• ETRI Journal
• /
• v.42 no.1
• /
• pp.90-100
• /
• 2020

Named entity recognition (NER) continues to be an important task in natural language processing because it is featured as a subtask and/or subproblem in information extraction and machine translation. In Urdu language processing, it is a very difficult task. This paper proposes various deep recurrent neural network (DRNN) learning models with word embedding. Experimental results demonstrate that they improve upon current state-of-the-art NER approaches for Urdu. The DRRN models evaluated include forward and bidirectional extensions of the long short-term memory and back propagation through time approaches. The proposed models consider both language-dependent features, such as part-of-speech tags, and language-independent features, such as the "context windows" of words. The effectiveness of the DRNN models with word embedding for NER in Urdu is demonstrated using three datasets. The results reveal that the proposed approach significantly outperforms previous conditional random field and artificial neural network approaches. The best f-measure values achieved on the three benchmark datasets using the proposed deep learning approaches are 81.1%, 79.94%, and 63.21%, respectively.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.37 no.4
• /
• pp.22-27
• /
• 2000

In this paper, new neural network called dynamic multidimensional wavelet neural network (DMWNN) is proposed. The resulting network from wavelet theory provides a unique and efficient representation of the given function. Also the proposed DMWNN have ability to store information for later use. Therefore it can represent dynamic mapping and decreases the dimension of the inputs needed for network. This feature of DMWNN can compensate for the weakness of diagonal recurrent neural network(DRNN) and feedforward wavelet neural network(FWNN). The efficacy of this type of network is demonstrated through experimental results.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.13 no.3
• /
• pp.275-280
• /
• 2003

In this paper, we propose a method for recognizing the human s emotion using output data of image and speech. The proposed method is based on the recognition rate of image and speech. In case that we use one data of image or speech, it is hard to produce the correct result by wrong recognition. To solve this problem, we propose the new method that can reduce the result of the wrong recognition by multiplying the emotion status with the higher recognition rate by the higher weight value. To experiment the proposed method, we suggest the simple recognizing method by using image and speech. Finally, we have shown the potentialities through the expriment.