NER-to-MRC: Named-Entity Recognition Completely Solving as Machine Reading Comprehension

TL;DR

This paper reformulates named-entity recognition as a machine reading comprehension task, enabling high-performance NER without external data by leveraging MRC strategies.

Contribution

It introduces a novel NER-to-MRC framework that transforms NER into an MRC problem and applies reasoning strategies, achieving state-of-the-art results without external data.

Findings

Achieved up to 11.24% improvement on WNUT-16 dataset.

Outperformed previous methods without using external data.

Demonstrated effectiveness across 6 benchmark datasets.

Abstract

Named-entity recognition (NER) detects texts with predefined semantic labels and is an essential building block for natural language processing (NLP). Notably, recent NER research focuses on utilizing massive extra data, including pre-training corpora and incorporating search engines. However, these methods suffer from high costs associated with data collection and pre-training, and additional training process of the retrieved data from search engines. To address the above challenges, we completely frame NER as a machine reading comprehension (MRC) problem, called NER-to-MRC, by leveraging MRC with its ability to exploit existing data efficiently. Several prior works have been dedicated to employing MRC-based solutions for tackling the NER problem, several challenges persist: i) the reliance on manually designed prompts; ii) the limited MRC approaches to data reconstruction, which fails to achieve performance on par with methods utilizing extensive additional data. Thus, our NER-to-MRC conversion consists of two components: i) transform the NER task into a form suitable for the model to solve with MRC in a efficient manner; ii) apply the MRC reasoning strategy to the model. We experiment on 6 benchmark datasets from three domains and achieve state-of-the-art performance without external data, up to 11.24% improvement on the WNUT-16 dataset.