Improving Named Entity Recognition with Attentive Ensemble of Syntactic Information

TL;DR

This paper enhances named entity recognition by using an attentive ensemble approach that effectively integrates various syntactic features through novel neural mechanisms, leading to improved performance across multiple datasets.

Contribution

It introduces a new attentive ensemble framework utilizing key-value memory networks, syntax attention, and gating mechanisms to better leverage syntactic information for NER.

Findings

Outperforms previous models on six benchmark datasets

Effectively encodes and aggregates syntactic features

Demonstrates robustness across English and Chinese datasets

Abstract

Named entity recognition (NER) is highly sensitive to sentential syntactic and semantic properties where entities may be extracted according to how they are used and placed in the running text. To model such properties, one could rely on existing resources to providing helpful knowledge to the NER task; some existing studies proved the effectiveness of doing so, and yet are limited in appropriately leveraging the knowledge such as distinguishing the important ones for particular context. In this paper, we improve NER by leveraging different types of syntactic information through attentive ensemble, which functionalizes by the proposed key-value memory networks, syntax attention, and the gate mechanism for encoding, weighting and aggregating such syntactic information, respectively. Experimental results on six English and Chinese benchmark datasets suggest the effectiveness of the proposed model and show that it outperforms previous studies on all experiment datasets.