CAN-NER: Convolutional Attention Network for Chinese Named Entity Recognition
arXiv:1904.02141
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.
arXiv commentThis paper is accepted by NAACL-HLT 2019. The code is available at https://github.com/microsoft/vert-papers/tree/master/papers/CAN-NER
References in corpus (4)
Cited by in corpus (8)
- TENER: Adapting Transformer Encoder for Named Entity Recognition
- A Survey on Recent Advances in Sequence Labeling from Deep Learning Models
- Porous Lattice-based Transformer Encoder for Chinese NER
- Self-attention-based BiGRU and capsule network for named entity recognition
- Using Chinese Glyphs for Named Entity Recognition
- Improving Named Entity Recognition with Attentive Ensemble of Syntactic Information
- Named Entity Recognition for Social Media Texts with Semantic Augmentation
- Incorporating Uncertain Segmentation Information into Chinese NER for Social Media Text