Learning Dynamic Context Augmentation for Global Entity Linking
arXiv:1909.02117
Abstract
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.
References in corpus (7)
- Adam: A Method for Stochastic Optimization
- Joint Learning of the Embedding of Words and Entities for Named Entity Disambiguation
- Improving Information Extraction by Acquiring External Evidence with Reinforcement Learning
- Improving Entity Linking by Modeling Latent Relations between Mentions
- Capturing Semantic Similarity for Entity Linking with Convolutional Neural Networks
- Relation Mention Extraction from Noisy Data with Hierarchical Reinforcement Learning
- Collective Entity Disambiguation with Structured Gradient Tree Boosting