Adam Poliak

Adam Poliak

Hi, I'm Adam Poliak. I am a PhD candidate at Johns Hopkins University studying Computer Science and am affiliated with the Center for Language & Speech Processing.

I study Machine Learning and Natural Language Processing, with a focus primarily on Natural Language Understanding and Computational Semantics. The long term goal of my research is to develop models and systems that can make inferences from texts. I am working with my advisor Professor Benjamin Van Durme on the Decompositional Semantics Initiative (Decomp).

In Fall 2019, I am TA-ing Artificial Intelligence (601.464/664).

Feel free to reach out to me at



  • Don’t Take the Premise for Granted: Mitigating Artifacts in Natural Language Inference
    Yonatan Belinkov*, Adam Poliak*, Stuart M. Shieber, Benjamin Van Durme, Alexander Rush. ACL. [paper][bib][code][video][Media: Harvard News]
  • On Adversarial Removal of Hypothesis-only Bias in Natural Language Inference
    Yonatan Belinkov*, Adam Poliak*, Stuart M. Shieber, Benjamin Van Durme, Alexandar Rush. *SEM. [paper][bib][code]
  • Probing what different NLP tasks teach machines about function word comprehension
    Najoung Kim, Roma Patel, Adam Poliak, Patrick Xia, Alex Wang, R. Thomas Mccoy, Ian Tenney, Alexis Ross, Tal Linzen, Benjamin Van Durme, Samuel Bowman, Ellie Pavlick. *SEM. [paper][bib][data] Best Paper Award
  • What do you learn from context? Probing for sentence structure in contextualized word representations
    Ian Tenney, Patrick Xia, Berlin Chen, Alex Wang, Adam Poliak, R. Thomas McCoy, Najoung Kim, Benjamin Van Durme, Samuel R. Bowman, Dipanjan Das, Ellie Pavlick. ICLR. [paper][bib]


  • Collecting Diverse Natural Language Inference Problems for Sentence Representation Evaluation
    Adam Poliak, Aparajita Haldar, Rachel Rudinger, J. Edward Hu, Ellie Pavlick, Aaron Steven White, Benjamin Van Durme. EMNLP. [paper][data][poster][slides][video][bib].
  • Hypothesis Only Baselines in Natural Language Inference
    Adam Poliak, Jason Naradowsky, Aparajita Haldar, Rachel Rudinger, Benjamin Van Durme. *SEM [paper][bib][code][slides]. Best Paper Award
  • On the Evaluation of Semantic Phenomena in Neural Machine Translation Using Natural Language Inference
    Adam Poliak, Yonatan Belinkov, Jim Glass, Benjamin Van Durme. NAACL.[paper][bib][code]
  • Neural Variational Entity Set Expansion for Automatically Populated Knowledge Graphs
    Pushpendre Rastogi, Adam Poliak, Vince Lyzinski, and Benjamin Van Durme. Information Retrieval Journal. [paper][bib]


  • CADET: Computer Assisted Discovery Extraction and Translation.
    Benjamin Van Durme, Tom Lippincott, Kevin Duh, Deana Burchfield, Adam Poliak, Cash Costello, Tim Finin, Scott Miller, James Mayfield, Philipp Koehn, Craig Harman, Dawn Lawrie, Chandler May, Max Thomas, Annabelle Carrell, Julianne Chaloux, Tongfei Chen, Alex Comerford, Mark Dredze, Benjamin Glass, Shudong Hao, Patrick Martin, Pushpendre Rastogi, Rashmi Sankepally, Travis Wolfe, Ying-Ying Tran and Ted Zhang. IJCNLP Demo 2017. [paper][code][bib]
  • Frame-Based Continuous Lexical Semantics through Exponential Family Tensor Factorization and Semantic Proto-Roles. Francis Ferraro, Adam Poliak, Ryan Cotterell and Benjamin Van Durme. *SEM 2017. [paper][poster][bib]
  • Efficient, Compositional, Order-sensitive n-gram Embeddings. Adam Poliak*, Pushpendre Rastogi*, M. Patrick Martin and Benjamin Van Durme. EACL 2017. [paper][code][data][poster][bib]
  • Explaining and Generalizing Skip-Gram through Exponential Family Principal Component Analysis. Ryan Cotterell, Adam Poliak, Benjamin Van Durme and Jason Eisner. EACL 2017. [paper][code][poster][bib]
  • Semantic Proto-Role Labeling. Adam Teichert, Adam Poliak, Benjamin Van Durme, Matthew R. Gormley. Thirty-First Conference on Artificial Intelligence (AAAI 2017). [paper][bib]
  • Generating Automatic Pseudo-entailments from AMR Parses. Adam Poliak and Benjamin Van Durme. 6th Mid-Atlantic Student Colloquium on Speech, Language and Learning (MASC-SLL) 2017. Extended Abstract. [paper][bib]