Named Entity Recognition via Machine Reading Comprehension: A Multi-Task Learning Approach
This work addresses a specific bottleneck in NER for natural language processing researchers, but it is incremental as it builds on existing MRC-based methods.
The paper tackles the problem of Named Entity Recognition (NER) by incorporating label dependencies among entity types into a multi-task learning framework based on machine reading comprehension, achieving better performance on nested and flat NER datasets.
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.