低秩瓶颈中的事件交互用于时序关系抽取
Event Interaction in Low-Rank Bottlenecks for Temporal Relation Extraction
- KU Leuven（鲁汶大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
针对参数高效微调中低秩瓶颈限制事件交互导致时序关系抽取性能下降的问题，提出卷积瓶颈交互（CBI）架构，在瓶颈内通过深度卷积和逐元素乘法增强交互，在多个数据集和骨干模型上显著提升F1分数。
AI中文摘要：
时序关系抽取判断一个事件发生在另一个事件之前、之后还是同时，因此依赖于准确建模两个事件之间的交互方式。主流系统通过拼接事件片段或使用浅层融合来实现这一点，当所有模型参数可训练时，这种方法效果良好。然而，在参数高效微调中，低秩瓶颈限制了信息流，阻止这些交互信号通过，导致明显的性能下降。为解决这一局限，我们提出了一种具有理论基础的架构——卷积瓶颈交互（CBI），该架构首先应用轻量级深度卷积来增强事件表示，然后在瓶颈内部使用逐元素乘法来捕获有效的事件-事件交互。在Adapter和LoRA设置下的五个数据集和七个骨干模型上，CBI提供了一致且显著的提升，最高可达+31.7微F1分数，同时仅增加极小的计算成本，表明在低秩空间内显式交互对于时序关系抽取至关重要。代码可在该https URL获取。
英文摘要：
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.
