Retrieval-Enhanced Named Entity Recognition

TL;DR

RENER enhances named entity recognition by integrating retrieval-augmented in-context learning with autoregressive language models, significantly improving performance on benchmark datasets.

Contribution

The paper introduces RENER, a modular retrieval-augmented in-context learning method for NER that outperforms existing approaches and is independent of specific models or retrieval algorithms.

Findings

RENER achieves state-of-the-art results on CrossNER.

Information retrieval boosts F-score by up to 11 percentage points.

The method is modular and adaptable to different models and retrieval techniques.

Abstract

When combined with In-Context Learning, a technique that enables models to adapt to new tasks by incorporating task-specific examples or demonstrations directly within the input prompt, autoregressive language models have achieved good performance in a wide range of tasks and applications. However, this combination has not been properly explored in the context of named entity recognition, where the structure of this task poses unique challenges. We propose RENER (Retrieval-Enhanced Named Entity Recognition), a technique for named entity recognition using autoregressive language models based on In-Context Learning and information retrieval techniques. When presented with an input text, RENER fetches similar examples from a dataset of training examples that are used to enhance a language model to recognize named entities from this input text. RENER is modular and independent of the underlying language model and information retrieval algorithms. Experimental results show that in the CrossNER collection we achieve state-of-the-art performance with the proposed technique and that information retrieval can increase the F-score by up to 11 percentage points.