In this paper we generate distract answers for multiple-choice questions given a reference text, question, and the correct answer. We fine tune a transformer (T5) on the distraction generation task with an additional term in the loss function to penalize distractors similar to the correct answer.
Fernando Gonzalez and Kevin Golan
Final project, Natural Language Procesing @ ETH Zurich 2020
Paper Code
Given human motion sequences, we predict how the motion continues for future frames using a Temporal Inception Module (TIM).
Fernando Gonzalez, Cristina Guzman, and Zixin Shu
Final project, Machine Perception @ ETH Zurich 2021
Paper
In this paper we predict the appeal outcome decision for legal briefs submitted to U.S. appellate courts.
Anver Khusainov, Clémence Lanfranchi, Fernando Gonzalez, Naman Goel, Dominik Stammbach, and Elliott Ash
Data Science Lab @ ETH Zurich 2021
Paper
I collaborated in the development of the website that presents the Lynching in Latin America (LYLA) dataset created by researchers of the Center for Security Studies in ETH Zurich
Fernando Gonzalez and Cristina Guzman
2022