Comparative Robustness of Single-Source vs Multi-Source Teacher-Student Architectures in Cross-Lingual Named Entity Recognition

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 comparative robustness of single-source versus multi-source teacher-student architectures against domain shift in cross-lingual named entity recognition tasks?

Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 9.0/10.