在参数高效微调中，显式建模事件交互可显著提升时间关系抽取性能。
Event Interaction in Low-Rank Bottlenecks for Temporal Relation Extraction
- 在低秩瓶颈中引入轻量卷积与逐元素相乘，增强事件间交互建模
- 在7种主干模型上最高提升31.7微F1，且计算开销极小
- 适用于适配器和LoRA等参数高效微调场景，适合高效训练需求
时间关系抽取需判断事件发生的先后或共现关系，依赖对事件间交互的准确建模。主流方法通过拼接事件跨度或浅层融合实现，但在参数高效微调中，低秩瓶颈限制信息流动，导致交互信号无法传递，性能明显下降。为此，我们提出理论支撑的架构Convolutional Bottleneck Interaction（CBI）：先用轻量深度卷积增强事件表示，再通过逐元素相乘捕捉瓶颈内的有效事件-事件交互。在五个数据集和七种主干模型的Adapter与LoRA设置下，CBI均带来一致且显著的提升，最高达+31.7微F1，且增加计算成本极低，证明在低秩空间内显式建模交互对时间关系抽取至关重要。代码已开源。
原文摘要 · Abstract (English)
Temporal relation extraction determines whether an event occurs before, after, or simultaneously with another event, and therefore relies on accurately modeling how the two events interact. Mainstream systems achieve this by concatenating event spans or using shallow fusion, which works well when all model parameters are trainable. However, in parameter-efficient fine-tuning, low-rank bottlenecks restrict information flow and prevent these interaction signals from passing through, leading to clear performance drops. To address this limitation, we propose a theoretically grounded architecture, Convolutional Bottleneck Interaction (CBI), which first applies lightweight depthwise convolution to enhance event representations and then uses element-wise multiplication to capture effective event-event interactions inside the bottleneck. Across five datasets and seven backbone models in the Adapter and LoRA settings, CBI provides consistent and substantial gains, up to +31.7 micro F1, while adding minimal computational cost, showing that explicit interaction inside low-rank spaces is crucial for temporal relation extraction. The code is available at https://github.com/VRCMF/CIF.git.
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。