Research

How is the brain able to process an infinitude of expressions composed from a small number of elements? What are the computational principles underlying symbolic manipulation in the human mind? How does symbolic computation emerge from computations in neural networks? These questions are intimately related to our ability to learn and deeply understand natural language — arguably one of the key components of human intelligence, and most certainly a required step in our journey for brain-like AI.

As a PhD candidate at Stanford, advised by Dan Jurafsky, Chris Potts and Josh Greene, I study these research questions in the intersection between Computational Linguistics, Computer Science, and Cognitive Neuroscience.

In my work, I develop Deep Reinforcement Learning models that learn compositional semantics in a systematic way. In particular, I’m interested in the role that memory plays in these architectures as a catalyst in the emergence of symbolic computation from the underlying substratum.

What's New

• Learning to Learn without Forgetting by Maximizing Transfer and Minimizing Interference with Matt Riemer, Robert Ajemian, Miao Liu, Irina Rish, Yuhai Tu, and Gerald Tesauro
• Continual Learning by Maximizing Transfer and Minimizing Interference with Matt Riemer, Robert Ajemian, Miao Liu, Irina Rish, Yuhai Tu, and Gerald Tesauro
• Learning to Compose with Scratchpad Memory, with Andrej Barbu, Yen-Ling Kuo, Diego Mendoza-Halliday and Boris Katz

Papers related to Computational Linguistics

• Cases, Ignacio, Thang Luong, and Christopher Potts
  2017 On the effective use of pretraining for Neural Natural Language Inference. arXiv:1710.02076
• Huang, Ruihong, Ignacio Cases, Dan Jurafsky, Cleo Condoravdi, and Ellen Riloff
  2016 Distinguishing Past, On-going, and Future Events: The EventStatus Corpus. EMNLP’16. Austin, Texas.
• Liu, Ting, Kit Cho, George Aaron Broadwell, Samira Shaikh, Tomek Strzalkowski, John Lien, Sarah Taylor, Laurie Feldman, Boris Yamrom, Nick Webb, Umit Boz, Ignacio Cases and Ching-Sheng Lin
  2014 Automatic Expansion of the MRC Psycholinguistic Database Imageability Ratings. Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC-2014). Reykjavik, Iceland.
• Shaikh, Samira, Tomek Strzalkowski, Ting Liu, George Aaron Broadwell, Boris Yamrom, Sarah Taylor, Laurie Feld- man, Kit Cho, Umit Boz, Ignacio Cases, Yuliya Peshkova, Ching-Sheng Lin
  2014 A Multi-Cultural Repository of Automatically Discovered Linguistic and Conceptual Metaphors. Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC-2014). Reykjavik, Iceland.
• Strzalkowski, Tomek, Samira Shaikh, Kit Cho, George Aaron Broadwell, Laurie Feldman, Sarah Taylor, Boris Yam- rom, Ting Liu, Ignacio Cases, Yuliya Peshkova, Kyle Elliot
  2014 Computing Affect in Metaphors. Proceedings of the Second Workshop on Metaphor in NLP. Baltimore, MD.
• Shaikh, Samira, Tomek Strzalkowski, Kit Cho, Ting Liu, George Aaron Broadwell, Laurie Feldman, Sarah Taylor, Boris Yamrom, Ching-Sheng Lin, Ning Sa, Ignacio Cases, Yuliya Peshkova, Kyle Elliot
  2014 Discovering Conceptual Metaphors using Source Domain Spaces. Proceedings of the 4th Workshop on Cognitive Aspects of the Lexicon (CogALex). Dublin, Ireland.
• Broadwell, George Aaron, Umit Boz, Ignacio Cases, Tomek Strzalkowski, Sarah Taylor, Laurie Feldman, Samira Shaikh, Ting Liu, Kit Cho, and Nick Webb
  2013 Using Imageability and Topic Chaining to Locate Metaphors in Linguistic Corpora. The 2013 International Conference on Social Computing, Behavioral-Cultural Modeling, & Prediction. Washington D.C.
• Taylor, Sarah, Laurie Feldman, Kit Cho, Samira Shaikh, Ignacio Cases, Yuliya Peshkova, George Aaron Broadwell, Tim Liu, Umit Boz, Kyle Elliott, Boris Yamrom, and Tomek Strzalkowski
  2013 Extracting understanding from automated metaphor identification: Contrasting concepts of poverty across cultures and languages. 5th International Conference on Applied Human Factors and Ergonomics (AHFE 2014). Kraków, Poland.
• Strzalkowski, Tomek, George Aaron Broadwell, Sarah Taylor, Laurie Feldman, Boris Yamrom, Samira Shaikh, Ting Liu, Kit Cho, Umit Boz, Ignacio Cases and Kyle Elliott
  2013 Robust Extraction of Metaphors from Novel Data. NAACL-2013 Workshop on Metaphors, Atlanta, GA.

About me

Before coming to Stanford I worked during my Masters in the development and application of AI techniques to the process of automated deciphering of writing systems. My undergraduate studies in Physics (Astrophysics) made me passioned about Mathematics and specially Numerical Analysis, Machine Learning, Signal Processing, and Computer Vision.

My email is my surname at my university dot edu.