Named entity recognition architecture combining contextual and global features

TL;DR

This paper introduces a novel NER architecture that combines contextual features from XLNet with global features from GCN, achieving competitive results on the CoNLL 2003 dataset.

Contribution

It proposes integrating XLNet and GCN for improved NER, addressing the challenge of representing global relations in context-dependent entities.

Findings

Achieved results competitive with state-of-the-art methods.

Demonstrated the effectiveness of combining contextual and global features.

Improved NER performance on the CoNLL 2003 dataset.

Abstract

Named entity recognition (NER) is an information extraction technique that aims to locate and classify named entities (e.g., organizations, locations,...) within a document into predefined categories. Correctly identifying these phrases plays a significant role in simplifying information access. However, it remains a difficult task because named entities (NEs) have multiple forms and they are context-dependent. While the context can be represented by contextual features, global relations are often misrepresented by those models. In this paper, we propose the combination of contextual features from XLNet and global features from Graph Convolution Network (GCN) to enhance NER performance. Experiments over a widely-used dataset, CoNLL 2003, show the benefits of our strategy, with results competitive with the state of the art (SOTA).