Kate Lin

I currently work on natural language processing and information retrieval on the Dataset Search team in Google Research.

My overarching research interests lie in building intelligent computer systems that can model human reasoning and behavior. In particular, I'm currently interested in reasoning about causality and uncertainty.

Prior to Google, I earned a BA in Computer Science from Wellesley College. I also spent some time studying computer science and cognition at MIT and Oxford.

During undergrad, I worked as an undergraduate research assistant at MIT with Zenna Tavares and Armando Solar-Lezama on causal probabilistic modeling and with Josh Tenenbaum on efficient inverse graphics for object recognition.

In summer 2021, I interned at Microsoft Research and worked with Adith Swaminathan and Harm Van Seijen on causal priors for reinforcement learning. In summer 2020, I interned on the Tensorflow Probability Team in Google Research and worked with Emily Fertig and Dave Moore on automatic structured variational inference. In summer 2019, I interned on the Structured Data Research Group in Google Research and worked with Vinh Q. Tran and Adam Lelkes to train BERT models to generate questions from passages. I spent the summer before that working on Brain Computer Interfaces at Neurable

Papers

• Relationships are Complicated! An Analysis of Relationships Between Datasets on the Web
  Kate Lin, Tarfah Alrashed, Natasha Noy
  International Semantic Web Conference (ISWC), 2024
  🏆 Best Paper Award, Research Track
  [arXiv, Google Research blog post]
• Automatic Structured Variational Inference
  Luca Ambrogioni, Kate Lin, Emily Fertig, Sharad Vikram, Max Hinne, Dave Moore, Marcel van Gerven
  International Conference on Artificial Intelligence and Statistics (AISTATS), 2021
  [arXiv, repository, tutorial]
• Causal Inductive Synthesis Corpus
  Zenna Tavares, Ria Das, Elizabeth Weeks, Kate Lin, Joshua B Tenenbaum, Armando Solar-Lezama
  NeurIPS Workshop on Computer Assisted Programming, 2020
  [OpenReview, poster]
• Cross-Subject EEG Event-Related Potential Classification for Brain-Computer Interfaces Using Residual Networks
  Arnaldo Pereira, Dereck Padden, Jay Jantz, Kate Lin, Ramses Alcaide-Aguirre
  [HAL preprint]

Invited Talks

• Open Ecosystem For Dataset Discovery
  Keynote Talk at DOME 4.0 Hackathon