The major challenge that text sentiment classification modeling faces is how to capture the intrinsic semantic, emotional dependence information and the key part of the emotional expression of text. To solve this problem, we proposed a Coordinated CNN-LSTM-Attention(CCLA) model. We learned the vector representations of sentence with CCLA unit. Semantic and emotional information of sentences and their relations are adaptively encoded to vector representations of document. We used softmax regression classifier to identify the sentiment tendencies in the text. Compared with other methods, the CCLA model can well capture the local and long distance semantic and emotional information. Experimental results demonstrated the effectiveness of CCLA model. It shows superior performances over several state-of-the-art baseline methods.
The sentiment classification of Chinese Microblog is a meaningful topic. Many studies has been done based on the methods of rule and word-bag, and to understand the structure information of a sentence will be the next target. We proposed a sentiment classification method based on Recurrent neural network (RNN). We adopted the technology of distributed word representation to construct a vector for each word in a sentence; then train sentence vectors with fixed dimension for different length sentences with RNN, so that the sentence vectors contain both word semantic features and word sequence features; at last use softmax regression classifier in the output layer to predict each sentence's sentiment orientation. Experiment results revealed that our method can understand the structure information of negative sentence and double negative sentence and achieve better accuracy. The way of calculating sentence vector can help to learn the deep structure of sentence and will be valuable for different research area.
To solve the problem that the Chinese named entity recognition (NER) models have poor anti-interference ability and inaccurate entity boundary recognition, this paper proposes the RGP-with-FGM model which is based on global pointer and adversarial learning. Firstly, the RoBERTa-WWM model is used to optimize the semantic representation of the text, and fast gradient method is used to add perturbation to the word embedding layer to enhance the robustness of the model. Then, BiGRU is used to focus on the timing information of Chinese characters to enhance the semantic connection. Finally, the global pointer is constructed in the decoding layer to obtain more accurate entity boundary recognition results. In order to verify the effectiveness of the model proposed in this paper, we construct Uyghur names dataset (UHND) to train the Chinese NER model, and perform extensive experiments with public Chinese NER data sets. Experimental results show that for UHND, the F1 value is 95.12%, which is 3.09% higher than that of the RoBERTa-WWM-BiGRU-CRF model. For the Resume data set, the Precision and F1 value are 96.28% and 96.10% respectively.
4 January 2020 in Lecture Notes in Computer Science