Exploiting Multiple Embeddings for Chinese Named Entity Recognition
This work addresses NER in Chinese microblogs, a domain-specific challenge, with an incremental method that improves performance for semantic applications.
The paper tackled the problem of Chinese named entity recognition (NER) in microblogs, where performance deteriorates due to colloquial language, by proposing ME-CNER, a neural framework that derives character-level embeddings from multiple granularities, achieving a large performance improvement on the Weibo dataset and comparable results on MSRA with lower computational cost.
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.