Name
Abstract | ||
|---|---|---|
Efficient recognition of proprietary entities is an important basic work for text data mining and intelligent application in power domain. Traditional power domain Named Entity Recognition (NER) methods rely on feature engineering seriously, which unable to learn power entity features automatically. In order to learn entity features automatically and extract power domain named entities efficiently, a model based on Bidirectional Long Short-Term Memory Neural Networks (Bi-LSTM) and Conditional Random Field (CRF) was proposed in this paper. Word representations were fed into the neural networks as an additional feature and Skip-gram embeddings were trained on power domain corpus. Experimental results showed the precision rate reaches higher than 88.25% and the recalling rate reaches higher than 88.04%, which confirm the method based on Bi-LSTM and CRF is effective for named entity recognition in the power domain.
|
Year | DOI | Venue |
|---|---|---|
2019 | 10.1145/3357254.3357283 | Proceedings of the 2nd International Conference on Artificial Intelligence and Pattern Recognition |
Keywords | Field | DocType |
Bi-LSTM, CRF, named entity recognition, power domain | Power domains,Computer science,Speech recognition,Named-entity recognition | Conference |
ISBN | Citations | PageRank |
978-1-4503-7229-9 | 0 | 0.34 |
References | Authors | |
0 | 8 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Zhenqiang Zhao | 1 | 0 | 0.34 |
| Zhenyu Chen | 2 | 0 | 1.35 |
| Jinbo Liu | 3 | 0 | 0.68 |
| Yunhao Huang | 4 | 0 | 0.34 |
| Xingyu Gao | 5 | 106 | 14.95 |
| Fangchun Di | 6 | 0 | 1.01 |
| Lixin Li | 7 | 0 | 0.34 |
| Xiaohui Ji | 8 | 0 | 0.68 |