Search

In both formal and informal texts, missing punctuation marks make the texts confusing and challenging to read. This paper aims to conduct exhaustive experiments to investigate the benefits of the pre-trained Transformer-based models on two Vietnamese punctuation datasets. The experimental results show our models can achieve encouraging results, and adding Bi-LSTM or/and CRF layers on top of the proposed models can also boost model performance. Finally, our best model can significantly bypass state-of-the-art approaches on both the novel and news datasets for the Vietnamese language. It can gain the corresponding performance up to \(21.45\%\) and \(18.27\%\) in the overall F1-scores.

Human body detection become one of the most attractive research field nowadays. The most difficult challenge with this research field is current approaches still cannot satisfy requirement of real life problem. In this paper, we propose a new method method for human body detection using extended PCA namely bidirectional PCA. There are two advantages of bidirectional Principal component analysis. The first one is preserving the shape structure of objects and the second one is effective computation mechanism. The method was tested on INRA PennFudanPed database and the experimental results show high accuracy of the proposed method.1