no code implementations • 4 Dec 2022 • Benjamin Muller, Deepanshu Gupta, Siddharth Patwardhan, Jean-Philippe Fauconnier, David Vandyke, Sachin Agarwal
For a given language, we are able to predict zero-shot performance, that increases on a logarithmic scale with the number of few-shot target language data points.
no code implementations • 9 Feb 2022 • Jiawen Zhang, Abhijit Mishra, Avinesh P. V. S, Siddharth Patwardhan, Sachin Agarwal
In this work, we propose a potentially data-efficient approach that reuses existing systems for (a) image analysis, (b) question rewriting, and (c) text-based question answering to answer such visual questions.
no code implementations • 14 Jan 2022 • Huiting Liu, Avinesh P. V. S., Siddharth Patwardhan, Peter Grasch, Sachin Agarwal
For this study, we propose a methodology for the assessment of model stability (which we refer to as jitter under various experimental conditions.