Do BERTs Learn to Use Browser User Interface? Exploring Multi-Step Tasks with Unified Vision-and-Language BERTs.

Taichi Iki Akiko Aizawa

Published in: CoRR (2022)

Keyphrases

multi step
user interface
visually guided
programming language
computer vision
vision system
single step
lower bounding
knn
natural language
user interaction
data sets
k nearest neighbor
human computer interaction
web browser
machine learning
neural network
text mining
web pages
tumor classification