Multi-Label Text Classification (MLTC) is one of the important subtasks in the field of Natural Language Processing (NLP). In order to solve the problem of complex correlation between multiple labels, an MLTC method TLA-BERT was proposed by incorporating Bidirectional Encoder Representations from Transformers (BERT) and label semantic attention. Firstly, the contextual vector representation of the input text was learned by fine-tuning the self-coding pre-training model. Secondly, the labels were encoded individually by using Long Short-Term Memory (LSTM) neural network. Finally, the contribution of text to each label was explicitly highlighted with the use of an attention mechanism in order to predict the multi-label sequences. Experimental results show that compared with Sequence Generation Model (SGM) algorithm, the proposed method improves the F value by 2.8 percentage points and 1.5 percentage points on the Arxiv Academic Paper Dataset (AAPD) and Reuters Corpus Volume I (RCV1)-v2 public dataset respectively.
Authorship attribution is the task of deciding who is the author of a particular document, however, the traditional methods for authorship attribution are target-independent without considering any constraint during the prediction of authorship, which is inconsistent with the actual problems. To address the above issue, a Target-Dependent method for Authorship Attribution (TDAA) was proposed. Firstly, the product ID corresponding to the user review was chosen to be the constraint information. Secondly, Bidirectional Encoder Representation from Transformer (BERT) was used to extract the pre-trained review text feature to make the text modeling process more universal. Thirdly, the Convolutional Neural Network (CNN) was used to extract the deep features of the text. Finally, two fusion methods were proposed to fuse the two different information. Experimental results on Amazon Movie_and_TV dataset and CDs_and_Vinyl_5 dataset show that the proposed method can increase the accuracy by 4%-5% compared with the comparison methods.
To solve the attitude drift, low real-time ability and high price problem in motion capture system based on inertial sensors, a kind of real-time motion capture system was designed to effectively overcome the attitude drift with low cost and power consumption. At first, a distributed joint motion capture node was built based on the human body kinematics principle, and every node worked in low-power mode, when the acquisition data from the node was lower than a predetermined threshold, the node would automatically enter into the sleep mode to reduce the power consumption of the system. In order to reduce the data drift in traditional algorithm, a kind of algorithm combined with inertial navigation and Kalman filter algorithm was designed to calculate the real-time motion data. Using the Wi-Fi module, the TCP-IP protocol was adopted to transmit the attitude data, which could drive the model in real time. At last, the accuracy of the algorithm was evaluated on the multi-axis motor test platform, and the effect of the system for tracking real human motion was compared. The experimental results show that the algorithm has higher accuracy by contrast with the traditional complementary filtering algorithm, which can control the angle drift in less than one degree; and the delay has no obvious lag by contrast with the complementary filter, which can realize the accurate tracking of human motion.