Capturing Semantic Similarity for Entity Linking with Convolutional Neural Networks
This addresses the problem of disambiguating entity mentions in text for natural language processing applications, representing an incremental improvement over existing methods.
The paper tackles entity linking by using convolutional neural networks to capture semantic similarity between mention context and target entities, achieving state-of-the-art performance on multiple datasets and outperforming prior systems.
A key challenge in entity linking is making effective use of contextual information to disambiguate mentions that might refer to different entities in different contexts. We present a model that uses convolutional neural networks to capture semantic correspondence between a mention's context and a proposed target entity. These convolutional networks operate at multiple granularities to exploit various kinds of topic information, and their rich parameterization gives them the capacity to learn which n-grams characterize different topics. We combine these networks with a sparse linear model to achieve state-of-the-art performance on multiple entity linking datasets, outperforming the prior systems of Durrett and Klein (2014) and Nguyen et al. (2014).