Learning Dynamic Context Augmentation for Global Entity Linking
This work improves entity linking for natural language processing applications by offering a plug-and-enhance module that is incremental in nature.
The paper tackles the problem of collective entity linking (EL) by addressing issues with sub-optimal results due to broken coherence assumptions and high computational costs, proposing Dynamic Context Augmentation (DCA) as a solution that achieves efficient inference with one pass through mentions.
Despite of the recent success of collective entity linking (EL) methods, these "global" inference methods may yield sub-optimal results when the "all-mention coherence" assumption breaks, and often suffer from high computational cost at the inference stage, due to the complex search space. In this paper, we propose a simple yet effective solution, called Dynamic Context Augmentation (DCA), for collective EL, which requires only one pass through the mentions in a document. DCA sequentially accumulates context information to make efficient, collective inference, and can cope with different local EL models as a plug-and-enhance module. We explore both supervised and reinforcement learning strategies for learning the DCA model. Extensive experiments show the effectiveness of our model with different learning settings, base models, decision orders and attention mechanisms.