Recent advancements in event argument extraction (EAE) involve incorporating beneficial auxiliary information into models during training and inference, such as retrieved instances and event templates. Additionally, some studies introduce learnable prefix vectors to models. These methods face three challenges: (1) insufficient utilization of relevant event instances due to deficiencies in retrieval; (2) neglect of important information provided by relevant event templates; (3) the advantages of prefixes are constrained due to their inability to meet the specific informational needs of EAE. In this work, we propose DEGAP, which addresses the above challenges through two simple yet effective components: (1) dual prefixes, where the instance-oriented prefix and template-oriented prefix are trained to learn information from different event instances and templates, respectively, and then provide relevant information as cues to EAE model without retrieval; (2) event-guided adaptive gating mechanism, which guides the prefixes based on the target event to fully leverage their advantages. Extensive experiments demonstrate that our method achieves new state-of-the-art performance on four datasets (ACE05, RAMS, WIKIEVENTS, and MLEE). Further analysis verifies the importance of the proposed design and the effectiveness of the main components.

翻译：近年来，事件论元抽取（EAE）的研究进展包括在训练和推理阶段向模型中融入有益的辅助信息，例如检索到的事件实例和事件模板。此外，一些研究引入了可学习的前缀向量。这些方法面临三个挑战：（1）由于检索的不足，未能充分利用相关事件实例；（2）忽略了相关事件模板提供的重要信息；（3）前缀的优势因其无法满足EAE特定的信息需求而受到限制。在本工作中，我们提出了DEGAP，它通过两个简单而有效的组件应对上述挑战：（1）双前缀，其中面向实例的前缀和面向模板的前缀分别被训练以学习来自不同事件实例和模板的信息，然后在无需检索的情况下为EAE模型提供相关信息作为线索；（2）事件引导的自适应门控机制，该机制基于目标事件引导前缀，以充分发挥其优势。大量实验表明，我们的方法在四个数据集（ACE05、RAMS、WIKIEVENTS和MLEE）上取得了新的最先进性能。进一步的分析验证了所提出设计的重要性以及主要组件的有效性。