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 as dialects/sociolects (national or social varieties of a language), …
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 as dialects/sociolects (national or social varieties of a language), …
Abbreviations and their associated long forms are important textual elements that are present in almost every scientific communication, and having information about these forms can help improve several NLP tasks. In this paper, our aim is to …
This was a poster I presented at [Convergence 2023](https://www.surrey.ac.uk/centre-translation-studies/convergence-2023). I discuss the work done, the collaborations, our NLP Cafe and publicly available resouces for NLP research contributed by …
Presented as a co-chair on the panel, '[Natural Language Processing Augmenting Translation and Interpreting](https://www.surrey.ac.uk/centre-translation-studies/convergence-2023/nlp-augmenting-translation-and-interpreting)' at [Convergence …