Extracting event relations that deviate from known schemas has proven challenging for previous methods based on multi-class classification, MASK prediction, or prototype matching. Recent advancements in large language models have shown impressive performance through instruction tuning. Nevertheless, in the task of event relation extraction, instruction-based methods face several challenges: there are a vast number of inference samples, and the relations between events are non-sequential. To tackle these challenges, we present an improved instruction-based event relation extraction framework named MAQInstruct. Firstly, we transform the task from extracting event relations using given event-event instructions to selecting events using given event-relation instructions, which reduces the number of samples required for inference. Then, by incorporating a bipartite matching loss, we reduce the dependency of the instruction-based method on the generation sequence. Our experimental results demonstrate that MAQInstruct significantly improves the performance of event relation extraction across multiple LLMs.

翻译：从已知模式中抽取偏离的事件关系，对于以往基于多分类、MASK预测或原型匹配的方法而言已被证明具有挑战性。大型语言模型的最新进展通过指令微调展现了令人印象深刻的性能。然而，在事件关系抽取任务中，基于指令的方法面临若干挑战：推理样本数量庞大，且事件间的关系是非顺序性的。为应对这些挑战，我们提出了一种改进的基于指令的事件关系抽取框架，命名为MAQInstruct。首先，我们将任务从使用给定的事件-事件指令抽取事件关系，转换为使用给定的事件-关系指令选择事件，这减少了推理所需的样本数量。随后，通过引入二分图匹配损失，我们降低了基于指令的方法对生成序列的依赖。我们的实验结果表明，MAQInstruct显著提升了多种大型语言模型在事件关系抽取任务上的性能。