近日，国际人工智能联合会议(IJCAI 2023)公布了录用论文列表，博士生宁金忠关于嵌套与重叠事件抽取（Overlapping and Nested Event Extraction）的研究成果被录取为长文。IJCAI是人工智能领域的顶级会议，被CCF推荐为A类国际学术会议。这次会议共收到4566篇有效长文投稿，仅有685篇长文被录用，录用率约15%。

题目：ODEE: A One-Stage Object Detection Framework for Overlapping and Nested Event Extraction

摘要：The task of extracting overlapping and nested events has received significant attention in recent times, as prior research has primarily focused on extracting flat events, overlooking the intricacies of overlapping and nested occurrences. In this work, we present a new approach to Event Extraction (EE) by reformulating it as an object detection task on a table of token pairs. Our proposed one-stage event extractor, called ODEE, can handle overlapping and nested events. The model is designed with a vertex-based tagging scheme and two auxiliary tasks of predicting the spans and types of event trigger words and argument entities, leveraging the full span information of event elements. Furthermore, in the training stage, we introduce a negative sampling method for table cells to address the imbalance problem of positive and negative table cell tags, meanwhile improving computational efficiency. Empirical evaluations demonstrate that ODEE achieves the state-of-the-art performance on three benchmarks for overlapping and nested EE (i.e., FewFC, Genia11, and Genia13). Furthermore, ODEE outperforms current state-of-the-art methods in terms of both number of parameters and inference speed, indicating its high computational efficiency.

  近年来，嵌套与重叠事件抽取受到了广泛关注。已有的研究主要关注于平事件的抽取，忽略了文本中广泛存在的嵌套与重叠事件。本工作中，我们引入了目标检测框架来解决填表事件抽取任务。我们提出的一阶段事件抽取器叫做ODEE，可以解决嵌套与重叠事件抽取问题。我们的模型中包含基于目标区域顶点的标注方案和两个预测事件触发词和要元实体类型和边界范围的辅助任务，充分利用了事件元素的跨度信息。除此之外，在训练阶段，我们引入了表格单元的负采样方法来解决表格单元的正负样本不均衡的问题。该负采样策略在提升模型性能的同时提高了模型的计算效率。实验结果表明，ODEE在三个基准嵌套与重叠事件抽取数据集上取得了最佳性能（i.e., FewFC, Genia11, and Genia13）。与此同时，ODEE相比已有方法，取得了最快推理速度和最少参数量等，这说明ODEE具有很高的计算效率。