Partial-input baselines show that NLI models can ignore context, but they don't.

Neha Srikanth Rachel Rudinger

Published in: NAACL-HLT (2022)

Keyphrases

statistical models
statistical model
context sensitive
real time
learning algorithm
social networks
information systems
case study
support vector
evolutionary algorithm
probabilistic model
input data
model selection
parameter estimation
machine learning algorithms
context dependent