Papers by Konul Baghirova
Kardeş-NLU: Transfer to Low-Resource Languages with Big Brother’s Help – A Benchmark and Evaluation for Turkic Languages (2024.eacl-long)
Copied to clipboard
| Challenge: | Cross-lingual transfer (XLT) driven by massively multilingual language models (mmLMs) has been shown to be ineffective for low-resource (LR) target languages with little (or no) representation in mmLM’s pretraining . |
| Approach: | They propose a benchmark to evaluate cross-lingual transfer (XLT) to LR languages that do have a close HR relative and a framework to integrate Turkish into XLT. |
| Outcome: | The proposed configuration is of practical relevance for more of the world’s languages: XLT to LR languages that do have a close HR relative. |