Tomer Levinboim
Tomer Levinboim
CS PhD (candidate)
e-mail: levinboim.1 at nd dot edu

M.Sc USC
M.Sc Tel Aviv University
B.A. IDC Herzliya
ND
USC
TAU
IDC
I am a Ph.D. student at the University of Notre Dame working with Prof. David Chiang on developing
Machine Learning techniques that improve Machine Translation, focusing on low-resource languages.

News

2016 - Listed on NAACL 2016 best reviewers
2016 - Winter internship at Microsft Research (Redmond)
2015 - Short paper accepted to EMNLP.
2015 - Two new papers accepted to NAACL-HLT 2015.

Recent Publications

Supervised Phrase Table Triangulation with Neural Word Embeddings for Low-Resource Languages
Tomer Levinboim, David Chiang. EMNLP 2015. PDF Poster

Multi-Task Word Alignment Triangulation for Low-Resource Languages
Tomer Levinboim, David Chiang. NAACL-HLT 2015. PDF

Model Invertibility Regularization (MIR): Sequence Alignment With or Without Parallel Data
Tomer Levinboim, Ashish Vaswani, David Chiang. NAACL-HLT 2015. PDF OMM slide code


Other Publications
Other Publications

Learning the Kernel Matrix with Low-Rank Multiplicative Shaping
Tomer Levinboim, Fei Sha. AAAI 2012. PDF

Provable Unlinkability against Traffic Analysis with Low Message Overhead
Ron Berman, Amos Fiat, Marcin Gomulkiewicz, Marek Klonowski, Miroslaw Kutylowski,
Tomer Levinboim, Amnon Ta-Shma. Journal Of Cryptology, December 2013. PDF

Master Thesis: Partition exchange and anonymous communication on sparse graphs
Tomer Levinboim (under the supervision of Prof. Amnon Ta-Shma, 2010). PDF

Learning and Evaluating Human-Like NPC Behaviors in Dynamic Games
Yu-Han Chang, Rajiv Maheswaran, Tomer Levinboim, Vasudev Rajan, AIIDE 2011. PDF

The Social Ultimatum Game
Yu-Han Chang, Tomer Levinboim, and Rajiv Maheswaran
Decision Making with Multiple Imperfect Decision Makers Workshop, NIPS 2010. PDF

Inverse Computer Graphics: Parametric Comics Creation from 3D Interaction
Ariel Shamir, Michael Rubinstein, Tomer Levinboim
IEEE Computer Graphics & Applications, Volume 26, number 3, 30-38, 2006. PDF
Code
Code
  • Python code for Penalized Unigram Segmentation
    • based on the segmentation model proposed in "Online EM for Unsupervised Models"
  • Python code for Spectral Projected Gradient (SPG) Descent
    • based on Mark Schmidt's matlab code
  • Python code for Parallel Coordinate Descent LASSO
  • MIR C++ implementation on top of the giza++ word aligner

Teaching
Teaching
TA: CSCI-567 - Machine Learning (USC)
TA: Electronic Voting Workshop (TAU)
Grader: Computational Complexity (TAU) (see our group)