3 research outputs found

    Towards Urdu Name Entity Recognition Using Bi-LSTM-CRF with Self-attention

    No full text
    Named Entity Recognition (NER) is essential in many natural language processing activities, including machine translation and automated question-answering systems. Focusing on the importance of NER, several NER approaches for Western and Asian languages have already been developed. Despite the fact, there are over 490 million Urdu speakers globally, NER resources for Urdu are either non-existent or insufficient. However, very less work is done in Urdu NER. In this work, we developed a deep learning-based method for Urdu NER using Bi LSTM with self-attention and conditional random field (CRF). We have performed tenfold cross-validation using the proposed method. The result shows that our method outperforms the state-of-the-art methods. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd

    Proceedings of First Conference for Engineering Sciences and Technology: Vol. 2

    Get PDF
    This volume contains contributed articles of Track 4, Track 5 & Track 6, presented in the conference CEST-2018, organized by Faculty of Engineering Garaboulli, and Faculty of Engineering, Al-khoms, Elmergib University (Libya) on 25-27 September 2018. Track 4: Industrial, Structural Technologies and Science Material Track 5: Engineering Systems and Sustainable Development Track 6: Engineering Management Other articles of Track 1, 2 & 3 have been published in volume 1 of the proceedings at this lin
    corecore