Dual-FOFE-net Neural Models for Entity Linking with PageRank
This work addresses entity linking for natural language processing applications, offering an incremental improvement with simpler and more efficient methods.
The paper tackles entity linking by proposing a computationally efficient approach using feedforward neural networks with dual-FOFE encoding and PageRank-based candidate generation, achieving higher accuracy than state-of-the-art models on TAC2016 and competitive results on TAC2017.
This paper presents a simple and computationally efficient approach for entity linking (EL), compared with recurrent neural networks (RNNs) or convolutional neural networks (CNNs), by making use of feedforward neural networks (FFNNs) and the recent dual fixed-size ordinally forgetting encoding (dual-FOFE) method to fully encode the sentence fragment and its left/right contexts into a fixed-size representation. Furthermore, in this work, we propose to incorporate PageRank based distillation in our candidate generation module. Our neural linking models consist of three parts: a PageRank based candidate generation module, a dual-FOFE-net neural ranking model and a simple NIL entity clustering system. Experimental results have shown that our proposed neural linking models achieved higher EL accuracy than state-of-the-art models on the TAC2016 task dataset over the baseline system, without requiring any in-house data or complicated handcrafted features. Moreover, it achieves a competitive accuracy on the TAC2017 task dataset.