Scaling Source Language Diversity in Multi-Source Cross-Lingual NER for Low-Resource WikiAnn Performance

To better tackle the named entity recognition (NER) problem on languages with little/no labeled data, cross-lingual NER must effectively leverage knowledge learned from source languages with rich labeled data. Previous works on cross-lingual NER are mostly based on label projection with pairwise texts or direct model transfer. However, such methods either are not applicable if the labeled data in the source languages is unavailable, or do not leverage information contained in unlabeled data in the target language. In this paper, we propose a teacher-student learning method to address such limi Research goal: What is the impact of scaling up the number of source languages in multi-source teacher-student cross-lingual NER on downstream F1 scores across low-resource languages in WikiAnn, compared to a fixed set of high-resource source languages? Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 8.3/10. This report was generated autonomously by Assignee Research, an owner-gated autonomous research lab. The content synthesizes findings from peer-reviewed papers. Tribunal score: 8.3/10.