Clara Meister

Clara Meister

PhD Student in Computer Science

ETH Zürich

About Me

I recently started my PhD in Computer Science with Professor Ryan Cotterell at ETH Zürich. I am passionate about the general applications of statistics and information theory to natural language processing; lately, my research has been on decoding methods for sequence models. In my free time, I like to rock climb, trail run, and search for the elusive cheap bar in Switzerland. You can check out some of my adventures on my husband’s blog:


  • Neural Machine Translation
  • Information Theory
  • Decoding Methods for Sequence Models
  • Statistical Methods for NLP


  • MSc in Computational and Mathematical Engineering, 2018

    Stanford University

  • BSc in Mathematical and Computational Science, 2017

    Stanford University



PhD Student

ETH Zürich

Feb 2020 – Present Zürich, Switzerland
PhD student in the Computer Science Department (Machine Learning Institute).

Research Assistant

ETH Zürich

Jan 2019 – Feb 2020 Zürich, Switzerland
Research assistant in the Advanced Software Technologies Lab under Professor Zhendong Su. Area of focus was on building systems for automatically testing machine translation systems.

Research Assistant

SLAC National Accelerator Laboratory

Jan 2018 – Jun 2018 Stanford, California
Research assistant with the Linac Coherent Light Source lab working with scientists to modify and enhance code base for analysis of electron pulse x-ray images generated at SLAC’s new hard x-ray free-electron laser.

Course Assistant

Stanford University Computer Science Department

Sep 2017 – Dec 2017 Stanford, California
Course assistant for CS102: Big Data- Tools and Techniques, Discoveries and Pitfalls. Taught students basic data wrangling and analysis along with visualization techniques using multiple software platforms.


Best-First Beam Search

Decoding for many NLP tasks requires a heuristic algorithm for approximating exact search since the full search space is often …

Machine Translation Testing via Pathological Invariance

Machine translation software has become heavily integrated into our daily lives due to the recent improvement in the performance of …

Structure-Invariant Testing for Machine Translation

Machine translation software has increasingly been integrated into our daily lives. People routinely use machine translation for …

Generalized Entropy Regularization or: There's Nothing Special about Label Smoothing

Prior work has explored directly regularizing the output distributions of probabilistic models to alleviates peaky (i.e. …