Daniel Khashabi

alt text 

Daniel Khashabi (دانیال خشابی)
PhD candidate
Computer and Information Science
University of Pennsylvania


* About the figure: A poor facial feature tracker on my own face.

About

I am thrilled to have Prof. Dan Roth as my advisor. I was greatly fortunate to work with Prof. Hamid Sheikhzadeh as my undergraduate advisor.

I do research on theoretical and empirical analysis of information, for learning, inference and decision making. More specifically, I focus on Artificial Intelligence, in the context of natural languages.

Publication

Disclaimer: This material is presented to ensure timely dissemination of scholarly works. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms invoked by each author's copyright.
★ shows equal contribution!

Zero-Shot Open Entity Typing as Type-Compatible Grounding

Ben Zhou, Daniel Khashabi, Chen-Tse Tsai and Dan Roth
Conference on Empirical Methods in Natural Language Processing (EMNLP), 2018
Code

Looking Beyond the Surface:A Challenge Set for Reading Comprehension over Multiple Sentences

Daniel Khashabi, Snigdha Chaturvedi, Michael Roth, Shyam Upadhyay and Dan Roth
Conference of the North American Chapter of the Association for Computational Linguistics (NAACL), 2018
Dataset Poster

CogCompNLP: Your Swiss Army Knife for NLP

Daniel Khashabi, Mark Sammons, Ben Zhou, Tom Redman, Christos Christodoulopoulos, Vivek Srikumar, Nicholas Rizzolo, Lev Ratinov, Guanheng Luo, Quang Do, Chen-Tse Tsai, Subhro Roy, Stephen Mayhew, Zhili Feng, John Wieting, Xiaodong Yu, Yangqiu Song, Shashank Gupta, Shyam Upadhyay, Naveen Arivazhagan, Qiang Ning, Shaoshi Ling, Dan Roth
International Conference on Language Resources and Evaluation (LREC), 2018
Code on github Poster: PDF PPTX

Question Answering as Global Reasoning over Semantic Abstractions

Daniel Khashabi, Tushar Khot, Ashish Sabharwal, and Dan Roth
The Conference on Artificial Intelligence (AAAI), 2018
Code on github, Slides(AAAI): PDF, Slides(AAAI): Google Drive

Relational Learning and Feature Extraction by Querying over Heterogeneous Information Networks

Parisa Kordjamshidi, Sameer Singh, Daniel Khashabi, Christos Christodoulopoulos, Mark Summons, Saurabh Sinha, and Dan Roth
Seventh International Workshop on Statistical Relational AI (StarAI), 2017
Code on github, Poster

Learning What is Essential in Questions

Daniel Khashabi, Tushar Khot, Ashish Sabharwal, and Dan Roth
The SIGNLL Conference on Computational Natural Language Learning (CoNLL), 2017
Code on github, Poster, Spotlight

Better call Saul: Flexible Programming for Learning and Inference in NLP

Parisa Kordjamshidi, Daniel Khashabi, Christos Christodoulopoulos, Bhargav Mangipudi, Sameer Singh and Dan Roth
International Conference on Computational Linguistics (COLING), 2016
Slides, Code on github

Question Answering via Integer Programming over Semi-Structured Knowledge

Daniel Khashabi, Tushar Khot, Ashish Sabharwal, Peter Clark, Oren Etzioni and Dan Roth
International Joint Conference on Artificial Intelligence (IJCAI), 2016
Code for demonstration, Demo, UW talk, IJCAI talk, Poster

EDISON: Feature Extraction for NLP, Simplified

Mark Sammons, Christos Christodoulopoulos, Parisa Kordjamshidi, Daniel Khashabi, Vivek Srikumar, Paul Vijayakumar, Mazin Bokhari, Xinbo Wu, Dan Roth
International Conference on Language Resources and Evaluation (LREC), 2016
Poster

Combining Retrieval, Statistics, and Inference to Answer Elementary Science Questions

Peter Clark, Oren Etzioni, Daniel Khashabi, Tushar Khot, Ashish Sabharwal, Oyvind Tafjord, Peter Turney
The Conference on Artificial Intelligence (AAAI), 2016

Online Learning with Adversarial Delays

Kent Quanrad, Daniel Khashabi
Advances in Neural Information Processing Systems (NIPS), 2015
Poster

Clustering With Side Information: From a Probabilistic Model to a Deterministic Algorithm

Daniel Khashabi★, John Wieting★, Jeffrey Yufei Liu★, Feng Liang★
arXiv preprint
Relevant: A list of constrained clustering algorithms

Illinois-Profiler: Knowledge Schemas at Scale

Zhiye Fei, Daniel Khashabi, Haoruo Peng, Hao Wu and Dan Roth
IJCAI 2015 Workshop on Cognitive Knowledge Acquisition and Applications (Cognitum 2015)
Demo, Slides: PPTX PDF, Poster

Knowledge Representation: How far we have come?

Daniel Khashabi
Tech Report, Spring 2015
Slides: PPTX PDF

Solving Hard Co-reference Problems

Haoruo Peng★, Daniel Khashabi★ and Dan Roth
Conference of the North American Chapter of the Association for Computational Linguistics – Human Language Technologies (NAACL HLT 2015)
Dataset, Software, Demo, Slides: PDF PPTX, Poster

Flow of Semantics in Narratives

Daniel Khashabi, Chris J.C. Burges, Erin Renshaw, Andrzej Pastusiak, Tech Report, August 2014.
Poster: PDF, PPT

Patent: Image demosaicing

Nowozin RS, Khashabi D, Jancsary JM, Lindbloom BJ, Fitzgibbon AW, Microsoft Technology Licensing LLC, United States patent US 9,344,690. 2016 May 17.

Joint Demosaicing and Denoising via Learned Non-parametric Random Fields

Daniel Khashabi, Sebastian Nowozin, Jeremy Jancsary, Andrew W. Fitzgibbon, IEEE Transaction on Image Processing (TIP), 2014.
Publisher link, Presentation file: PDF PPT, Public data release: Link, Relevant: A list of demosaicing code available online

On Recursive Neural Networks for Relation Extraction and Entity Recognition

Daniel Khashabi
Computer Science Research and Tech Reports, May 2013.

Heteroscedastic Relevance Vector Machine

Daniel Khashabi and Feng Liang
Preliminary version on arXiv.org

Analysis and Implementation of Bayesian Methods for Modelling Correlated Multioutput Information (Multitask Learning)

Daniel Khashabi,
BSc Thesis, 2012 (In Persian)

More on Adaptive Tiled Neural Networks

Mohammad Nokhbeh-Zaeem, Daniel Khashabi and Heidar-Ali Talebi
Technical Report, 2012

Adaptive Tiled Neural Networks

M. Nokhbeh-Zaeem, D. Khashabi, H. Talebi, S. Navabi and F. Jabbarvaziri,
in IEEE International Conference on Systems, Man, and Cybernetics (SMC), 2011
Code or Code

Haar wavelet for function approximation and solving ordinary differential equations

Sayed Mohsen Moosavi Dezfooli and Daniel Khashabi
in 13th Iranian Student Conference on Electrical and Computer Engieering(ISCEE2010), 2010 (In Persian)

Design and Optimizing Digital Combinational Logic Circuits Using Genetic Algorithm

Sayed Mohsen Moosavi Dezfooli and Daniel Khashabi
in 13th Iranian Student Conference on Electrical and Computer Engieering(ISCEE2010), 2010 (In Persian), Best Paper Award!
Source and demo

C++ Programming and Numerical Methods

D. Khashabi, M. Motamedi, S. Navabi and B. Taheri
2009 (In Persian)

Nemesis Team Description

M. Norouzitallab, M. Korjani, S. Salehizadeh, A. Pourshoghi, D. Khashabi, A. Razaghpanah, P. Kaviani and M. Vosoughpour
2009.

Talks

Teaching

Past Projects and Resources

Notes

Machine Learning (Tom Mitchell), in Persian (یادگیری ماشین-محمد نخبه زعیم )