Do Transformers Parse while Predicting the Masked Word?

Haoyu Zhao Abhishek Panigrahi Rong Ge Sanjeev Arora

Published in: CoRR (2023)

Keyphrases

n gram
word sense disambiguation
co occurrence
stochastic grammar
predicting future
linguistic knowledge
parse tree
language independent
microsoft word
text corpus
word pairs
word segmentation
database
information retrieval systems
artificial neural networks
case study
web pages
data sets