PUnifiedNER: A Prompting-based Unified NER System for Diverse Datasets

TL;DR

PUnifiedNER is a versatile, prompt-based model capable of recognizing multiple entity types across diverse datasets, reducing deployment costs and achieving competitive performance with domain-specific models.

Contribution

This work introduces PUnifiedNER, a novel prompt learning approach enabling a single model to handle multiple datasets and entity types simultaneously, unlike traditional dataset-specific models.

Findings

PUnifiedNER outperforms dataset-specific models in prediction accuracy.

It reduces model deployment costs significantly.

Achieves competitive or better results than state-of-the-art methods.

Abstract

Much of named entity recognition (NER) research focuses on developing dataset-specific models based on data from the domain of interest, and a limited set of related entity types. This is frustrating as each new dataset requires a new model to be trained and stored. In this work, we present a ``versatile'' model -- the Prompting-based Unified NER system (PUnifiedNER) -- that works with data from different domains and can recognise up to 37 entity types simultaneously, and theoretically it could be as many as possible. By using prompt learning, PUnifiedNER is a novel approach that is able to jointly train across multiple corpora, implementing intelligent on-demand entity recognition. Experimental results show that PUnifiedNER leads to significant prediction benefits compared to dataset-specific models with impressively reduced model deployment costs. Furthermore, the performance of PUnifiedNER can achieve competitive or even better performance than state-of-the-art domain-specific methods for some datasets. We also perform comprehensive pilot and ablation studies to support in-depth analysis of each component in PUnifiedNER.