Adaptive Ordered Information Extraction with Deep Reinforcement Learning
This work addresses a bottleneck in information extraction for complex tasks, offering a novel approach to optimize extraction order, though it is incremental in improving existing methods.
The paper tackles the problem of fixed extraction orders in complex information extraction tasks, which can significantly affect results, by proposing an adaptive ordered IE paradigm that uses deep reinforcement learning to dynamically find optimal extraction orders, achieving improved performance on various public datasets.
Information extraction (IE) has been studied extensively. The existing methods always follow a fixed extraction order for complex IE tasks with multiple elements to be extracted in one instance such as event extraction. However, we conduct experiments on several complex IE datasets and observe that different extraction orders can significantly affect the extraction results for a great portion of instances, and the ratio of sentences that are sensitive to extraction orders increases dramatically with the complexity of the IE task. Therefore, this paper proposes a novel adaptive ordered IE paradigm to find the optimal element extraction order for different instances, so as to achieve the best extraction results. We also propose an reinforcement learning (RL) based framework to generate optimal extraction order for each instance dynamically. Additionally, we propose a co-training framework adapted to RL to mitigate the exposure bias during the extractor training phase. Extensive experiments conducted on several public datasets demonstrate that our proposed method can beat previous methods and effectively improve the performance of various IE tasks, especially for complex ones.