English

Few-shot Name Entity Recognition on StackOverflow

Computation and Language 2024-04-30 v2 Artificial Intelligence

Abstract

StackOverflow, with its vast question repository and limited labeled examples, raise an annotation challenge for us. We address this gap by proposing RoBERTa+MAML, a few-shot named entity recognition (NER) method leveraging meta-learning. Our approach, evaluated on the StackOverflow NER corpus (27 entity types), achieves a 5% F1 score improvement over the baseline. We improved the results further domain-specific phrase processing enhance results.

Keywords

Cite

@article{arxiv.2404.09405,
  title  = {Few-shot Name Entity Recognition on StackOverflow},
  author = {Xinwei Chen and Kun Li and Tianyou Song and Jiangjian Guo},
  journal= {arXiv preprint arXiv:2404.09405},
  year   = {2024}
}

Comments

5 pages

R2 v1 2026-06-28T15:53:59.272Z