Named Entity Recognition via Machine Reading Comprehension: A Multi-Task Learning Approach

TL;DR

This paper introduces Multi-NER, a multi-task learning framework that incorporates label dependencies into MRC-based NER, significantly improving performance on nested and flat NER datasets.

Contribution

It proposes a novel multi-task learning approach with self-attention to model label dependencies in MRC-based NER, enhancing recognition accuracy.

Findings

Multi-NER outperforms existing methods on nested NER datasets.

Multi-NER achieves superior results on flat NER datasets.

Incorporating label dependencies improves NER performance.

Abstract

Named Entity Recognition (NER) aims to extract and classify entity mentions in the text into pre-defined types (e.g., organization or person name). Recently, many works have been proposed to shape the NER as a machine reading comprehension problem (also termed MRC-based NER), in which entity recognition is achieved by answering the formulated questions related to pre-defined entity types through MRC, based on the contexts. However, these works ignore the label dependencies among entity types, which are critical for precisely recognizing named entities. In this paper, we propose to incorporate the label dependencies among entity types into a multi-task learning framework for better MRC-based NER. We decompose MRC-based NER into multiple tasks and use a self-attention module to capture label dependencies. Comprehensive experiments on both nested NER and flat NER datasets are conducted to validate the effectiveness of the proposed Multi-NER. Experimental results show that Multi-NER can achieve better performance on all datasets.