A Multi-channel Hierarchical Graph Attention Network for Open Event Extraction
A Multi-channel Hierarchical Graph Attention Network for Open Event Extraction
复制标题
DOI：
10.1145/3528668
复制
发表时间：
2022-04
影响因子：
5.6
通讯作者：
Qi-Zhi Wan;Changxuan Wan;Keli Xiao;Rong Hu;Dexi Liu
中科院分区：
文献类型：
--
作者：
Qi-Zhi Wan;Changxuan Wan;Keli Xiao;Rong Hu;Dexi Liu
事件抽取是自然语言处理中的一项重要任务。尽管已有的研究成果得到了广泛的研究，但仍存在以下三个方面的问题：（1）使用原始句法依赖结构的局限性;（2）对图注意力网络（GAT）中的节点级别和类型信息考虑不足;（3）对图结构上的节点依赖类型和词性编码的联合利用不足。为了解决这些问题，我们提出了一个新的框架，开放事件提取文件。具体来说，为了获得具有强大编码能力的增强依赖结构，我们的模型能够处理具有连接省略节点的丰富并行结构。此外，通过一个双向依赖分析图，它考虑顺序结构的顺序和关联的祖先和后代节点。随后，我们进一步利用节点的信息，如节点的级别和类型，以加强我们的GAT节点功能的聚合。最后，基于三通道特征的协调（即，语义、句法依赖和词性），事件提取的性能得到显著提高。大量的实验进行了验证，我们的方法的有效性，结果证实了其优越性的国家的最先进的基线。此外，提供了深入的分析，以探索决定萃取性能的基本因素。
Event extraction is an essential task in natural language processing. Although extensively studied, existing work shares issues in three aspects, including (1) the limitations of using original syntactic dependency structure, (2) insufficient consideration of the node level and type information in Graph Attention Network (GAT), and (3) insufficient joint exploitation of the node dependency type and part-of-speech (POS) encoding on the graph structure. To address these issues, we propose a novel framework for open event extraction in documents. Specifically, to obtain an enhanced dependency structure with powerful encoding ability, our model is capable of handling an enriched parallel structure with connected ellipsis nodes. Moreover, through a bidirectional dependency parsing graph, it considers the sequence of order structure and associates the ancestor and descendant nodes. Subsequently, we further exploit node information, such as the node level and type, to strengthen the aggregation of node features in our GAT. Finally, based on the coordination of triple-channel features (i.e., semantic, syntactic dependency and POS), the performance of event extraction is significantly improved. Extensive experiments are conducted to validate the effectiveness of our method, and the results confirm its superiority over the state-of-the-art baselines. Furthermore, in-depth analyses are provided to explore the essential factors determining the extraction performance.