Recurrent neural networks for Turkish named entity recognition
| Autor: | Suzan Uskudarli, Onur Güngör, Tunga Güngör |
|---|---|
| Rok vydání: | 2018 |
| Předmět: |
Conditional random field
Artificial neural network Computer science Turkish business.industry 02 engineering and technology 010501 environmental sciences computer.software_genre 01 natural sciences language.human_language Recurrent neural network Named-entity recognition Position (vector) 0202 electrical engineering electronic engineering information engineering language 020201 artificial intelligence & image processing Artificial intelligence business computer Natural language processing Sentence 0105 earth and related environmental sciences |
| Zdroj: | SIU |
| DOI: | 10.1109/siu.2018.8404788 |
| Popis: | 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. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|