← Search

Poulami Ghosh

2 accepted papers

2025

Are Language Models Agnostic to Linguistically Grounded Perturbations? A Case Study of Indic Languages

NAACL 2025findings

Pre-trained language models (PLMs) are known to be susceptible to perturbations to the input text, but existing works do not explicitly focus on linguistically grounded attacks, which are subtle and more prevalent in nature. In this paper, we study whether PLMs are agnostic to linguistically grounde…

Cited by 0SourcePDFScholar
2024

A Morphology-Based Investigation of Positional Encodings

EMNLP 2024main

Contemporary deep learning models effectively handle languages with diverse morphology despite not being directly integrated into them. Morphology and word order are closely linked, with the latter incorporated into transformer-based models through positional encodings. This prompts a fundamental in…

Cited by 1SourcePDFScholar