English

Logits-Constrained Framework with RoBERTa for Ancient Chinese NER

Computation and Language 2025-05-07 v1

Abstract

This paper presents a Logits-Constrained (LC) framework for Ancient Chinese Named Entity Recognition (NER), evaluated on the EvaHan 2025 benchmark. Our two-stage model integrates GujiRoBERTa for contextual encoding and a differentiable decoding mechanism to enforce valid BMES label transitions. Experiments demonstrate that LC improves performance over traditional CRF and BiLSTM-based approaches, especially in high-label or large-data settings. We also propose a model selection criterion balancing label complexity and dataset size, providing practical guidance for real-world Ancient Chinese NLP tasks.

Keywords

Cite

@article{arxiv.2505.02983,
  title  = {Logits-Constrained Framework with RoBERTa for Ancient Chinese NER},
  author = {Wenjie Hua and Shenghan Xu},
  journal= {arXiv preprint arXiv:2505.02983},
  year   = {2025}
}

Comments

5 pages, 2 figures, 6 tables. Accepted to EvaHan 2025 shared task on Ancient Chinese NLP

R2 v1 2026-06-28T23:22:03.638Z