What question did this study set out to answer?

This research aims to improve named entity recognition, especially in specialized domains like GNSS, by addressing limitations in data and model performance.

March 4, 2026SensorsOpen Access

HybridNER: A Multi-Model Ensemble Framework for Robust Named Entity Recognition—From General Domains to Adversarial GNSS Scenarios

View Full Paper

Ask AI

Bookmark

Authors

YLYing LiuShenyang Pharmaceutical University GZGeorge ZhangShihezi University RLRuipeng LuanAcademy of Military Medical Sciences

Discussion

Member takes

Implication

HybridNER enhances named entity recognition in adversarial GNSS scenarios, suggesting improved robustness in specialized domains.

Key Points

This research aims to improve named entity recognition, especially in specialized domains like GNSS, by addressing limitations in data and model performance.
Developed HybridNER, integrating span-based models with large language models.
Utilized a metasystem to compute span to label compatibility scores for entity recognition.
Implemented a two-stage classification process with uncertainty estimation for effective decision making.
HybridNER shows higher precision, recall, and F1 scores compared to traditional ensemble methods.
Significant performance improvements noted in specialized GNSS domains, overcoming challenges faced by existing models.

Cite This Study

Liu et al. (2026) studied this question.

synapsesocial.com/papers/69a7cd8cd48f933b5eed9f32 https://doi.org/10.3390/s26051553

View Full Paper

Ask AI

Bookmark

HybridNER: A Multi-Model Ensemble Framework for Robust Named Entity Recognition—From General Domains to Adversarial GNSS Scenarios

Discussion

Member takes

Implication

Key Points

Cite This Study

HybridNER: A Multi-Model Ensemble Framework for Robust Named Entity Recognition—From General Domains to Adversarial GNSS Scenarios

Discussion

Member takes

Implication

Key Points

Cite This Study

Also Consider

Also Consider