Document-level event argument extraction poses new challenges of long input and cross-sentence inference compared to its sentence-level counterpart. However, most prior works focus on capturing the relations between candidate arguments and the event trigger in each event, ignoring two crucial points: a) non-argument contextual clue information; b) the relevance among argument roles. In this paper, we propose a SCPRG (Span-trigger-based Contextual Pooling and latent Role Guidance) model, which contains two novel and effective modules for the above problem. The Span-Trigger-based Contextual Pooling(STCP) adaptively selects and aggregates the information of non-argument clue words based on the context attention weights of specific argument-trigger pairs from pre-trained model. The Role-based Latent Information Guidance (RLIG) module constructs latent role representations, makes them interact through role-interactive encoding to capture semantic relevance, and merges them into candidate arguments. Both STCP and RLIG introduce no more than 1% new parameters compared with the base model and can be easily applied to other event extraction models, which are compact and transplantable. Experiments on two public datasets show that our SCPRG outperforms previous state-of-the-art methods, with 1.13 F1 and 2.64 F1 improvements on RAMS and WikiEvents respectively. Further analyses illustrate the interpretability of our model.

翻译：篇章级事件论元抽取相较于句子级任务，面临输入文本长度增加及跨句子推理的新挑战。然而，现有研究大多聚焦于捕获每个事件中候选论元与事件触发词之间的关联，忽略两个关键因素：a) 非论元的上下文线索信息；b) 论元角色之间的语义关联性。本文提出SCPRG（基于触发词-文本片段的上下文池化与潜在角色引导）模型，包含两个创新且高效的模块以解决上述问题。基于触发词-文本片段的上下文池化（STCP）模块通过从预训练模型中提取特定论元-触发词对的上下文注意力权重，自适应地筛选并聚合非论元线索词信息。基于角色的潜在信息引导（RLIG）模块构建潜在角色表征，通过角色交互编码机制捕获语义关联，并将其融入候选论元表征。与基础模型相比，STCP与RLIG模块引入的新参数不超过1%，且可便捷移植至其他事件抽取模型，具有紧凑性与可迁移性。在两类公开数据集上的实验表明，本模型在RAMS与WikiEvents数据集上分别以1.13 F1和2.64 F1的提升超越此前最优方法。进一步分析验证了模型的可解释性。