Exploiting Multiple Embeddings for Chinese Named Entity Recognition

TL;DR

This paper introduces ME-CNER, a neural framework that leverages multi-granularity character embeddings to improve Chinese NER, especially in colloquial microblogs, achieving significant performance gains with lower computational cost.

Contribution

The paper proposes a novel multi-granularity character embedding method for Chinese NER that enhances performance in microblogs and reduces computational complexity.

Findings

Significant performance improvement on Weibo dataset.

Comparable performance on MSRA news dataset.

Lower computational cost compared to existing methods.

Abstract

Identifying the named entities mentioned in text would enrich many semantic applications at the downstream level. However, due to the predominant usage of colloquial language in microblogs, the named entity recognition (NER) in Chinese microblogs experience significant performance deterioration, compared with performing NER in formal Chinese corpus. In this paper, we propose a simple yet effective neural framework to derive the character-level embeddings for NER in Chinese text, named ME-CNER. A character embedding is derived with rich semantic information harnessed at multiple granularities, ranging from radical, character to word levels. The experimental results demonstrate that the proposed approach achieves a large performance improvement on Weibo dataset and comparable performance on MSRA news dataset with lower computational cost against the existing state-of-the-art alternatives.