Sentiment Analysis is an important research direction of natural language processing, and it is widely used in politics, news and other fields. Word embeddings play a significant role in sentiment analysis. The existing sentiment embeddings methods directly embed the sentiment lexicons into traditional word representation. This sentiment representation methods can only differentiate the sentiment information of different words, not the same word in different contexts, so it cannot provide accurate sentiment information for word in different contexts. This paper proposes sentiment concept to solve the problem. First, we found the optimal sentiment concept of words in Microsoft Concept Graph according to the context of words. Then we obtained the sentiment information of words under optimal sentiment concept from the multi-semantics sentiment intensity lexicon which we constructed in this paper to achieve accurate embedding of sentiment information and provide more accurate semantics and sentiment representation for words. Finally, we combined two refined word embeddings methods to achieve a more comprehensive word representation. Compared with traditional and sentiment embeddings methods on six representative datasets, the validity of the word embeddings method based on sentiment concept proposed in this paper is verified.
As one of the prominent research directions in the field of natural language processing (NLP), short-text similarity has been widely used in search recommendation and question-and-answer systems. Most of the existing short textual similarity models focus on considering semantic similarity while overlooking the importance of syntactic similarity. In this paper, we first propose an enhanced knowledge language representation model based on graph convolutional networks (KEBERT-GCN), which effectively uses fine-grained word relations in the knowledge base to assess semantic similarity and model the relationship between knowledge structure and text structure. To fully leverage the syntactic information of sentences, we also propose a computational model of constituency parse trees based on tree kernels (CPT-TK), which combines syntactic information, semantic features, and attentional weighting mechanisms to evaluate syntactic similarity. Finally, we propose a comprehensive model that integrates both semantic and syntactic information to comprehensively evaluate short-text similarity. The experimental results demonstrate that our proposed short-text similarity model outperforms the models proposed in recent years, achieving a Pearson correlation coefficient of 0.8805 on the STS-B dataset.
14 July 2019 in Computational Intelligence and Neuroscience
Relation extraction is the underlying critical task of textual understanding. However, the existing methods currently have defects in instance selection and lack background knowledge for entity recognition. In this paper, we propose a knowledge-based attention model, which can make full use of supervised information from a knowledge base, to select an entity. We also design a method of dual convolutional neural networks (CNNs) considering the word embedding of each word is restricted by using a single training tool. The proposed model combines a CNN with an attention mechanism. The model inserts the word embedding and supervised information from the knowledge base into the CNN, performs convolution and pooling, and combines the knowledge base and CNN in the full connection layer. Based on these processes, the model not only obtains better entity representations but also improves the performance of relation extraction with the help of rich background knowledge. The experimental results demonstrate that the proposed model achieves competitive performance.
Short text understanding is a key task and popular issue in current natural language processing. Because the content of short texts is characterized by sparsity and semantic limitation, the traditional search methods that analyze only the semantics of literal text for short text understanding and similarity matching have certain restrictions. In this paper, we propose a combined method based on knowledge-based conceptualization and a transformer encoder. Specifically, for each term in a short text, we obtain its concepts and enrich the short text information from a knowledge base based on cooccurrence terms and concepts, construct a convolutional neural network (CNN) to capture local context information, and introduce the subnetwork structure based on a transformer embedding encoder. Then, we embed these concepts into a low-dimensional vector space to obtain more attention from these concepts based on a transformer. Finally, the concept space and transformer encoder space construct the understanding models. An experiment shows that the method in this paper can effectively capture more semantics of short texts and can be applied to a variety of applications, such as short text information retrieval and short text classification.
1 July 2023 in International Journal of Computational Intelligence Systems
Training a deep-learning text classification model usually requires a large amount of labeled data, yet labeling data are usually labor-intensive and time-consuming. Few-shot text classification focuses on predicting unknown samples using only a few labeled samples. Recently, metric-based meta-learning methods have achieved promising results in few-shot text classification. They use episodic training in labeled samples to enhance the model’s generalization ability. However, existing models only focus on learning from a few labeled samples but neglect to learn from a large number of unlabeled samples. In this paper, we exploit the knowledge learned by the model in unlabeled samples to improve the generalization performance of the meta-network. Specifically, we introduce a novel knowledge distillation method that expands and enriches the meta-learning representation with self-supervised information. Meanwhile, we design a graph aggregation method that efficiently interacts the query set information with the support set information in each task and outputs a more discriminative representation. We conducted experiments on three public few-shot text classification datasets. The experimental results show that our model performs better than the state-of-the-art models in 5-way 1-shot and 5-way 5-shot cases.