Ryo Kamoi

Ryo Kamoi

I’m interested in building reliable and explainable NLP systems. I received a master’s degree in Computer Science from the University of Texas at Austin where I was advised by Professor Greg Durrett, and received a bachelor’s degree in Statistics from Keio University where I was advised by Professor Kei Kobayashi.

  • Natural Language Generation
  • Interpretability, Explainability
  • M.S. in Computer Science, 2020 - 2022

    University of Texas at Austin

  • B.E. in Statistics, 2016 - 2020

    Keio University

(2023). WiCE: Real-World Entailment for Claims in Wikipedia. arXiv preprint arXiv:2303.01432. PDF Cite Dataset

AI Safety

(2021). Efficient Unknown Object Detection with Discrepancy Networks for Semantic Segmentation. NeurIPS Workshop on Machine Learning for Autonomous Driving. PDF Cite
(2020). Out-of-Distribution Detection with Likelihoods Assigned by Deep Generative Models Using Multimodal Prior Distributions. The AAAI’s Workshop on Artificial Intelligence Safety. PDF Cite
(2020). Why is the Mahalanobis Distance Effective for Anomaly Detection?. arXiv preprint arXiv:2003.00402. Cite URL

Others

(2020). Alternative methods for fast and stable GAN. MIRU. Cite
 
 
 
 
 
Amazon - Applied Scientist Internship Jul 2021 – Dec 2021 Cambridge, U.K.
Research in Quality Evaluation of Alexa
 
 
 
 
 
SenseTime Japan - Research Internship Feb 2020 – Jan 2021 Tokyo, Japan
Research in Obstacle Detection for Autonomous Driving Systems
 
 
 
 
 
Datasection - Research Internship May 2017 – Aug 2018 Tokyo, Japan
Research in Natural Language Generation with Small Training Data
Scholarship for alumni of Keio University to pursue degrees at overseas graduate schools
Graduation with highest honors - First place in the Department of Mathematics at Keio University