1885, 2006.
• Identification of potential CSF biomarkers in ALS. G. M. Pasinetti, L. H. Ungar et al. Neurology,
February 15, 2006.
• Automatic term list generation for entity tagging. Ted Sandler, Andrew I. Schein, and Lyle H. Ungar
Bioinformatics, October 25, 2005.
• Iterative Combinatorial Auctions with Bidder-determined Combinations. R. Kwon, A. Anandalingam
and L. Ungar, Management Science, 51(3), 407-418, 2005.
• Using Prior Knowledge to Improve Genetic Network Reconstruction from Microarray Data, A. Bahl,
P. Le, and L. Ungar, In Silico Biology (ISB), 2004
• The CRASSS Algorithm For Integrating Annotation Data With Hierarchical Clustering Results, E. C.
Buehler, J. R. Sachs, K. Shao, A. Bagchi, L. Ungar, Bioinformatics, 1367-4803, 2004.
• CROC: A New Metric for Recommender System Evaluation. A. I. Schein, A. Popescul, L. H. Ungar
and D. M. Pennock, Journal of Electronic Commerce Research 5(1): 51-74, 2005.
• Dual Pricing in Electronic Markets, P. Markopoulos, R. Aron and L. H. Ungar, Proc. International
Conference on Information Systems (ICIS-2003) December, 2003.
• Chloroplast Transit Peptide Prediction: a Peek Behind the Black Box, A.I. Schein, J. C. Kissinger and
L. H. Ungar, Nucleic Acids Research Methods, 29(16) e82. 2001.
• Pricing Interprocess Streams Using Slack Auctions, R. A. Jose and L.H. Ungar, AIChE Journal, 575587, March, 2000.
• Estimating Monotonic Functions and Their Bounds, H. Kay and L.H. Ungar, AIChE Journal, 46(12),
2425-2434, 2000.
• Hybrid neural network models for environmental process control, R.D. De Veaux, R. Bain and L.H.
Ungar, Environmetrics 10(3), 225-236, 1999.
• Prediction Intervals for Neural Networks via Nonlinear Regression, R. De Veaux, J. Schumi, J. Schweinsberg, D. Shellington and L.H. Ungar, Technometrics, 40(4) 273-282, 1998.
• A non-parametric Monte-Carlo technique for controller verification, E. Gazi, W. D. Seider and L. H.
Ungar, Automatica 33(5), 901-906, 1997.
• Active Learning for Vision-Based Robot Grasping, M. Salganicoff, L.H., Ungar and R. Bajcsy, Machine
Learning Journal 23251-78, 1996.
• Verification of controllers in the presence of uncertainty: application to styrene polymerization, E.
Gazi, W.D. Seider and L.H. Ungar, Industrial and Engineering Chemistry Research, 35 (7) 2277-2287,
1996.
• Automatic-analysis of monte-carlo simulations of dynamic chemical plants, E. Gazi, L.H. Ungar, W.D.
Seider and B.J. Kuipers, Computers & Chemical Engineering 20 S987-S992, 1996.
• Control of the physical world by intelligent agents: putting the pieces together, B. Kuipers and L.H.
Ungar, AI Magazine 16:7-8 Spring 1995.
• Dynamic Process Monitoring and Fault Diagnosis with Qualitative Models, J.M. Vinson and L.H.
Ungar, IEEE Transactions on Man, Machines and Cybernetics, 25(1), 181-189, 1995.

6

• A Model-Based Approach to Automated Hazard Identification of Chemical Plants, C.A. Catino and
L.H. Ungar, Computers and Chem. Engr.,41(1), 97-109, 1995.
• Comment on “Neural Networks and Related Methods for Classification” R.D. De Veaux, L.H. Ungar,
D.J. Darken, Journal of the Royal Statistical Society, Series B, 56(3), 446-447. 1994.
• SVD-Net: An Algorithm which Automatically Selects Network Structure, D.C. Psichogios and L.H.
Ungar, IEEE Transactions on Neural Networks, 5(3) 513-515, 1994.
• Significance of conductances in Hodgkin-Huxley models, W.R. Foster, L.H. Ungar and J.S. Schwaber,
Journal of Neurophysiology,70(6) 2502–2518, 1993.
• A Comparison of Two Nonparametric Estimation Schemes: MARS and Neural Networks, R.D. De
Veaux, D.C. Psichogios and L.H. Ungar, Computers and Chem. Engr., 17(8), 819–837, 1993.
• A Hybrid Neural Network - First Principles Approach to Process Modeling, D.C. Psichogios and L.H.
Ungar, AIChE Journal, 1499–1512, October, 1992.
• Using Radial Basis Functions to Approximate a Function and Its Error Bounds, J.A. Leonard, M.A.
Kramer and L.H. Ungar, IEEE Transactions on Neural Networks, 3(4) 624-627, 1992.
• A Neural Network Architecture that Computes its own Reliability, J.A. Leonard, M.A. Kramer and
L.H. Ungar, Computers and Chem. Engr., 16(9) 819–837, 1992.
• Neural Network Forecasting of Short Noisy Time Series, B. Foster, F. Collopy and L.H. Ungar, Computers and Chem. Engr., 16(4) 293-298, 1992.
• Automatic Rebuilding of Qualitative Models for Diagnosis, J.M. Vinson, S.D. Grantham and L.H.
Ungar, IEEE Expert, 23–30, August, 1992.
• Direct and Indirect Model Based Control Using Artificial Neural Networks, D.C. Psichogios and L.H.
Ungar, I & EC Res. 30, 2564-2573, 1991.
• Automatic Generation of Qualitative Models of Chemical Process Units, C.A. Catino, S.D. Grantham
and L.H. Ungar, Computers and Chem. Engr. 15(8) 583-599, 1991.
• Comparative Analysis of Qualitative Models when the Model Changes, S. D. Grantham and L. H.
Ungar, AIChE Journal 37(6), 931-943, 1991.
• A First Principles Approach to Automated Troubleshooting of Chemical Plants, S. D. Grantham and
L.H. Ungar, Computers and Chem. Engr. 14(7), 783-798, 1990.
• Prediction of Decoupling in High Temperature Superconductors, P.P. Durand and L.H. Ungar, Phys.
Rev. B 41(1), 815-818, 1990.
• Expert Multivariable Control: Part 3 - Extension of EMC to Three-Product Sidestream Distillation
Columns, W. L. Luyben, V. Tzouanas, C. Georgakis and L.H. Ungar, I & EC Research 29, 403-415,
1990.
• Expert Multivariable Control: Part 2 - Application of Two-Product Distillation Columns, W. L. Luyben, V. Tzouanas, C. Georgakis and L.H. Ungar, I & EC Research 29, 389-403, 1990.
• Luyben, W. L., V. Tzouanas, C. Georgakis and L.H. Ungar, Expert Multivariable Control: Part I Structure and Design Methodology, I & EC Research 29, 382-388, 1990.
• A Theoretical Study of Two- Phase Flow through a Narrow Gap with a Moving Contact Line: Viscous
Fingering in a Hele-Shaw Cell, S.J. Weinstein, E.B. Dussan V. and L.H. Ungar, J. Fluid. Mech. 221,
53-76, 1990.
7

• Adaptive Networks for Fault Diagnosis and Process Control, L.H. Ungar, S.N. Kamens and B. Powell,
Computers and Chem. Eng. 14, 561-572, 1990.
• A Molecular Dynamics Investigation of Solute Trapping During Rapid Solidification of Silicon, F.X.
Kelly and L.H. Ungar, J. Crystal Growth 102, 658-666, 1990.
• Finite Element Methods for Unsteady Solidification Problems Arising in Prediction of Morphological
Structure, L.H. Ungar, N. Ramprasad and R.A. Brown, J. Scientific Computing 3(1), 77-108, 1988.
• Expert Multivariable Control, V. Tzouanas, C. Georgakis, W. L. Luyben and L.H. Ungar, Computers
and Chem. Eng. 12(9/10), 1065-1074, 1988.
• Percolation and Transport in an Assembly of Anisotropic Conductors, P.P. Durand and L.H. Ungar,
Physical Review A 26, 2487-2501, 1988.
• Application of the Boundary Element Method to Dense Dispersions, P.P. Durand and L.H. Ungar, Int.
J. Numer. Methods in Engr. 26, 2487-2501, 1988.
• Nonlinear Systems in Chemical Engineering, W.D. Seider and L.H. Ungar, Chemical Engineering Education 21(4), 178-183, 1987.
• Steady and Oscillatory Pattern Formation in Rapid Solidification, F.X. Kelly and L.H. Ungar, Physical
Review B 34, 1746-1753,1986.
• Cellular Morphologies in Directional Solidification: IV. The Formation of Deep Cells, L.H. Ungar and
R.A. Brown, Physical Review B31, 5931-5940, 1985.
• Cellular Morphologies in Directional Solidification: III. The Effects of Heat Transfer and Solid Diffusivity, L.H. Ungar, M.J. Bennett and R.A. Brown, Physical Review B 31, 5923-5930, 1985.
• Applied Mathematics in Chemical Engineering, D. Lauffenburger, E. Dussan V. and L. Ungar, Chemical
Engineering Education Fall, 160-163 and 214-215, 1984.
• Cellular Interface Morphologies in Directional Solidification: II. The Effect of Grain Boundaries, L.H.
Ungar and R.A. Brown, Physical Review B 30, 3993-3999, 1984.
• Cellular Interface Morphologies in Directional Solidification: I. The One-Sided Model, L.H. Ungar and
R.A. Brown, Physical Review B 29, 1367-1380, 1984.
• The Dependence of the Shape and Stability of Captive Rotating Drops on Multiple Parameters, L.H.
Ungar and R.A. Brown, Phil. Trans. R. Soc. Lond. A306, 347-370, 1982.

Publications - Refereed Conference Proceedings
• Spectral Dependency Parsing with Latent Variables, Dhillon, Rodu, Collins, Foster and Ungar EMNLP
2012.
• Spectral Learning of Latent-Variable PCFGs Shay B. Cohen, Karl Stratos, Michael Collins, Dean P.
Foster, and Lyle Ungar ACL 2012.
• Using CCA to improve CCA: A new spectral method for estimating vector models of words, Paramveer
Dhillon, Dean Foster and Lyle Ungar, ICML 2012.
• Using Word Similarities to better Estimate Sentence Similarity, Sneha Jha, H. Andrew Schwartz and
Lyle H. Ungar, Semeval 2012.

8

• Characterizing Emergence Using a Detailed Micro-model of Science: Investigating Two Hot Topics in
Nanotechnology Kevin W. Boyack,Richard Klavans,Henry Small, Lyle Ungar Technology Management
for Emerging Technologies (PICMET) 2012.
• Partial Sparse Canonical Correlation Analysis (PSCCA) for population studies in medical imaging
Paramveer S. Dhillon, Brian Avants, Lyle Ungar, James Gee, ISBI 2012 Paper 1074, 2012.
• Spectral methods for estimating probabilistic language models Lyle Ungar, Paramaveer Dhillon, Jordan
Rodu, Michael Collins, and Dean Foster Snowbird Learning Workshop, 2012.
• Multi-View Learning of Word Embeddings via CCA, Paramveer Dhillon, Dean Foster, Lyle Ungar,
Neural Information Processing Systems ( NIPS) 2011.
• Discovery of Significant Emerging Trends, Saurabh Goorha and Lyle Ungar ACM Knowledge Discovery
and Data mining (KDD) 57–64, 2010.
• A System for De-identifying Medical Message Board Text Benton, A. and Hill, S. and Ungar, L. and
Chung, A. and Leonard, C. and Freeman, C. and Holmes, J.H. IEEE Ninth International Conference
on Machine Learning and Applications. 485490, 2010. also published in BMC Bioinformatics,Jun 9;12
Suppl 3:S2, 2011.
• Mining Internet Conversations for Evidence of Supplement-Associated Adverse Events John H. Holmes,
Adrian Benton, Annie Chung, Cristin Freeman, Sean Hennessy, Shawndra Hill, Charles Leonard, Jun
Mao, Lyle Ungar AMIA 2010 Symposium Proceedings (AMIA-1851-A2009) 1082. 2010.
• A new approach to lexical disambiguation of Arabic text, R. Shah, P.S Dhillon, M. Liberman, D.
Foster, M. Maamouri and L. Ungar, Proceedings of the 2010 Conference on Empirical Methods in
Natural Language Processing, 725–735, 2010.
• Feature Selection using Multiple Streams, Paramveer Dhillon, Dean Foster and Lyle Ungar. Proceedings of The Thirteenth International Conference on Artificial Intelligence and Statistics (AISTATS):
Journal of Machine Learning Research - Proceedings Track 9 153-160, 2010.
• Multi-Task Feature Selection using the Multiple Inclusion Criterion (MIC), Paramveer Dhillon, Brian
Tomasik, Dean Foster and Lyle Ungar, ECML-PKDD (European Conference on Machine Learning),
Bled, Slovenia, Sept. 2009.
• Transfer Learning, Feature Selection and Word Sense Disambiguation, Paramveer Dhillon, and Lyle
Ungar. ACL-IJCNLP (Annual Meeting of the Association of Computational Linguistics),257-260, 2009.
• Transfer Learning Using Feature Selection, Paramveer S. Dhillon, Dean P. Foster, Lyle H. Ungar,
CoRR abs/0905.4022, 2009.
• Gamma-band ECoG correlates of human cognitive representations. Jacobs, J., Ungar, L.H. and Kahana, M.J. Program No. 279.2. Chicago, IL: Society for Neuroscience, 2009.
• Efficient Clustering of Web-Derived Data Sets. Luis Sarmento, Alexander Kehelenbeck, Eugenio
Oliveira, and Lyle Ungar, International Conference on Machine Learning and Data Mining (MLDM)
2009.
• An Approach to Web-scale Named-Entity Disambiguation. Luis Sarmento, Alexander Kehelenbeck,
Eugenio Oliveira, and Lyle Ungar, International Conference on Machine Learning and Data Mining
(MLDM) 2009.
• Resolving Identity Uncertainty with Learned Random Walks. Ted Sandler, Lyle H. Ungar and Koby
Crammer, International Conference on Data Mining (ICDM), 457-465, 2009.b

9

• Regularized Learning with Networks of Features. Ted Sandler, John Blitzer, Partha Pratim Talukdar,
Lyle H. Ungar, Neural Information Processing Systems (NIPS), 1401-1408, 2008.
• Protein-Protein Interaction Network Alignment by Quantitative Simulation. P Evans, T Sandler, L
Ungar Proceedings of the 2008 IEEE International Conference on Bioinformatics and Biomedicine
(BIBM ’08), 325-328, 2008.
• Multiway Clustering for Creating Biomedical Term Sets. V Kandylas, L Ungar, T Sandler, S Jensen
Proceedings of the 2008 IEEE International Conference on Bioinformatics and Biomedicine (BIBM
’08), 449-452, 2008.
• Using Text Mining to Analyze User Forums. R. Feldman, M. Fresko, J. Goldenberg, O. Netzer, L.
Ungar 5th IEEE ICSSSM’08, Melbourne, 2008.
• Web-Scale Named Entity Recognition. Casey Whitelaw, Alex Kehlenbeck, Nemanja Petrovic and Lyle
Ungar ACM 17th Conference on Information and Knowledge Management (CIKM), 123-132, 2008.
• Using sequence classification for filtering web pages. Binyamin Rosenfeld, Ronen Feldman and Lyle H.
Ungar ACM 17th Conference on Information and Knowledge Management (CIKM), 1355-1356, 2008.
• Efficient Feature Selection in the Presence of Multiple Feature Classes Paramveer S. Dhillon, Dean
Foster and Lyle H. Ungar IEEE International Conference on Data Mining (ICDM), 2008.
• Scalable Methods for Extracting Named Entities from the Web Casey Whitelaw, Alex Kehlenbeck,
Luis Sarmento, Lyle Ungar INFORMS 2008 (abstract only)
• In defense of L0 . Dongyu Lin, Dean Foster and Lyle Ungar ICML-2008 Workshop on Sparse Optimization and Variable Selection, 2008.
• Information Theory-Based Feature Selection Dean P. Foster and Lyle H. Ungar Fourteenth Yale Workshop on Adapative and Learning Systems, 2008
• Learning with Locally Linear Feature Regularization Ted Sandler, John Blitzer, Lyle Ungar Snowbird
Learning Workshop, 2008
• Maximal Subset Feature Selection for BioInformatics Dean P. Foster, Anna Goldenberg and Lyle H.
Ungar Snowbird Learning Workshop, 2008
• Finding cohesive clusters for analyzing knowledge communities, Vasileios Kandylas, S. Phineas Upham,
and Lyle H. Ungar, Seventh IEEE International Conference on Data Mining (ICDM), Oct 2007.
• Extracting Product Comparisons from Discussion Boards, Feldman et al. Seventh IEEE International
Conference on Data Mining (ICDM), Oct 2007.
• Innovating Knowlege Communities, Phin Upham, Lori Rosenkopf, and Lyle Ungar, 2007 Academy of
Management Meeting, Philadelphia, PA (selected for the “Best Paper Proceedings of the 2007 Academy
of Management Meeting.”)
• An Empirical Study of the Behavior of Active Learning for Word Sense Disambiguation, J. Chen, A.
Schein, L. Ungar and M. Palmer HLT-NAACL 06, 2006.
• Is Online Product Information Diven by Quality or Diferentiation?, P.M. Markopoulos and R. Aron
and L.H. Ungar. proceedings of the International Conference of Information Systems (ICIS-2005),
2005.
• Cluster-based Concept Invention for Statistical Relational Learning, A. Popescul and L. Ungar, KDD2004, 2004.
10

• Genomic Characterization of Synaptic Proteins, SynapseDB, M. Bucan et al. The Biology of Genomes
(Cold Spring Harbor May, 2004). (abstract only)
• Integrated Annotation for Biomedical Information Extraction , S. Kulick, A. Bies, M. Libeman, M.
Mandel, R. McDonald, M. Palmer, A. Schein and L. Ungar, HLT/NAACL, Boston, May, 2004.
• Statistical Relational Learning for Document Mining, A. Popescul, L. H. Ungar, S.Lawrence and K.M.
Pennock. International Conference on Data Mining (ICDM-2003), 2003.
• Using Reinforcement Learning to Refine Autonomous Robot Controllers, G. Grudic, V. Kumar and L.
Ungar, International Conference on Intelligent Robots and Systems (IROS), 2003.
• Mixtures of Conditional Maximum Entropy Models, D. Pavlov, A. Popescul, D.M. Pennock and L.H.
Ungar, International Conference on Machine Learning (ICML), 2003.
• Structural Logistic Regression for Link Prediction, A. Popescul and L. H. Ungar, KDD Workshop on
Multi-Relational Data Mining and a similar paper, Statistical Relational Learning for Link Prediction.
A. Popescul and L. H. Ungar, IJCAI-03 Workshop on Relational Learning, 2003.
• A Combinatorial Auction-Based Method for Supply Chain Management, R. Kwon and L. Ungar,
Institute for Operations Research and the Management Sciences (INFORMS), 2003.
• Static and Dynamic Analysis of the Internet’s Susceptibility to Faults and Attacks, S-T. Park, A.
Khrabrov, D.M. Pennock, S. Lawrence, C.L. Giles and L.H. Ungar, Infocom, 2003.
• A Generalized Linear Model for Principal Component Analysis of Binary Data, A. I. Schein, L. K.
Saul and L. H. Ungar, Proc. 9th International Workshop of AI and Statistics, Jan 3-6, 2003.
• Rates of Convergence of Performance Gradient Estimates Using Function Approximation adn Bias in
Reinforcement Learning, G. Grudic, and L. Ungar, NIPS 14, 2002.
• Dual Pricing and Information Deficit in Electronic Markets, P. Markopoulos, R. Aron and L. H. Ungar,
International Conference on Information Systems (ICIS) 2003; earlier version apperared in Workshop
on Information Systems and Economics (WISE), 2002.
• Towards Structural Logistic Regression: Combining Relational and Statistical Learning, A. Popescul,
L. H. Ungar, S. Lawrence and D. M. Pennock, Workshop on Multi-Relational Data Mining, at the
Eighth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD
2002), 2002.
• Methods and Metrics for Cold-Start Recommendations, A. I. Schein, A. Popescul, L. H. Ungar and D.
M. Pennock, ACM Special Interest Group on Information Retrieval SIGIR-2002, August 2002.
• Pricing Price Information in E-commerce, P.M. Markopoulos and L.H. Ungar, Proceedings of the ACM
Conference on Electronic Commerce (EC01), Tampa, Florida, October 2001.
• Towards Learning by Ontological Leaps, L. Ungar and D. Foster, Snowbird Learning Workshop. 2001.
• A Primal-Dual Algorithm for Winner Determination in Combinatorial Auctions, R. Kwon, G. Anandalingam and L.H. Ungar, INFORMS, 2001.
• Maximum Entropy Methods for Biological Sequence Modeling, Buehler, E. and L.H. Ungar, BIOKDD
2001 workshop, 2001.
• Generative Models for Cold-Start Recommendations, A. Schein, A. Popescul, L. H. Ungar and D. M.
Pennock, Workshop on Recommender Systems, SIGIR-2001, 2001

11

• Exploiting Multiple Secondary Reinforcers in Policy Gradient Reinforcement Learning, G. Z. Grudic
and L. H. Ungar, IJCAI 2001, 2001.
• Probabilistic Models for Unified Collaborative and Content-Based Recommendation in Sparse-Data
Environments, A. Popescul, L. H. Ungar, D. M. Pennock and S. Lawrence, Uncertainty in AI (UAI
2001) Conference, August 2001
• Efficient Reinforcement Learning for Robots, G. Z. Grudic and L. H. Ungar, Yale Workshop on Adaptive
and Learning Systems, June, 2001.
• Iterative Combinatorial Auctions: Theory and Practice. D. C. Parkes and L.H. Ungar, Proc. 18th
National Conference on Artificial Intelligence, (AAAI-00), 74-81. 2000.
• Preventing Strategic Manipulation in Iterative Auctions: Proxy-Agents and Price-Adjustment, D. C.
Parkes and L.H. Ungar, Proc. 18th National Conference on Artificial Intelligence, (AAAI-00), 82-89.
2000.
• Localizing Search in Reinforcement Learning, G. Z. Grudic and L. H. Ungar, Proc. 18th National
Conference on Artificial Intelligence, (AAAI-00), 590-595. 2000.
• Localizing Policy Gradient Estimates to Action Transitions, G. Z. Grudic and L. H. Ungar, International Conference on Machine Learning (ICML2000), 343-350. 2000.
• Efficient Clustering of High-Dimensional Data Sets with Application to Reference Matching, A. McCallum, K. Nigam and L. Ungar, KDD-2000, 2000.
• Clustering and Identifying Temporal Trends in Document Databases, A. Popescul, G. W. Flake, S.
Lawrence, L.H. Ungar and C. L. Giles, Proc. IEEE Advances in Digital Libraries 2000 Conference,
2000.
• String Edit Analysis for Merging Databases, J.J. Zhu and L.H. Ungar, Proc. KDD-2000 Workshop on
Text Mining, 2000.
• Accounting for Cognitive Costs in On-line Auction Design, D. C. Parkes, L. H. Ungar and D. P. Foster,
LNAI 1571 Agent mediated Electronic Commerce (AMEC-98), pp 25–40, Springer Verlag, 1999.
• Clustering methods for collaborative filtering L.H. Ungar and D.P. Foster AAAI Workshop on Recommendation Systems, 1998
• A formal statistical approach to collaborative filtering L.H. Ungar, D.P. Foster CONALD98, 1998
• Auction-driven coordination for plantwide optimization, R.A. Jose and L.H. Ungar, Foundations of
Computer-Aided Process Operation FOCAPO, 1998.
• Learning and Adaption in Multiagent Systems, D.C. Parkes and L. H. Ungar, AAAI97 Workshop on
MultiAgent Learning, 1997.
• Characterizing the generalization performance of model selection strategies, D. Schuurmans, D.P. Foster and L.H. Ungar, Proceedings of 1997 ML/COLT, 1997.
• Learning and Adaption in Multiagent Systems, D.C. Parkes and L. H. Ungar, AAAI97 Workshop on
MultiAgent Learning, 1997.
• Automatic Analysis of Monte-Carlo Simulations of Dynamic Chemical Plants, E. Gazi, L. H. Ungar,
W. D. Seider and B. J. Kuipers, Proceedings of the ESCAPE 6 Symposium, Rhodes, Greece, May,
Pergamon Press, 1996.

12

• Controller verification for polymerization reactors, E. Gazi, W.D. Seider and L.H. Ungar, Proc. Intelligent Systems in Process Engineering (ISPE ’95), 1995.
• Neural Networks for Process Control, L.H. Ungar, E. Hartman and J. Keeler, Proc. Intelligent Systems
in Process Engineering (ISPE ’95), 1995.
• A Statistical Basis for Using Radial Basis Functions for Process Control, L.H. Ungar and R.D. DeVeaux,
Proceedings of the ACC, 1995.
• Active Exploration and Learning in Real-Valued Spaces using Multi-Armed Bandit Allocation Indices,
Salganicoff, M. and L.H. Ungar, Proc. 12th Intl. Conf. on Machine Learning, July, 1995.
• Statistical Approaches to Fault Analysis in Multivariate Process Control, R.D. DeVeaux, L.H. Ungar
and J.M. Vinson, Proceedings of the ACC, 1994.
• Active Exploration-Based ID-3 Learning for Robot Grasping, M. Salganicoff, L.G. Kunin and L.H.
Ungar, Proceedings of the Workshop on Robot Learning, 11th Intl. Conf. on Machine Learning, July,
1994.
• Control of Nonlinear Processes Using Qualitative Reasoning, E. Gazi, W.D. Seider and L.H. Ungar,
Proceedings of ESCAPE 3, 1994.
• Controller Verification Using Qualitative Reasoning, E. Gazi, L.H. Ungar and W.D. Seider, ADCHEM
Proceedings, 1994.
• Stability of Neural Net Based Model Predictive Control, J.W. Eaton, J.B. Rawlings and L.H. Ungar,
Proceedings of the ACC, 2481-85, 1994.
• The Role of Baroreceptor Resetting in Habituating Control of Blood Pressure, S.R. Carden, L.H.
Ungar, W.C. Rose and J.S. Schwaber, Proceedings of the ACC, 87-91, 1994.
• Dynamic Fault Detection with the Automatic Process Evaluator, J.M. Vinson and L.H. Ungar, CIMPRO Proceedings, 295-301, 1994.
• Radial Basis Function Neural Networks for Process Control, L.H. Ungar, T. Johnson and R.D. DeVeaux, Computer-Integrated Manufacturing in the PROcess industries (CIMPRO) Proceedings, 357364, 1994.
• Controller verification using qualitative reasoning, E. Gazi, W.D. Seider and L.H. Ungar, Proceedings
of 2nd IFAC workshop on computer software structure integ. AI/KBS Sys. In Proc. Cont. Lund,
Sweden, 1994.
• Control of Nonlinear Processes using Qualitative Reasoning, E. Gazi, W.D. Seider and L.H. Ungar,
Proceedings of 1993 ESCAPE in Computers and Chem. Engr., 18, S189–S193, 1994.
• The Automatic Process Evaluator, J.M.Vinson and L.H. Ungar, Proceedings of the Second Intl. Conf.
on FOCAPO, ed. Rippin et al., CACHE, 443-449, 1993.
• QMIMIC: Model-based Monitoring and Diagnosis, J.M. Vinson and L.H. Ungar, Proceedings of the
ACC 1880–1884, 1993.
• A Tale of Two Nonparametric Estimation Schemes: MARS and Neural Networks, R.D. DeVeaux, D.C.
Psichogios and L.H. Ungar, 4th Intl. Conf. on Artificial Intelligence and Statistics, Jan. 1993.
• Neural Control and Adaptation in Blood Pressure Control, L.H. Ungar, J.S. Schwaber and W.R. Foster,
Proceedings of the Yale Workshop on Adaptive and Learning Systems, 111-115, 1992.

13

• Matching Neural Models to Experiment, W.R. Foster, J.F.R. Paton, J.J. Hopfield, L.H. Ungar and
J.S. Schwaber, Proceedings of Computation and Neural Systems Meeting, San Francisco, 1992.
• Fault Detection and Diagnosis using Qualitative Modelling and Interpretation, J.M. Vinson and L.H.
Ungar, in On-line Fault Detection and Supervision in the Chemical Process Industries Preprints of the
IFAC Symposium, Newark, Delaware, USA April 22-24, 1992, Ed. P.S. Dhurjati, pp. 81-86, 1992.
• Process Modeling Using Structured Neural Networks, D.C. Psichogios and L.H. Ungar, Proceedings of
the ACC 1917-1921 (1992).
• Nonparametric System Identification: A Comparison of MARS and Neural Networks, D.C. Psichogios,
R.D. DeVeaux and L.H. Ungar, Proceedings of the ACC 1436-1440, 1992.
• Nonlinear Internal Model Control Using Neural Networks, D.C. Psichogios and L.H. Ungar, Proceedings
of the IEEE Fifth Int’l. Symposium on Intelligent Control, September, 1990.
• Nonlinear Internal Model Control Using Neural Networks, D.C. Psichogios and L.H. Ungar, Proceedings
of the Sixth Yale Workshop on Adaptive and Learning Systems, Yale, August, 1990.
• A Bioreactor Benchmark for Adaptive Network-based Control, L.H. Ungar, Proceedings of the 1988
NSF Workshop on Neural Networks for Robotics MIT Press, 1990.
• Expert Systems for Engineering Design and Manufacturing, L.H. Ungar, Proceedings of the Fifth National Conference on University Programs in Computer-Aided Engineering, Design and Manufacturing
114-117, 1987.
• Towards an Expert Multivariable Controller, V. Tzouanas, L.H. Ungar and C. Georgakis, IFAC Proceedings, 1987.
• Pattern Formation in Directional Solidification: The Nonlinear Evolution of Cellular Melt/Solid Interfaces, R.A. Brown and L.H. Ungar, Aachen Workshop on Microgravity and Directional Solidification
Ed. P. Sahm, 1984.
• A Model of an Artificial Pancreas: Transient Diffusion in a Two Phase Composite with a Glucose
Dependent Insulin Source at the Interface, C.K. Colton and L.H. Ungar, Proceedings of the N.E.
Bioengineering Conf. 547-522, 1980.

Books Edited
Proceedings of the Twelfth ACM SIGKDD International Conference on Knowledge Discovery and Data
Mining, Philadelphia, PA, USA, August 20-23, 2006 Tina Eliassi-Rad, Lyle H. Ungar, Mark Craven and
Dimitrios Gunopulos, ACM, 2006.

Book Chapters
• Reinforcement Learning in Large, High Dimensional State Spaces Grudic and Ungar, in Learning and
Approximate Dynamic Programming: Scaling Up to the Real World, IEEE Press and John Wiley &
Sons, 2004.
• Shopbots and Pricebots in Electronic Service Markets, P.M. Markopoulos and L.H. Ungar, 2000, in
Game theory and decision theory in agent-based systems, Kluwer Academic Publishers, 2002. An early
version was presented in Game Theoretic and Decision Theoretic Agents workshop in ICMAS ’2000
-The Fourth International Conference on MultiAgent Systems.
• Forecasting, L.H. Ungar, in The Handbook of Brain Theory and Neural Networks, ed. M.A. Arbib,
MIT Press, 399-403, 1995, revised in second edition, 2003.
14

• Process Control, L.H. Ungar, in The Handbook of Brain Theory and Neural Networks, ed. M.A. Arbib,
MIT Press, 760-764, 1995.
• Advanced Knowledge Representation: CACHE Monograph on Artificial Intelligence for Chemical Engineering, L.H. Ungar and V. Venkatasubramanian, AIChE, 1990.
• Qualitative Physics, S. Grantham and L.H. Ungar, in A Sourcebook on Formal Techniques in Artificial
Intelligence ed. R. Banerji, Elsevier Press, 77-121, 1990.
• Nonlinear Interactions of Interface Structures at Differing Wavelength in Directional Solidification,
M.J. Bennett, R.A. Brown and L.H. Ungar, in The Physics of Structure Formation Springer Verlag,
ed. W. Guttinger and G. Dangelmeyer, 180-190, 1987.
• Convection, Segregation and Interface Morphology in Directional Solidification, R.A. Brown, L.H.
Ungar and P.M. Adornato, in Modeling of Patterns in Space and Time ed. W. Jaeger, Springer Verlag,
1984.

Patents
• US 5,335,391 Method and apparatus for pattern mapping system with self-reliability check
M.A. Kramer, J.A. Leonard and L.H. Ungar
• US 5,951,623 Lempel-Ziv data compression technique utilizing a dictionary prefilled with frequent letter combinations, words and/or phrases
J.C Reynar, F. Herz, J. Eisner and L. Ungar
• US 5,835,087 System for general of object profiles for a system for customized elecronic identification
of desirable objects
F. Herz, J. Eisner and L. Ungar
• US 5,758,257 System and method of scheduling broadcast of and access to video program and other
data using customer profiles
F. Herz, L. Ungar, J. Zhang, D. Wachob and M. Salganicoff
• US 5,754,939 System for generation of user profiles for a sysem for customized electronic identification
of desirable objects
F. Herz, J. Eisner L. Ungar, M. Marcus
• US 6,088,722 System and method for scheduling broadcast of and access to video programs and other
data using customer profiles (divisional of the 5,835,087)
F. Herz, L. Ungar, J. Zhang, D. Wachob and M. Salganicoff
• US 6,020,883 System and method of scheduling broadcast of and access to video program and other
data using customer profiles
F. Herz, L. Ungar, J. Zhang, D. Wachob and M. Salganicoff
• US 20,030,135,445 Stock market prediction using natural language processing
F. Herz, L. Ungar, J. Eisner and P. Labys

15

• US 20,020,184,102 Selling price information in e-commerce
P. Markopoulos and L. Ungar

16