Data scarcity has been the main factor that hinders the progress of event extraction. To overcome this issue, we propose a Self-Training with Feedback (STF) framework that leverages the large-scale unlabeled data and acquires feedback for each new event prediction from the unlabeled data by comparing it to the Abstract Meaning Representation (AMR) graph of the same sentence. Specifically, STF consists of (1) a base event extraction model trained on existing event annotations and then applied to large-scale unlabeled corpora to predict new event mentions as pseudo training samples, and (2) a novel scoring model that takes in each new predicted event trigger, an argument, its argument role, as well as their paths in the AMR graph to estimate a compatibility score indicating the correctness of the pseudo label. The compatibility scores further act as feedback to encourage or discourage the model learning on the pseudo labels during self-training. Experimental results on three benchmark datasets, including ACE05-E, ACE05-E+, and ERE, demonstrate the effectiveness of the STF framework on event extraction, especially event argument extraction, with significant performance gain over the base event extraction models and strong baselines. Our experimental analysis further shows that STF is a generic framework as it can be applied to improve most, if not all, event extraction models by leveraging large-scale unlabeled data, even when high-quality AMR graph annotations are not available.

翻译：数据稀缺一直是制约事件抽取进展的主要因素。为解决这一问题，我们提出了一种基于反馈的自训练（STF）框架，该框架利用大规模无标注数据，并通过将每个新事件预测与对应句子的抽象语义表示（AMR）图进行比较，从无标注数据中获取反馈。具体而言，STF包含：(1) 一个基础事件抽取模型，该模型在现有事件标注上训练后应用于大规模无标注语料库，预测新事件提及作为伪训练样本；(2) 一个新颖的评分模型，该模型接收每个新预测的事件触发词、论元及其论元角色，以及它们在AMR图中的路径，以估计表示伪标签正确性的兼容性得分。这些兼容性得分进一步作为反馈，在自训练过程中鼓励或抑制模型对伪标签的学习。在三个基准数据集（包括ACE05-E、ACE05-E+和ERE）上的实验结果表明，STF框架在事件抽取（尤其是事件论元抽取）上具有显著效果，相比基础事件抽取模型和强基线模型取得了显著的性能提升。我们的实验分析进一步表明，STF是一个通用框架，可应用于改进大多数（若非全部）事件抽取模型，即使在高质量AMR图标注不可用的情况下，也能通过利用大规模无标注数据实现性能提升。