Multi-source Cross-lingual NER via Teacher-Student Learning: Low-Resource Evaluation on CoNLL-2003

Cross-lingual transfer learning enables NLP for low-resource languages by leveraging labeled data from higher-resource sources, yet existing comparisons of source language selection strategies do not control for total training data, confounding language selection effects with data quantity effects. We introduce Budget-Xfer, a framework that formulates multi-source cross-lingual transfer as a budget-constrained resource allocation problem. Given a fixed annotation budget B, our framework jointly optimizes which source languages to include and how much data to allocate from each. We evaluate fou

Research goal: How does the performance of multi-source cross-lingual NER via teacher-student learning compare to single-source baselines when evaluated on low-resource languages using the CoNLL-2003 benchmark?

Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 7.6/10.