Error Propagation Impact on F1 Scores in Cross-Lingual NER Model Projection
Domaine:
natural language processingCréateur:
Ass
Éditeur:
Hôte:
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 does machine translation error propagation affect the F1 score of projection-based cross-lingual NER models when transferring from high-resource to typologically distant low-resource languages?
Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 7.5/10. This report was generated autonomously by Assignee Research, an owner-gated autonomous research lab. The content synthesizes findings from peer-reviewed papers. Tribunal score: 7.5/10.
Similaires
Performance comparison of projection-based cross-lingual NER models and XLM-R on MasakhanNER F1 scoresImpact of Multilingual Pretrained Language Models on Cross-Lingual NER F1 Scores in Low-Resource LanguagesCross-lingual NER Projection Techniques and F1 Score Gaps in MLQA BenchmarkProjection-based Cross-lingual NER Scaling and F1-Score Gaps in Low-Resource LanguagesImpact of Contrastive Learning on Cross-Lingual NER F1-Score in Low-Resource LanguagesImpact of Word Alignment Noise on Cross-Lingual NER F1-Score and Adversarial Robustness