Search

The requirements for automatic document summarization that can be applied to practical applications are increasing rapidly. As a general sentence regression architecture, extractive text summarization captures sentences from a document by leveraging externally related information. However, existing sentence regression approaches have not employed features that mine the contextual information and relations among sentences. To alleviate this problem, we present a neural network model, namely the Contextualized-Representation Hierarchical-Attention Summarization (CRHASum), that uses the contextual information and relations among sentences to improve the sentence regression performance for extractive text summarization. This framework makes the most of their advantages. One advantage is that the contextual representation is allowed to vary across linguistic context information, and the other advantage is that the hierarchical attention mechanism is able to capture the contextual relations from the word-level and sentence-level by using the Bi-GRU. With this design, the CRHASum model is capable of paying attention to the important context in the surrounding context of a given sentence for extractive text summarization. We carry out extensive experiments on three benchmark datasets. CRHASum alone can achieve comparable performance to the state-of-the-art approach. Meanwhile, our method significantly outperforms the state-of-the-art baselines in terms of multiple ROUNG metrics and includes a few basic useful features. [ABSTRACT FROM AUTHOR]

Emotion cause extraction is to extract the cause information that triggers the emotion expression of described person. This task in text plays a critical role in natural language processing applications, such as sentiment analysis and semantic comprehension system. However, most existing methods for this emotion cause extraction task only focus on feature engineering and ignore the latent semantic information between emotion word and context to hinder the performance. In this paper, we propose a novel computational multi-granularity bidirectional attention stream network based on a machine comprehension frame to settle this problem. The context and query are embedded by this multistage hierarchical process based on the fine-grained levels of embeddings. Then, the bidirectional attention stream mechanism is applied to get an emotional query-aware context representation. Meanwhile, we have conducted extensive experiments on available Chinese emotion cause dataset. The experimental results demonstrate that our approach significantly outperforms the state-of-the-art methods and is able to extract the emotion cause. [ABSTRACT FROM AUTHOR]

Detecting biomedical events in text plays a critical role in building natural language processing applications, such as in medical search, disease prevention, and pharmacovigilance. Since an event trigger can signify the occurrence of the event, the detection of biomedical event triggers is a critical step in biomedical event extraction. Current methods usually extract rich features and then feed these features to a classifier. To enhance both automatic feature selection and classification, this paper presented an end-to-end convolutional highway neural network and extreme learning machine (CHNN–ELM) framework to detect biomedical event triggers. This structure has two stages. In the first stage, CHNN is used to efficiently select higher level semantic features based on four different dimensions: embedding, convolutional layer, pooling layer, and highway layer. In the second stage, the proposed model leverages ELM, which has great scalability and generalization performance, to identify various types of biomedical event triggers. Extensive experiments are conducted on the Multi-Level Event Extraction (MLEE) dataset. To the best of our knowledge, this paper is the first to introduce ELM into this task. The results demonstrated that with better feature selection and classification, our approach outperforms several current state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Abstract With increasing demand for a renewable source of energy and the rapid development of smart cities and cluster computing, wind energy is gaining widespread significance on a global basis. There has been the unprecedented increase in annual installation of wind turbines reaching 60 GW for the first time in history from 51.7 GW of wind energy installation in 2014. Most of the high-power installations utilized double-fed induction generators (DFIG) due to low power losses, which reduced the cost of power converters required in the circuit. Nevertheless, natural factors, such as varying wind speed, influence the output of generators which results in the unsteady generation of power thus affecting the stability of the system. A neural network-based DFIG integrated with super capacitor energy storage system (SCESS) is proposed in this paper. Modeling and simulation have been carried out in MATLAB/Simulink and the observations indicate the significant improvement in the stability of the system. [ABSTRACT FROM AUTHOR]

As the global wind power generation capacity is constantly increasing, the problems of safe operation and utilization after grid connection are becoming more and more prominent. Aiming at the problem of low accuracy and stability of wind power time series with chaotic characteristics, a time series prediction method combining chaotic characteristic processing and neural networks is proposed. First, optimal variational mode decomposition with permutation entropy (OVMD-PE) is used to decompose the original wind power time series and overcome the disadvantage of insufficient mode aliasing encountered by empirical and integrated empirical modes. Second, an improved multi-objective state transition algorithm is proposed to determine the weight coefficients among the neural networks and improve the accuracy of the reconstructed predictive neural networks. Finally, the combined prediction method is used to study and analyze the wind power data from a wind farm in Xinjiang, China, from the perspectives of multiple scenarios and multiple time scales. The experimental results show that OVMD-PE can successfully deal with chaotic characteristics and the improved algorithm has improved the prediction accuracy. Compared with other traditional prediction models, the combined prediction model has higher robustness and stability. • An improved multi-objective state transition algorithm is proposed. • Various shallow neural networks and hybrid neural network models are combined. • OVMD and PE are used to reduce the complex volatility of wind power data. • A new weight determination method is applied to the combination of each model. • The improved algorithm improves the prediction accuracy and stability of wind power. [ABSTRACT FROM AUTHOR]