Named Entity Recognition in Context
This addresses entity disambiguation in Classical Chinese for the EvaHan2025 competition, with incremental improvements over the baseline.
The authors tackled Named Entity Recognition in Classical Chinese by integrating a transformer-based encoder, retrieval module, and generative reasoning, achieving an average F1 score of 85.58 and improving the competition baseline by nearly 5 points.
We present the Named Entity Recognition system developed by the Edit Dunhuang team for the EvaHan2025 competition. Our approach integrates three core components: (1) Pindola, a modern transformer-based bidirectional encoder pretrained on a large corpus of Classical Chinese texts; (2) a retrieval module that fetches relevant external context for each target sequence; and (3) a generative reasoning step that summarizes retrieved context in Classical Chinese for more robust entity disambiguation. Using this approach, we achieve an average F1 score of 85.58, improving upon the competition baseline by nearly 5 points.