Vivek Srikumar

Research Interests
Publications
Code for recent papers
Tutorials

Research

I am interested in research questions arising from the need to manage, analyze and understand large amounts of unstructured data, particularly in textual form. My research lies in the areas of machine learning and natural language processing.

In particular, I am interested in the following broad questions:

Text understanding: What does text understanding mean? How can we represent and transform text into a computer-understandable form to perform machine reading and textual inference?
Learning Representations: How can we learn to represent inputs and outputs in real or discrete spaces that makes it easy to build predictors, especially of the structured variety?
Structured learning, especially with very little supervision: Many text understanding problems can be phrased as that of predicting a structured representation of text. How do we take advantage of the structure to help to efficiently learn a predictor in spite of having very little annotated data?
Structured prediction: Predicting structures is a combinatorial optimization problem. How can we make this faster and scalable?

Elsewhere: Google scholar, DBLP, arXiv, Semantic Scholar

Publications

The list of publications here is almost never current. See Google scholar for the most up-to-date list of publications.

Psychotherapy is Not One Thing: Simultaneous Modeling of Different Therapeutic Approaches. Maitrey Mehta, Derek Caperton, Katherine Axford, Lauren Weitzman, David Atkins, Vivek Srikumar and Zac Imel. Proceedings of the Eighth Workshop on Computational Linguistics and Clinical Psychology, 2022.
[pdf] [details]
Is My Model Using The Right Evidence? Systematic Probes for Examining Evidence-Based Tabular Reasoning. Vivek Gupta, Riyaz A Bhat, Atreya Ghosal, Manish Shrivastava, Maneesh Singh and Vivek Srikumar. Transactions of the Association for Computational Linguistics, volume 10, 2022.
[pdf] [details]
Putting Context in SNACS: A 5-Way Classification of Adpositional Pragmatic Markers. Yang Janet Liu, Jena D. Hwang, Nathan Schneider and Vivek Srikumar. Proceedings of The 16th Lingusitic Annotation Workshop (LAW-XVI), 2022.
[pdf] [details]
Pylon: A PyTorch Framework for Learning with Constraints. Kareem Ahmed, Tao Li, Thy Ton, Quan Guo, Kai-Wei Chang, Parisa Kordjamshidi, Vivek Srikumar, Guy van Den Broeck and Sameer Singh. Proceedings of the NeurIPS 2021 Competitions and Demonstrations Track, 2022.
[link] [details]
REFLACX, a dataset of reports and eye-tracking data for localization of abnormalities in chest x-rays. Ricardo Bigolin Lanfredi, Mingyuan Zhang, William F. Auffermann, Jessica Chan, Phuong-Anh T Duong, Vivek Srikumar, Trafton Drew, Joyce D Schroeder and Tolga Tasdizen. Scientific Data, volume 9, 1, 2022.
[link] [details]
Right for the Right Reason: Evidence Extraction for Trustworthy Tabular Reasoning. Vivek Gupta, Shuo Zhang, Alakananda Vempala, Yujie He, Temma Choji and Vivek Srikumar. Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (ACL), 2022.
[pdf] [details]
An Interactive Visual Demo of Bias Mitigation Techniques for Word Representations From a Geometric Perspective. Archit Rathore, Sunipa Dev, Vivek Srikumar, Jeff Phillips, Yan Zheng, Michael Yeh, Junpeng Wang, Wei Zhang and Bei Wang. Proceedings of the NeurIPS 2021 Competitions and Demonstrations Track, 2022.
[link] [details]
A Closer Look at How Fine-tuning Changes BERT. Yichu Zhou and Vivek Srikumar. Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (ACL), 2022.
[pdf] [details]
OSCaR: Orthogonal Subspace Correction and Rectification of Biases in Word Embeddings. Sunipa Dev, Tao Li, Jeff Phillips and Vivek Srikumar. Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing (EMNLP), 2021.
[pdf] [details]
Putting Words in BERT's Mouth: Navigating Contextualized Vector Spaces with Pseudowords. Taelin Karidi, Yichu Zhou, Nathan Schneider, Omri Abend and Vivek Srikumar. Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing (EMNLP), 2021.
[pdf] [details]
Automatic Entity State Annotation using the VerbNet Semantic Parser. Ghazaleh Kazeminejad, Martha Palmer, Tao Li and Vivek Srikumar. Proceedings of The Joint 15th Linguistic Annotation Workshop (LAW) and 3rd Designing Meaning Representations (DMR) Workshop, 2021.
[pdf] [details]
X-Fact: A New Benchmark Dataset for Multilingual Fact Checking. Ashim Gupta and Vivek Srikumar. Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics (ACL), 2021.
[pdf] [details]
Evaluating Relaxations of Logic for Neural Networks: A Comprehensive Study. Mattia Medina Grespan, Ashim Gupta and Vivek Srikumar. Proceedings of the International Joint Conference on Artificial Intelligence (IJCAI), 2021.
[pdf] [details]
Incorporating External Knowledge to Enhance Tabular Reasoning. J. Neeraja, Vivek Gupta and Vivek Srikumar. Proceedings of the 2021 Annual Conference of the North American Chapter of the Association for Computational Linguistics, 2021.
[pdf] [details]
DirectProbe: Studying Representations without Classifiers. Yichu Zhou and Vivek Srikumar. Proceedings of the 2021 Annual Conference of the North American Chapter of the Association for Computational Linguistics, 2021.
[pdf] [details]
How Do You Feel? Using Natural Language Processing to Automatically Rate Emotion in Psychotherapy. Michael Tanana, Christina Soma, Patty B. Kuo, Nicolas M. Bertagnolli, Aaron Dembe, Brian T. Pace, Vivek Srikumar, David Atkins and Zac Imel. Behavior Research Methods, volume 53, 5, 2021.
[link] [details]
BERT & Family Eat Word Salad: Experiments with Text Understanding. Ashim Gupta, Giorgi Kvernadze and Vivek Srikumar. AAAI, 2021.
[pdf] [details]
SweetPea: A Standard Language for Factorial Experimental Design. Sebastian Musslick, Annie Cherkaev, Ben Draut, Ahsan Butt, Pierce Darragh, Vivek Srikumar, Matthew Flatt and Jonathan D. Cohen. Behavior Research Methods, volume 54, 2, 2021.
[link] [details]
Supertagging the Long Tail with Tree-Structured Decoding of Complex Categories. Jakob Prange, Nathan Schneider and Vivek Srikumar. Transactions of the Association for Computational Linguistics, volume 9, 2021.
[pdf] [details]
Sprucing up Supersenses: Untangling the Semantic Clusters of Accompaniment and Purpose. Jena D. Hwang, Nathan Schneider and Vivek Srikumar. Proceedings of the 14th Linguistic Annotation Workshop, 2020.
[pdf] [details]
UNQOVERing Stereotyping Biases via Underspecified Questions. Tao Li, Tushar Khot, Daniel Khashabi, Ashish Sabarwal and Vivek Srikumar. Findings of EMNLP, 2020.
[pdf] [details]
InfoTabS: Inference on Tables as Semi-structured Data. Vivek Gupta, Pegah Nokhiz, Maitrey Mehta and Vivek Srikumar. Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, 2020.
[pdf] [details]
Structured Tuning for Semantic Role Labeling. Tao Li, Parth Anand Jawale, Martha Palmer and Vivek Srikumar. Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, 2020.
[pdf] [details]
Learning Constraints for Structured Prediction Using Rectifier Networks. Xingyuan Pan, Maitrey Mehta and Vivek Srikumar. Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, 2020.
[pdf] [details]
On Measuring and Mitigating Biased Inferences of Word Embeddings. Sunipa Dev, Tao Li, Jeff Phillips and Vivek Srikumar. AAAI, 2020.
[pdf] [details]
Prediction of Obstructive Lung Disease from Chest Radiographs via Deep Learning Trained on Pulmonary Function Data. Joyce D Schroeder, Ricardo Bigolin Lanfredi, Tao Li, Jessica Chan, Clement Vachet, Robert Paine III, Vivek Srikumar and Tolga Tasdizen. International Journal of Chronic Obstructive Pulmonary Disease, volume 15, 2020.
[link] [details]
On the Limits of Learning to Actively Learn Semantic Representations. Omri Koshorek, Gabriel Stanovsky, Yichu Zhou, Vivek Srikumar and Jonathan Berant. Proceedings of the Conference on Natural Language Learning (CoNLL), 2019.
[pdf] [details] [Best paper honorable mention]
A Logic-Driven Framework for Consistency of Neural Models. Tao Li, Vivek Gupta, Maitrey Mehta and Vivek Srikumar. Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP), 2019.
[pdf] [details]
Observing Dialogue in Therapy: Categorizing and Forecasting Behavioral Codes. Jie Cao, Michael Tanana, Zac Imel, Eric Poitras, David Atkins and Vivek Srikumar. Annual Meeting of the Association for Computational Linguistics (ACL), 2019.
[pdf] [details]
Augmenting Neural Networks with First-order Logic. Tao Li and Vivek Srikumar. Annual Meeting of the Association for Computational Linguistics (ACL), 2019.
[pdf] [details]
Preparing SNACS for Subjects and Objects. Adi Shalev, Jena D. Hwang, Nathan Schneider, Vivek Srikumar, Omri Abend and Ari Rappoport. The First International Workshop on Designing Meaning Representations (DMR), 2019.
[pdf] [details]
Beyond Context: A New Perspective for Word Embeddings. Yichu Zhou and Vivek Srikumar. *SEM, 2019.
[pdf] [details]
NLIZE: A Perturbation-Driven Visual Interrogation Tool for Analyzing and Interpreting Natural Language Inference Models. Shusen Liu, Zhimin Li, Tao Li, Vivek Srikumar, Valerio Pascucci and Peer-Timo Bremer. IEEE Transactions on Visualization and Computer Graphics, volume 25, 1, 2019.
[pdf] [details]
Development and evaluation of ClientBot: A patient-like conversational agent to train basic counseling skills. Michael Tanana, Christina Soma, Vivek Srikumar, David Atkins and Zac Imel. Journal of Medical Internet Research, volume 21, 7, 2019.
[link] [details]
Visual Interrogation of Attention-Based Models for Natural Language Inference and Machine Comprehension. Shusen Liu, Tao Li, Zhimin Li, Vivek Srikumar, Valerio Pascucci and Peer-Timo Bremer. Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP): System Demonstrations, 2018.
[pdf] [details]
Newton: Gravitating Towards the Physical Limits of Crossbar Acceleration. Anirban Nag, Ali Shafiee, Rajeev Balasubramonian, Vivek Srikumar, Ross Walker, John Paul Strachan and Naveen Muralimanohar. IEEE Micro, volume 38, 5, 2018.
[pdf] [details]
Learning to Speed Up Structured Output Prediction. Xingyuan Pan and Vivek Srikumar. Proceedings of the International Conference on Machine Learning (ICML), 2018.
[pdf] [details]
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 and Dan Roth. Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC), 2018.
[pdf] [details]
Visual Exploration of Semantic Relationships in Neural Word Embeddings. Shusen Liu, Peer-Timo Bremer, Jayaraman J. Thiagarajan, Vivek Srikumar, Bei Wang, Yarden Livnat and Valerio Pascucci. IEEE Transactions on Visualization and Computer Graphics, volume 24, 2018.
[pdf] [details]
Predicting electricity consumption for commercial and residential buildings using deep recurrent neural networks. Aowabin Rahman, Vivek Srikumar and Amanda D. Smith. Applied Energy, volume 212, 2018.
[link] [details]
Comprehensive supersense disambiguation of English prepositions and possessives. Nathan Schneider, Jena D. Hwang, Vivek Srikumar, Jakob Prange, Austin Blodgett, Sarah Moeller, Aviram Stern, Adi Bitan and Omri Abend. Annual Meeting of the Association for Computational Linguistics (ACL), 2018.
[pdf] [details]
DeepLog: Anomaly Detection and Diagnosis from System Logs through Deep Learning. Min Du, Feifei Li, Guineng Zheng and Vivek Srikumar. Proceedings of 24th ACM Conference on Computer and Communications Security, 2017.
[pdf] [details]
Double Trouble: The Problem of Construal in Semantic Annotation of Adpositions. Jena D. Hwang, Archna Bhatia, Na-Rae Han, Tim O'Gorman, Vivek Srikumar and Nathan Schneider. *SEM, 2017.
[pdf] [details]
An Algebra for Feature Extraction. Vivek Srikumar. Annual meeting of the Association of Computational Linguistics (ACL), 2017.
[pdf] [details]
Integer Linear Programming Formulations in Natural Language Processing. Dan Roth and Vivek Srikumar. EACL, 2017.
[link] [details]
Coping with Construals in Broad-Coverage Semantic Annotation of Adpositions. Jena D. Hwang, Archna Bhatia, Na-Rae Han, Tim O'Gorman, Vivek Srikumar and Nathan Schneider. AAAI Spring Symposium on Computational Construction Grammar and Natural Language Understanding, 2017.
[pdf] [details]
Exploiting Sentence Similarities for Better Alignments. Tao Li and Vivek Srikumar. Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP), 2016.
[pdf] [details]
Continuous Kernel Learning. John Moeller, Vivek Srikumar, Sarathkrishna Swaminathan, Suresh Venkatasubramanian and Dustin Webb. European Conference on Machine Learning (ECML), 2016.
[pdf] [details]
A corpus of preposition supersenses in English web reviews. Nathan Schneider, Jena D. Hwang, Vivek Srikumar, Abhijit Suresh, Meredith Green, Kathryn Conger, Tim O'Gorman and Martha Palmer. Linguistic Annotation Workshop, 2016.
[pdf] [details]
Expressiveness of Rectifier Networks. Xingyuan Pan and Vivek Srikumar. Proceedings of the International Conference on Machine Learning (ICML), 2016.
[pdf] [details]
ISAAC: A Convolutional Neural Network Accelerator with In-Situ Analog Arithmetic in Crossbars. Ali Shafiee, Anirban Nag, Naveen Muralimanohar, Rajeev Balasubramonian, John Paul Strachan, Miao Hu, R. Stanley Williams and Vivek Srikumar. ISCA, 2016.
[pdf] [details] [IEEE Micro top picks of the year, honorable mention]
Is Sentiment in Movies the Same as Sentiment in Psychotherapy? Comparisons Using a New Psychotherapy Sentiment Database. Michael Tanana, Aaron Dembe, Christina Soma, David Atkins, Zac Imel and Vivek Srikumar. Proceedings of the 3nd Workshop on Computational Linguistics and Clinical Psychology: From Linguistic Signal to Clinical Reality, 2016.
[pdf] [details]
EDISON: Feature Extraction for NLP, Simplified. Mark Sammons, Christos Christodoulopoulos, Parisa Kordjamshidi, Daniel Khashabi, Vivek Srikumar, Paul Vijayakumar, Mazin Bokhari, Xinbo Wu and Dan Roth. Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC'16), 2016.
[pdf] [details]
Learning and Inference in Structured Prediction Models. Kai-Wei Chang, Gourab Kundu, Dan Roth and Vivek Srikumar. AAAI-16 Tutorial Forum, 2016.
[link] [details]
A Comparison of Natural Language Processing Methods for Automated Coding of Motivational Interviewing. Michael Tanana, Kevin Hallgren, Zac Imel, David Atkins and Vivek Srikumar. Journal of Substance Abuse Treatment, volume 65, 2016.
[link] [details]
RhymeDesign: A Tool for Analyzing Sonic Devices in Poetry. Nina McCurdy, Vivek Srikumar and Miriah Meyer. Proceedings of the Fourth Workshop on Computational Linguistics for Literature, 2015.
[pdf] [details]
A Hierarchy with, of, and for Preposition Supersenses. Nathan Schneider, Vivek Srikumar, Jena D. Hwang and Martha Palmer. Linguistic Annotation Workshop, 2015.
[pdf] [details]
Recursive Neural Networks for Coding Therapist and Patient Behavior in Motivational Interviewing. Michael Tanana, Kevin Hallgren, Zac Imel, David Atkins, Padhraic Smyth and Vivek Srikumar. Proceedings of the 2nd Workshop on Computational Linguistics and Clinical Psychology: From Linguistic Signal to Clinical Reality, 2015.
[pdf] [details]
Learning Distributed Representations for Structured Output Prediction. Vivek Srikumar and Christopher D. Manning. Advances in Neural Information Processing Systems, 2014.
[pdf] [details] [Spotlight presentation]
Modeling Biological Processes for Reading Comprehension. Jonathan Berant, Vivek Srikumar, Pei-Chun Chen, Abby Vander Linden, Brittany Harding, Brad Huang, Peter Clark and Christopher D. Manning. Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP), 2014.
[pdf] [details] [Best paper award]
WOLFE: Strength Reduction and Approximate Programming for Probabilistic Programming. Sebastian Riedel, Sameer Singh, Vivek Srikumar, Tim Rocktäschel, Larysa Visengeriyeva and Jan Noessner. International Workshop on Statistical Relational AI (StarAI), 2014.
[pdf] [details]
Correcting Grammatical Verb Errors. Alla Rozovskaya, Dan Roth and Vivek Srikumar. Conference of the European Chapter of the ACL (EACL), 2014.
[pdf] [details]
Multi-core Structural SVM Training. Kai-Wei Chang, Vivek Srikumar and Dan Roth. European Conference on Machine Learning (ECML), 2013.
[pdf] [details]
The Semantics of Role Labeling. Vivek Srikumar. University of Illinois at Urbana-Champaign PhD thesis, 2013.
[pdf] [details]
Margin-based Decomposed Amortized Inference. Gourab Kundu, Vivek Srikumar and Dan Roth. Annual meeting of the Association of Computational Linguistics (ACL), 2013.
[pdf] [details]
Modeling Semantic Relations Expressed by Prepositions. Vivek Srikumar and Dan Roth. Transactions of the Association for Computational Linguistics (TACL), volume 1, 2013.
[pdf] [details]
On Amortizing Inference Cost for Structured Prediction. Vivek Srikumar, Gourab Kundu and Dan Roth. Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP), 2012.
[pdf] [details]
Learning Shared Body Plans. Ian Endres, Vivek Srikumar, Ming-Wei Chang and Derek Hoiem. Conference on Computer Vision and Pattern Recognition (CVPR), 2012.
[pdf] [details]
Predicting Structures in NLP: Constrained Conditional Models and Integer Linear Programming in NLP. Dan Goldwasser, Vivek Srikumar and Dan Roth. NAACL HLT Tutorial Abstracts, 2012.
[pdf] [details]
An NLP Curator (or: How I Learned to Stop Worrying and Love NLP Pipelines). James Clarke, Vivek Srikumar, Mark Sammons and Dan Roth. Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC'12), 2012.
[pdf] [details]
A Joint Model for Extended Semantic Role Labeling. Vivek Srikumar and Dan Roth. Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP), 2011.
[pdf] [details]
Discriminative Learning over Constrained Latent Representations. Ming-Wei Chang, Dan Goldwasser, Dan Roth and Vivek Srikumar. Human Language Technologies: The 2010 Annual Conference of the North American Chapter of the Association for Computational Linguistics, 2010.
[pdf] [details]
Structured Output Learning with Indirect Supervision. Ming-Wei Chang, Vivek Srikumar, Dan Goldwasser and Dan Roth. Proceedings of the International Conference on Machine Learning (ICML), 2010.
[pdf] [details]
Relation Alignment for Textual Entailment Recognition. Mark Sammons, V.G. Vinod Vydiswaran, Tim Vieira, Nikhil Johri, Ming-Wei Chang, Dan Goldwasser, Vivek Srikumar, Gourab Kundu, Yuancheng Tu, Kevin Small, Joshua Rule, Quang Do and Dan Roth. Text Analysis Conference (TAC), 2009.
[pdf] [details]
Importance of Semantic Represenation: Dataless Classification. Ming-Wei Chang, Lev Ratinov, Dan Roth and Vivek Srikumar. Proceedings of the National Conference on Artificial Intelligence (AAAI), 2008.
[pdf] [details]
Proactive Intrusion Detection. Benjamin Liebald, Dan Roth, Neelay Shah and Vivek Srikumar. Proceedings of the National Conference on Artificial Intelligence (AAAI), 2008.
[pdf] [details]
Extraction of Entailed Semantic Relations Through Syntax-based Comma Resolution. Vivek Srikumar, Roi Reichart, Mark Sammons, Ari Rappoport and Dan Roth. Proceedings of ACL-08: HLT, 2008.
[pdf] [details]

Expository Articles, Unpublished Manuscripts and Tech Reports

A Simple Global Neural Discourse Parser. Yichu Zhou, Omri Koshorek, Vivek Srikumar and Jonathan Berant. arXiv preprint arXiv:2009.01312, 2020.
[pdf] [details]
Learning In Practice: Reasoning About Quantization. Annie Cherkaev, Waiming Tai, Jeff Phillips and Vivek Srikumar. arXiv preprint arXiv:1905.11478, 2019.
[pdf] [details]
Adposition Supersenses v2. Nathan Schneider, Jena D. Hwang, Archna Bhatia, Na-Rae Han, Vivek Srikumar, Tim O'Gorman and Omri Abend. arXiv preprint arXiv:1704.02134, 2017.
[link] [details]
An Inventory of Preposition Relations. Vivek Srikumar and Dan Roth. arXiv preprint arXiv:1305.5785, 2013.
[pdf] [details]
Soft Constraints in Integer Linear Programs. Vivek Srikumar. Unpublished note, 2013.
[pdf] [details]
A brief introduction to inference using Lagrangian Relaxation. Vivek Srikumar. Unpublished note, 2012.
[pdf] [details]
Conceptual Search and Text Categorization. Lev Ratinov, Dan Roth and Vivek Srikumar. University of Illinois Technical Report, UIUCDCS-R-2008-2932, 2008.
[pdf] [details]
Proactive Detection of Insider Attacks. Benjamin Liebald, Dan Roth, Neelay Shah and Vivek Srikumar. University of Illinois Technical Report, UIUCDCS-R-2007-2879, 2007.
[pdf] [details]

Code for recent papers

The code for my recent papers is available at the Utah NLP github repository. Please follow the github projects and let us know if things don’t work.