Abstract | ||
---|---|---|
In this work, we propose a neural network model for Turkish named entity recognition. Model creates a context vector for every position in the sentence by processing the words in forward and backward directions. This context vector is used to obtain a score vector for deciding whether there is an entity in that position or not. A conditional random field (CRF) model is employed to decide the final entity label. In our experiments using this model, performance results higher than the previous works in the literature were observed. |
Year | Venue | Keywords |
---|---|---|
2018 | Signal Processing and Communications Applications Conference | named entity recognition,neural networks,natural language processing |
Field | DocType | ISSN |
Conditional random field,Turkish,Pattern recognition,Computer science,Recurrent neural network,Artificial intelligence,Artificial neural network,Named-entity recognition,Sentence | Conference | 2165-0608 |
Citations | PageRank | References |
0 | 0.34 | 0 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Onur Güngör | 1 | 21 | 3.89 |
Suzan Uskudarli | 2 | 10 | 5.19 |
Tunga Güngör | 3 | 342 | 32.67 |