Showing 2024Show all
3 papers · 1 filter
cs.CL2024
BESSTIE: A Benchmark for Sentiment and Sarcasm Classification for Varieties of English
Dipankar Srirag, Aditya Joshi, Jordan Painter +1
Despite large language models (LLMs) being known to exhibit bias against non-standard language varieties, there are no known labelled datasets for sentiment analysis of English. To…
cs.CL2024
Experiences from Creating a Benchmark for Sentiment Classification for Varieties of English
Dipankar Srirag, Jordan Painter, Aditya Joshi +1
Existing benchmarks often fail to account for linguistic diversity, like language variants of English. In this paper, we share our experiences from our ongoing project of building…
cs.CL2024
Connecting Ideas in 'Lower-Resource' Scenarios: NLP for National Varieties, Creoles and Other Low-resource Scenarios
Aditya Joshi, Diptesh Kanojia, Heather Lent +2
Despite excellent results on benchmarks over a small subset of languages, large language models struggle to process text from languages situated in `lower-resource' scenarios such…