Research Article
Named Entity Recognition of Ancient Poems Based on Albert-BiLSTM-MHA-CRF Model
Table 7
values of different models in three public datasets.
| | Model | Weibo | MSRA | Resume |
| | CRF | 48.76% | 84.22% | 93.92% | | BiLSTM-CRF | 52.35% | 90.25% | 94.31% | | Lattice-LSTM | 58.79% | 93.18% | 94.46% | | CAN_NER | 59.31% | 92.97% | 94.94% | | CWPC_BiAtt | 59.5% | 92.99% | — | | ACNN | — | 93.01% | 94.45% | | Bert-BiLSTM-CRF | 67.33% | 94.83% | 95.51% | | Albert-BiLSTM-MHA-CRF | 72.84% | 94.60% | 95.92% |
|
|
