Pre-trained language models are vulnerable to phonologically and orthographically motivated character substitutions in Indic languages, but less so than to unconstrained random character substitution.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Are Language Models Agnostic to Linguistically Grounded Perturbations? A Case Study of Indic Languages
Pre-trained language models are vulnerable to phonologically and orthographically motivated character substitutions in Indic languages, but less so than to unconstrained random character substitution.