Joint Learning of Local and Global Features for Entity Linking via Neural Networks

Previous studies have highlighted the necessity to capture the local entity-mention similarities and the global topical coherence for entity linking systems. We introduce a novel framework based on convolutional neural networks and recurrent neural networks to simultaneously model the local and global features for entity linking. The proposed model benefits from the capacity of convolutional neural networks to induce the underlying representations for local contexts and the advantage of recurrent neural networks to adaptively compress variable length sequences of predictions for global constraints. Our evaluation on multiple datasets demonstrates the effectiveness of the model and yields the state-of-the-art performance on such datasets. In addition, we examine the entity linking systems on the domain adaptation setting that further demonstrates the cross-domain robustness of the proposed model in the domain shifts.

By: Thien Huu Nguyen, Nicolas R. Fauceglia, Mohammad Sadoghi Hamedani, Mariano Rodriguez Muro, Oktie Hassanzadeh, Alfio Gliozzo

Published in: RC25622 in 2016

This Research Report is not available electronically. Please request a copy from the contact listed below. IBM employees should contact ITIRC for a copy.

Questions about this service can be mailed to .