Contextual Deep Search using Long Short Term Memory Recurrent Neural Network

被引:0
作者
Rahman, Mohammad Arifur [1 ]
Ahmed, Fahad [1 ]
Ali, Nafis [2 ]
机构
[1] Amer Int Univ Bangladesh, Dept Comp Sci, Dhaka, Bangladesh
[2] Univ Sydney, Fac Engn & Informat Technol, Sydney, NSW, Australia
来源
2019 1ST INTERNATIONAL CONFERENCE ON ROBOTICS, ELECTRICAL AND SIGNAL PROCESSING TECHNIQUES (ICREST) | 2019年
关键词
LSTM; RNN; Neural Network; POS Tagging; Normalization; Web Scraping; MEAN Stack;
D O I
10.1109/icrest.2019.8644508
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
The internet is teeming with an ocean worth of information and combing through all that in order to find what one wants can become a daunting task if one does not possess the right tools and techniques. This paper explores one such technique, exploiting the rapidly responsive Long-Short Term Memory Recurrent Neural Networks (LSTM-RNNs) by harnessing the machine learning capabilities of neural networks and eventually, provides contextual search results at the finger tips of the user of the system.
引用
收藏
页码:39 / 42
页数:4
相关论文
共 14 条
  • [11] Schmidhuber J., 2016, IEEE Trans Neural Networks Learn Syst, V28, P2222, DOI DOI 10.1109/TNNLS.2016.2582924
  • [12] Sproat Richard, 2016, ARXIV161100068V1
  • [13] Wang Y, 2016, BIG DATA: STORAGE, SHARING, AND SECURITY, P97
  • [14] Yan Yan, 2016, 7 CHIN C COMM COMP S