用专家路由提升古汉语与现代汉语信息抽取的联合效果
Joint Information Extraction Across Classical and Modern Chinese with Tea-MOELoRA
- 多专家低秩适配器动态分配任务与时代专长
- 在古文与现代文数据上均超越单任务与联合基线
- 适合需要跨时代中文信息抽取的研究者
中文信息抽取涉及古典与现代文本中的多种任务。单一模型在异构任务和不同年代间微调易产生干扰，导致性能下降。本文提出 Tea-MOELoRA，一种基于低秩适配器（LoRA）与混合专家（MoE）结构的参数高效多任务框架。多个低秩专家分别专精于不同信息抽取任务和历史时期，由任务-时代感知的路由机制动态分配贡献。实验表明，Tea-MOELoRA 在多个任务和跨时代数据上均优于单任务及联合微调基线，有效利用了任务与时间知识。
原文摘要 · Abstract (English)
Chinese information extraction (IE) involves multiple tasks across diverse temporal domains, including Classical and Modern documents. Fine-tuning a single model on heterogeneous tasks and across different eras may lead to interference and reduced performance. Therefore, in this paper, we propose Tea-MOELoRA, a parameter-efficient multi-task framework that combines LoRA with a Mixture-of-Experts (MoE) design. Multiple low-rank LoRA experts specialize in different IE tasks and eras, while a task-era-aware router mechanism dynamically allocates expert contributions. Experiments show that Tea-MOELoRA outperforms both single-task and joint LoRA baselines, demonstrating its ability to leverage task and temporal knowledge effectively.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。