Maria Ryskina

[spelling and pronouncing my name]


I am a PhD candidate at the Language Technologies Institute of the School of Computer Science at Carnegie Mellon University. I am fortunate to be advised by Matt Gormley, Eduard Hovy, and Taylor Berg-Kirkpatrick.

My research takes an interdisciplinary approach to natural language processing, bringing together machine learning (latent variable models, finite-state models, unsupervised learning) and computational linguistics (morphology, linguistic typology, language change, psycholinguistics). I aim both to uncover new linguistic knowledge using computational methods and to leverage this knowledge to improve NLP applications.

I recieved my bachelor’s and master’s degrees from the Moscow Institute of Physics and Technology and Skoltech. I worked on my master’s thesis at MIT InfoLab. In 2020, I interned at DiDi Labs with Kevin Knight.

I am a member of BergLab and LLab. In my spare time, I play quiz games and sing with the D♭ Singers.

I am searching for postdoc positions! Please email me if you think I would be a good fit for your lab.


Nov 11, 2021 We are presenting our work on Learning Mathematical Properties of Integers at BlackboxNLP 2021! Come find us at virtual poster sessions 11:00–12:00 and 14:45–16:15 Punta Cana time.
Nov 8, 2021 I passed my thesis proposal and am now a PhD candidate! 🎉
Nov 3, 2021 I am giving a talk on informal romanization at the NLP with Friends seminar on November 3 at 14:00 UTC! Contact me for the Zoom link or watch on YouTube.
Oct 20, 2021 mildlyoverfitted created a video tutorial for our integer embedding probing experiments!
Oct 8, 2021 Abhilasha Ravichander is giving an invited talk on our NoiseQA work at the Search-Oriented Conversational AI workshop – watch the session here.

selected publications

  1. BlackboxNLP
    Learning Mathematical Properties of Integers
    Maria Ryskina and Kevin Knight
    In Proceedings of the Fourth BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP 2021
  2. ACL
    Phonetic and Visual Priors for Decipherment of Informal Romanization
    In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics 2020
  3. SCiL
    Where New Words Are Born: Distributional Semantic Analysis of Neologisms and Their Semantic Neighborhoods
    In Proceedings of the Society for Computation in Linguistics 2020
  4. ACL
    Automatic Compositor Attribution in the First Folio of Shakespeare
    In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics 2017