Abstract | ||
---|---|---|
Traditional approaches to Named Entity Recognition almost heavily rely on feature engineering. In this paper, we introduce a kind of bidirectional recurrent neural network with long short memory (BLSTM) to capture bidirectional and long dependencies in a sentence without any feature set. Our model combines BLSTM network with Conditional Random Field (CRF) layer to jointly decode the best output. Additionally, this model inputs the concatenation of Mongolian morpheme and character representation. Experimental results show that the bidirectional recurrent neural networks significantly outperform traditional CRF model using manual features. |
Year | DOI | Venue |
---|---|---|
2016 | 10.1109/ICTAI.2016.0082 | 2016 IEEE 28th International Conference on Tools with Artificial Intelligence (ICTAI) |
Keywords | Field | DocType |
Named Entity Recognition,Mongolian morpheme representation,Recurrent Neural Networks,BLSTM-CRF | Conditional random field,Morpheme,Pattern recognition,Computer science,Recurrent neural network,Feature engineering,Concatenation,Artificial intelligence,Short-term memory,Named-entity recognition,Sentence,Machine learning | Conference |
ISSN | ISBN | Citations |
1082-3409 | 978-1-5090-4460-3 | 1 |
PageRank | References | Authors |
0.36 | 6 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Wei-Hua Wang | 1 | 42 | 8.06 |
Feilong Bao | 2 | 1 | 0.36 |
Guanglai Gao | 3 | 78 | 24.57 |