Cross-lingual NER Model Accuracy with Multi-Source vs. Single-Source Teacher Ensembles on Low-Resource Languages

Cross-lingual named entity recognition task is one of the critical problems for evaluating the potential transfer learning techniques on low resource languages. Knowledge distillation using pre-trained multilingual language models between source and target languages have shown their superiority in transfer. However, existing cross-lingual distillation models merely consider the potential transferability between two identical single tasks across both domains. Other possible auxiliary tasks to improve the learning performance have not been fully investigated. In this study, based on the knowledg

Research goal: How does the accuracy of cross-lingual NER models trained with multi-source teacher ensembles compare to those using single-source teachers when evaluated on the MLC-NER benchmark across 10 low-resource languages?

Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 8.7/10.