Multilingual Pre-trained Models for Low-Resource Language Error Correction

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: Can multilingual pre-trained models fine-tuned on synthetic error corpora achieve comparable accuracy to supervised baselines on the BEA-2019 shared task benchmark for unseen low-resource languages?

Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 9.2/10.