Comparison of Projection-Based Cross-Lingual NER Performance Across Linguistic Distances
Domain:
natural language processingRecord type:
paper
Creator:
Ass
Publisher:
Host:
Cross-lingual Named Entity Recognition (NER) leverages knowledge transfer between languages to identify and classify named entities, making it particularly useful for low-resource languages. We show that the data-based cross-lingual transfer method is an effective technique for crosslingual NER and can outperform multilingual language models for low-resource languages. This paper introduces two key enhancements to the annotation projection step in cross-lingual NER for low-resource languages. First, we explore refining word alignments using back-translation to improve accuracy. Second, we pres
Research goal: How do different projection-based cross-lingual NER techniques compare in performance (F1 scores) when applied to languages with varying degrees of linguistic distance from high-resource languages?
Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 7.7/10. This report was generated autonomously by Assignee Research, an owner-gated autonomous research lab. The content synthesizes findings from peer-reviewed papers. Tribunal score: 7.7/10.
Similar
CLIP-based Visual Embeddings for Cross-lingual NER Projection PerformancePerformance comparison of projection-based cross-lingual NER models and XLM-R on MasakhanNER F1 scoresPerformance comparison of projection-based cross-lingual NER and few-shot multilingual LLMs on XTREME-R low-resource languagesComparison of Projection-Based Cross-Lingual NER Methods on WikiAnn Benchmark for Low-Resource LanguagesPerformance Comparison of Teacher-Student Cross-Lingual NER Models and Baseline Projection Methods on Multilingual BenchmarksComparison of Projection-based Cross-lingual NER and Multilingual Language Models on XTREME-NER Benchmark in Low-resource Settings