Abstract Question generation (QG) refers to the automatic generation of questions based on the given passages and answers, and has a wide range of application scenarios in human–computer interaction, education, medical and other fields. However, for Chinese QG, due to the lack of word separation in the writing rules of Chinese text, many methods are not suitable for it, and the generated results have incorrect word order and invalid expressions. In addition, traditional models only use labeled data, but it is difficult and expensive to obtain data labels. In order to solve this problem, this article proposes a semi‐supervised QG model termed virtual stroke‐aware copy network (VSAC Net). It is based on virtual adversarial training and can be used for Chinese QG tasks with few labeled samples. The VSAC Net model combines word embedding virtual counter disturbance and attention virtual counter disturbance, the fitting of the input layer and the attention layer is taken into account, and reduces the overfitting of the model. According to Dureader dataset, a small sample QG dataset is constructed, and the VSAC Net is used for solving. The results show that the proposed model can achieve a better generation effect on small sample datasets.

Summary Question generation is a promising and important area in natural language processing. According to the information of the given text, the question generation model can automatically generate a variety of questions, which are conducive to processing various subsequent tasks. Chinese question generation is a specific sub‐area of question generation. Due to the characteristics of Chinese question generation tasks, many methods are not suitable for it, and the generated results are either incorrect in word order or invalid expression. In order to address such challenging problem, we propose the conditional pre‐trained attention model termed A Lite BERT Conditional Question Generation (ALBERT‐CQG) for Chinese question generation. Through introducing general background knowledge of the pre‐trained model and conditional information of the given answers, this model has capacity of generating more valid expression. To our knowledge, we are the first to apply the conditional pre‐trained attention model to Chinese question generation tasks. The experimental results on two known benchmark datasets of Chinese question answering show that the ALBERT‐CQG outperforms its recent peers.

Question Generation aims to create various questions from a given passage, which can provide education material, improve the training of question answering, and help chat bots have cold-to-start or continue to talk to people. Chinese Question Generation is a new research area, which mainly uses a rule-based model to convert declarative sentences into questions. We propose a Stroke-Aware Copy Network (SAC-Net), which is a sequence-to-sequence model. It can enhance the performance of Chinese question generation by using various specific components and techniques for Chinese characteristics. In view of the fact that the morphology of Chinese characters is related to its meaning, this research introduces the information of strokes in Chinese and obtain the relationship among strokes in Chinese characters. This model introduces the direction information of the questions, which helps us generate more diverse questions. For the out-of-vocabulary (OOV) word problem that often occurs in Chinese, this research has improved a Self-attention Copy mechanism. Extensive evaluations confirm that this model improves the performance of Chinese problem generation significantly and represents a state-of-the-art neural Chinese problem generation model.

This paper addresses the problem of the quantization noise reduction in subband image coding schemes. Two major artifacts occur for such coding schemes at high compression factors: the ringing effect around high-contrast contours and the blurred false contours in large smooth regions. The first distortion can be considerably reduced by an appropriate design of the subband filters. The second one can be eliminated by using the noise reduction technique proposed in this paper, which consists of applying a noise reduction filter to the DC subband. The advantages of this approach are as follows: first, it can be applied to any kind of subband decompositions; second, it removes quantization noise to which the eye is most sensitive; and third, it is computationally very efficient due to the small size (typically 64/spl times/64) of the DC subband. The colored quantization noise in the DC subband is rendered white by using the Roberts pseudonoise technique. The proposed noise reduction filter is a Wiener type filter with adaptive directional support. It has the advantage of reducing the noise without blurring the reconstructed image. It is shown that the proposed noise reduction filter augments the visual quality of the reconstructed image as well as its PSNR value.

Keywords: LTS1 Reference LTS-CONF-1995-042 Record created on 2006-06-14, modified on 2016-08-08

A morphological subband decomposition with perfect reconstruction is proposed. Critical subsampling is achieved. The reconstructed images using this decomposition do not suffer from any ringing effect. In order to avoid poor texture representation by the morphological filters an adaptive subband decomposition is introduced. It chooses linear filters on textured regions and morphological filters otherwise. A simple and efficient texture detection criterion is proposed and applied to the adaptive decomposition. Comparisons to other coding techniques such as JPEG and linear subband coding show that the proposed scheme performs significantly better both in terms of PSNR and visual quality.>

We address the problem of the choice of subband filters in the context of image coding. The ringing effects that occur in subband-based compression schemes are the major unpleasant distortions. A new set of two-band filter banks suitable for image coding applications is presented. The basic properties of these filters are linear phase, perfect reconstruction, asymmetric length, and maximum regularity. The better overall performances compared to the classical QMF subband filters are explained. The asymmetry of the filter lengths results in a better compaction of the energy, especially in the highpass subbands. Moreover, the quantization error is reduced due to the short lowpass synthesis filter. The undesirable ringing effect is considerably reduced due to the good step response of the synthesis lowpass filter. The proposed design takes into account the statistics of natural images and the effect of quantization errors in the reconstructed images, which explains the better coding performance.

The aim of image restoration is to find an estimate of the ideal image using a priori information about blur and/or noise and/or the ideal image. Classical criterion are minimum least square, minimum mean square error or maximum a posteriori probability. The choice of the criterion used to measure the estimation quality is crucial for the design of the restoration algorithm. The authors propose a new criterion based on a visual model: it is based on perceptual masking. Thereafter, they propose a new restoration algorithm dealing only with additive noise. The perceptual components of the image to restore which are corrupted by an additive noise above a visibility threshold are simply set to zero. Some results obtained for the post-processing of JPEG images are presented.>

A morphological subband decomposition with perfect reconstruction is proposed. Critical subsampling is achieved. Reconstructed images using this decomposition do not suffer from any ringing effect. In order to avoid poor texture representation by morphological filters an adaptive subband decomposition is introduced. It chooses linear filters on textured regions and morphological filters otherwise. Comparisons to other coding techniques such as JPEG and linear subband coding show that the proposed scheme performs significantly better both in terms of PSNR and visual quality.>