Impact of Source Language Diversity on Cross-Lingual Transferability in Multilingual GED Models

Grammatical Error Detection (GED) methods rely heavily on human annotated error corpora. However, these annotations are unavailable in many low-resource languages. In this paper, we investigate GED in this context. Leveraging the zero-shot cross-lingual transfer capabilities of multilingual pre-trained language models, we train a model using data from a diverse set of languages to generate synthetic errors in other languages. These synthetic error corpora are then used to train a GED model. Specifically we propose a two-stage fine-tuning pipeline where the GED model is first fine-tuned on mult

Research goal: Does increasing the diversity of source languages in synthetic error corpora improve the cross-lingual transferability of multilingual GED models, as measured by accuracy on low-resource language benchmarks such as FCE and Lang-8?

Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 9.1/10.