查看文章

The tas6 of transliteration of named entities from one lanY guage into another is complicated and considered as one of the challenging tas6s in machine translation (MT). To build a well performed transliteration system, we apply wellYesY tablished techniques based on Hybrid Deep Learning. The system based on convolutional neural networ6 (CNN) folY lowed by BiYLSTM and CRF. The proposed hybrid mechaY nism is examined on ANERCorp and Kalimat corpus. The results show that the neural machine translation approach can be employed to build efficient machine transliteration systems achieving stateYoftheYart results for Arabic-EngY lish language.