Event Arguments Extraction via Dilate Gated Convolutional Neural Network with Enhanced Local Features
This work addresses the bottleneck of event arguments extraction in information extraction, which is crucial for understanding real-world events, though it appears incremental as it builds on existing pipelined structures.
The paper tackled the problem of event arguments extraction, which has lower F-scores than trigger extraction, by proposing a multi-layer Dilate Gated Convolutional Neural Network with enhanced local features, achieving significant performance improvement beyond state-of-the-art approaches on real-world datasets.
Event Extraction plays an important role in information-extraction to understand the world. Event extraction could be split into two subtasks: one is event trigger extraction, the other is event arguments extraction. However, the F-Score of event arguments extraction is much lower than that of event trigger extraction, i.e. in the most recent work, event trigger extraction achieves 80.7%, while event arguments extraction achieves only 58%. In pipelined structures, the difficulty of event arguments extraction lies in its lack of classification feature, and the much higher computation consumption. In this work, we proposed a novel Event Extraction approach based on multi-layer Dilate Gated Convolutional Neural Network (EE-DGCNN) which has fewer parameters. In addition, enhanced local information is incorporated into word features, to assign event arguments roles for triggers predicted by the first subtask. The numerical experiments demonstrated significant performance improvement beyond state-of-art event extraction approaches on real-world datasets. Further analysis of extraction procedure is presented, as well as experiments are conducted to analyze impact factors related to the performance improvement.