CAN-NER: Convolutional Attention Network for Chinese Named Entity Recognition

TL;DR

This paper introduces CAN, a convolutional attention network for Chinese NER that effectively captures character and sentence context without relying on external resources, outperforming existing methods across multiple datasets.

Contribution

The paper proposes a novel character-based convolutional attention network that eliminates the need for external lexicons and word segmentation, improving Chinese NER accuracy.

Findings

Outperforms state-of-the-art methods on multiple datasets

Does not depend on external lexicons or word segmentation

Uses small character embeddings for practicality

Abstract

Named entity recognition (NER) in Chinese is essential but difficult because of the lack of natural delimiters. Therefore, Chinese Word Segmentation (CWS) is usually considered as the first step for Chinese NER. However, models based on word-level embeddings and lexicon features often suffer from segmentation errors and out-of-vocabulary (OOV) words. In this paper, we investigate a Convolutional Attention Network called CAN for Chinese NER, which consists of a character-based convolutional neural network (CNN) with local-attention layer and a gated recurrent unit (GRU) with global self-attention layer to capture the information from adjacent characters and sentence contexts. Also, compared to other models, not depending on any external resources like lexicons and employing small size of char embeddings make our model more practical. Extensive experimental results show that our approach outperforms state-of-the-art methods without word embedding and external lexicon resources on different domain datasets including Weibo, MSRA and Chinese Resume NER dataset.