Abstract | ||
---|---|---|
In this paper, we investigate how to improve Chinese named entity recognition (NER) by applying self-attention mechanism on span-level semantic representations. Specifically, we propose a model which acquires character representations through pre-trained BERT, then extracts features of each possible character-span through LSTM, estimates the semantic reference value of each span, then explicitly leverages span-level information by performing self-attention calculation among span representations. Experiments on OntoNotes 4.0 dataset have demonstrated that the proposed model achieves 79.97% F1-score, outperforming our baseline methods. |
Year | DOI | Venue |
---|---|---|
2019 | 10.1109/CIS.2019.00023 | 2019 15th International Conference on Computational Intelligence and Security (CIS) |
Keywords | DocType | ISBN |
Chinese NER,self-attention,span-level information | Conference | 978-1-7281-6093-1 |
Citations | PageRank | References |
0 | 0.34 | 0 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Xiaoyu Dong | 1 | 0 | 0.34 |
Xin Xin | 2 | 77 | 23.24 |
Ping Guo | 3 | 601 | 85.05 |