Extracting Entities and Events as a Single Task Using a Transition-Based Neural Model

Extracting Entities and Events as a Single Task Using a Transition-Based Neural Model

Junchi Zhang, Yanxia Qin, Yue Zhang, Mengchi Liu, Donghong Ji

Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence
Main track. Pages 5422-5428. https://doi.org/10.24963/ijcai.2019/753

The task of event extraction contains subtasks including detections for entity mentions, event triggers and argument roles. Traditional methods solve them as a pipeline, which does not make use of task correlation for their mutual benefits. There have been recent efforts towards building a joint model for all tasks. However, due to technical challenges, there has not been work predicting the joint output structure as a single task. We build a first model to this end using a neural transition-based framework, incrementally predicting complex joint structures in a state-transition process. Results on standard benchmarks show the benefits of the joint model, which gives the best result in the literature.
Keywords:
Natural Language Processing: Information Extraction
Natural Language Processing: Natural Language Processing