Synthetic Noise Impact on Cross-Lingual NER Alignment in Low-Resource Languages
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: To what extent does incorporating synthetic noise into unlabeled target data improve the alignment accuracy of cross-lingual NER student models across low-resource language pairs?
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
Domain Adaptation for Cross-Lingual NER Alignment with Synthetic NoiseCross-lingual NER Generalization via Embedding Alignment in Low-Resource LanguagesMultimodal Alignment for Robust Cross-Lingual NER in Low-Resource LanguagesRobustness of Cross-Lingual NER Models Under Annotation Projection Noise in Low-Resource LanguagesImpact of Word Alignment Noise on Cross-Lingual NER F1-Score and Adversarial RobustnessImpact of Contrastive Learning on Cross-Lingual NER F1-Score in Low-Resource Languages