The Role of Global and Local Context in Named Entity Recognition

Abstract

Pre-trained transformer-based models have recently shown great performance when applied to Named Entity Recognition (NER). As the complexity of their self-attention mechanism prevents them from processing long documents at once, these models are usually applied in a sequential fashion. Such an approach unfortunately only incorporates local context and prevents leveraging global document context in long documents such as novels, which might hinder performance. In this article, we explore the impact of global document context, and its relationships with local context. We find that correctly retrieving global document context has a greater impact on performance than only leveraging local context, prompting for further research on how to better retrieve that context.

arXiv commentAccepted to ACL2023

References in corpus (7)

• Longformer: The Long-Document Transformer
• Introduction to the CoNLL-2002 Shared Task: Language-Independent Named Entity Recognition
• Linformer: Self-Attention with Linear Complexity
• Synthesizer: Rethinking Self-Attention in Transformer Models
• Long Range Arena: A Benchmark for Efficient Transformers
• Sparse Sinkhorn Attention
• Domain-Specific NER via Retrieving Correlated Samples