Text style transfer is mainly to modify the text style to suit various application scenarios without changing the semantic meaning of the text, which is a great significant issue in natural language processing. To exp...
详细信息
Knowledge graph is a useful resources and tools for describing entities and relationships in natural language processing tasks. However, the existing knowledge graph are incomplete. Therefore, knowledge graph completi...
详细信息
Knowledge graph is a useful resources and tools for describing entities and relationships in natural language processing tasks. However, the existing knowledge graph are incomplete. Therefore, knowledge graph completion technology has become a research hotspot in the field of artificial intelligence, but the traditional knowledge graph embedding method does not fully take into account the role of logic rules and the effect of false negative samples on knowledge *** on the logic rules of knowledge and the role of adversarial learning in knowledge embedding, we proposes a model to improve the completion of knowledge graph:soft Rules and graph adversarial learning(RUGA). Firstly,the traditional knowledge graph embedding model is trained as generator and discriminator by using adversarial learning method, and high-quality negative samples are obtained. Then these negative samples and the existing positive samples together constitute the label triple in the injection rule model. The whole model will benefit from both high-quality samples and logical rules. In addition,we evaluated the performance of link prediction task and triple classification task on Freebase and Yago datasets respectively. Finally, the experimental results show that the model can effectively improve the effect of knowledge graph completion.
Graph attention network (GAT) has achieved great success in graph representation learning in recent years. However, the lower Physical properties of GAT in training process severely affects the application of attentio...
详细信息
With the development of 5G network and Internet of things (IOT), a large amount of information is required. In this work, we focus on Topic-to-Essay Generation (TEG), which aims to generate the text based on the topic...
详细信息
Graph attention network (GAT) has achieved great success in graph representation learning in recent years. However, the lower Physical properties of GAT in training process severely affects the application of attentio...
详细信息
Graph attention network (GAT) has achieved great success in graph representation learning in recent years. However, the lower Physical properties of GAT in training process severely affects the application of attention mechanism in graph domain. Particularly, the attention coefficients and the multi-head mechanism are calculated or introduced in the process of model training, which obviously increases the storage complexity. In this paper, we present a graph explicit attention network (GEAT), a novel graph attention architecture that leverage predefined strategy to calculate attention coefficients, which combine global structural and node feature information. In this way, GEAT can effectively reduce the storage complexity, improve the training efficiency and alleviate the over-smoothing problem of attention scores. Experiments on benchmark datasets — Core, Citeseer and Pubmed — demonstrate that our model outperforms the state-of-the-art methods with a clear margin in challenging classifcation tasks, while being computationally efficient.
With the development of 5G network and Internet of things (IOT), a large amount of information is required. In this work, we focus on Topic-to-Essay Generation (TEG), which aims to generate the text based on the topic...
详细信息
With the development of 5G network and Internet of things (IOT), a large amount of information is required. In this work, we focus on Topic-to-Essay Generation (TEG), which aims to generate the text based on the topics. Existing methods utilize the RNN-based models, and it’s not so useful to capture the long dependencies in the text. The information of topics is insufficient to generate a long text and the existing methods also suffer from the problem about the topic relevance of the text. To fill these gaps, we propose a Transformer-based Hierarchical Topic-to-Essay Generation Model (THTEG), and the experimental results on a real dataset show that our model performs better than the baselines in terms of automatic evaluation and human evaluation.
How to classify incredible messages has attracted great attention from academic and industry nowadays. The recent work mainly focuses on one type of incredible messages(a.k.a rumors or fake news) and achieves some suc...
详细信息
How to classify incredible messages has attracted great attention from academic and industry nowadays. The recent work mainly focuses on one type of incredible messages(a.k.a rumors or fake news) and achieves some success to detect them. The existing problem is that incredible messages have different types on social media, and rumors or fake news cannot represent all incredible messages. Based on this, in the paper, we divide messages on social media into five types based on three dimensions of information evaluation metrics. And a novel method is proposed based on deep learning for classifying the five types of incredible messages on social *** specifically, we use attention mechanism to obtain deep text semantic features and strengthen emotional semantics features, meanwhile, construct universal metadata as auxiliary features, concatenating them for incredible messages classification. A series of experiments on two representative real-world datasets demonstrate that the proposed method outperforms the state-of-the-art methods.
Exploring evidence from relevant articles to confirm the veracity of claims is a trend towards explainable claim verification. However, most strategies capture the top-k check-worthy articles or salient words as evide...
详细信息
Recent studies constructing direct interactions between the claim and each single user response to capture evidence have shown remarkable success in interpretable claim verification. Owing to different single response...
Recently, many methods discover effective evidence from reliable sources by appropriate neural networks for explainable claim verification, which has been widely recognized. However, in these methods, the discovery pr...
详细信息
暂无评论