CodeNER: Code Prompting for Named Entity Recognition

TL;DR

This paper introduces a novel code-based prompting technique for large language models to enhance named entity recognition by explicitly providing detailed labeling instructions, leading to improved performance across multiple languages and benchmarks.

Contribution

It proposes embedding code within prompts to better capture labeling schemas, significantly improving NER accuracy over traditional text prompts.

Findings

Outperforms conventional prompts on ten multilingual benchmarks

Combining code-based prompting with chain-of-thought further boosts performance

Effective across diverse languages including English, Arabic, Finnish, Danish, and German

Abstract

Recent studies have explored various approaches for treating candidate named entity spans as both source and target sequences in named entity recognition (NER) by leveraging large language models (LLMs). Although previous approaches have successfully generated candidate named entity spans with suitable labels, they rely solely on input context information when using LLMs, particularly, ChatGPT. However, NER inherently requires capturing detailed labeling requirements with input context information. To address this issue, we propose a novel method that leverages code-based prompting to improve the capabilities of LLMs in understanding and performing NER. By embedding code within prompts, we provide detailed BIO schema instructions for labeling, thereby exploiting the ability of LLMs to comprehend long-range scopes in programming languages. Experimental results demonstrate that the proposed code-based prompting method outperforms conventional text-based prompting on ten benchmarks across English, Arabic, Finnish, Danish, and German datasets, indicating the effectiveness of explicitly structuring NER instructions. We also verify that combining the proposed code-based prompting method with the chain-of-thought prompting further improves performance.