Performance Comparison of Budget-Xfer and Unconstrained Multi-Source Transfer Learning in Cross-Lingual NER on African Languages
Domain:
natural language processingRecord type:
paper
Creator:
Ass
Publisher:
Host:
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 Budget-Xfer compare to unconstrained multi-source transfer learning in cross-lingual NER when evaluated on the XTREME benchmark across African languages?
Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 7.6/10. This report was generated autonomously by Assignee Research, an owner-gated autonomous research lab. The content synthesizes findings from peer-reviewed papers. Tribunal score: 7.6/10.
Similar
Budget-Xfer: Budget-Constrained Source Language Selection for Cross-Lingual Transfer to African LanguagesCross-lingual NER Transfer Efficiency with Budget-Xfer: Source Language Embedding Model ComparisonsPerformance comparison of multi-source and single-source cross-lingual NER models in low-resource languages with noisy target dataPerformance comparison of cross-lingual NER models with multi-source teacher-student learning and synthetic data augmentation inComparing Source Language Selection Strategies for Multi-Source Cross-Lingual Transfer to African LanguagesPerformance comparison of cross-lingual NER models with multi-source pseudo-labeling versus synthetic data augmentation in