PUnifiedNER: A Prompting-based Unified NER System for Diverse Datasets
This addresses the issue of high model deployment costs and inefficiency for researchers and practitioners dealing with multiple NER datasets, though it is an incremental improvement over existing prompting methods.
The paper tackles the problem of named entity recognition (NER) requiring dataset-specific models by proposing PUnifiedNER, a prompting-based unified system that works across diverse domains and recognizes up to 37 entity types simultaneously, achieving competitive or better performance than state-of-the-art domain-specific methods for some datasets.
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.