Karina Halevy

CMU LTI | Harvard CS + History


Image Description: Karina (white skin, brown hair, black top) smiling at the camera outside. Picture credits: Oriana Li Halevy, 2022.

Hello! My name is Karina, and I am a PhD student at the Carnegie Mellon University Language Technologies Institute, supported by a National Science Foundation Graduate Research Fellowship! I am co-advised by Mona Diab and Maarten Sap. My main academic interest is in natural language processing/computational linguistics.

I am specifically interested in:

  • constructing evaluation metrics and benchmark datasets to make large language models more understandable (e.g. what linguistic information are they really capturing, what latent biases do they have, why does model x perform better than model y on task z)
  • doing NLP for low-resource/non-Indo-European languages
  • carefully doing NLP for social science/social good (e.g. information extraction or visualization for long legal/medical/historical texts, hate speech detection)
  • algorithmic fairness/ethics (especially for disabled people, ethnically minoritized people, & people who are marginalized in multiple ways)
  • intersections of NLP with human-computer interaction and data visualization

I also dance.

Selected Publications

  1. preview_p2.png
    Evaluating Word Embeddings with Categorical Modularity
    Sı́lvia Casacuberta, Karina Halevy, and Damián Blasi
    In Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021, Aug 2021