Unlike Emotion Cause Extraction(ECE) task which consists of pre-annotate emotions and passage, emotion-cause pair extraction(ECPE) aims at extracting potential emotions and corresponding causes in the document without...
详细信息
Unlike Emotion Cause Extraction(ECE) task which consists of pre-annotate emotions and passage, emotion-cause pair extraction(ECPE) aims at extracting potential emotions and corresponding causes in the document without the need for pre-annotations. Traditional ECPE solutions divide the extracting emotions and causes operation into two separate parts. However, separating the bidirectional dependence between emotion and cause may lose a lot of potentially useful information. In this paper, we propose a novel interactive recurrent attention network(IRAN). Our approach focuses on the bidirectional impact between emotions and causes, and extracts emotions and causes simultaneously. The information in the document can be fully exploited through multiple modeling and information extraction. Our emotion-specific transformation and distance fusion correlation can adaptively focus on the emotions and the distance, gracefully incorporate them into a distinguishable neural network attention framework. The experimental results show that our proposed model achieves better performance than other widely-used models on the ECPE corpus.
Facts in military field tend to involve elements of time, space, quantity, status, and so on. Existing methods of representing knowledge in the form of triples fail to adequately express these facts, and also cause ob...
详细信息
ISBN:
(纸本)9781665418164
Facts in military field tend to involve elements of time, space, quantity, status, and so on. Existing methods of representing knowledge in the form of triples fail to adequately express these facts, and also cause obstacles to knowledge storage and updating. Furthermore, question answering on these facts introduces new complexity dimension, which are complicated to be supported by existing corpus. Thus, we construct a Chinese knowledge base for military field covering entities and events centric knowledge, referred as MilKB. It consists of 965 entities and 3,017 facts. Moreover, we classify the natural questions into 26 types and construct a complex question answering dataset derived from MilKB, referred as MilKBQA. It consists of 2,829 question-answer pairs, in which 600 are event-centric ones. Experiments with three recent strong baseline models demonstrate that MilKBQA requires further research.
By adopting successive cancellation list decoding (SCL), polar codes demonstrate competitive error correction performance over LDPC and Turbo codes. However, SCL decoding suffers from high computational complexity and...
ISBN:
(数字)9781509066315
ISBN:
(纸本)9781509066322
By adopting successive cancellation list decoding (SCL), polar codes demonstrate competitive error correction performance over LDPC and Turbo codes. However, SCL decoding suffers from high computational complexity and long decoding latency, especially when the list size is very large. Successive cancellation flip (SCF), as another decoding algorithm that can achieve high error correction performance, has a complexity that is close to that of successive cancellation (SC) decoding. With the observation that SCL and SCF decoding are similar at giving more chances to inspect possible codewords simultaneously or sequentially, a novel hybrid decoder is proposed in this paper, which essentially combines the ideas of SCF and SCL decoders. Moreover, in order to compensate for the degradation of performance caused by the reduction of path splitting and further reduce the decoding latency, the convolutional polar codes are adopted with a designed bit-flipping set. Simulation results demonstrate that the proposed decoder achieves the reduction of decoding latency while attaining better performance than conventional CRC-aided SCL decoder.
Convolutional Neural Networks (CNNs), one of the most representative algorithms of deep learning, are widely used in various artificial intelligence applications. Convolution operations often take most of the computat...
详细信息
Convolutional Neural Networks (CNNs), one of the most representative algorithms of deep learning, are widely used in various artificial intelligence applications. Convolution operations often take most of the computational overhead of CNNs. The FFT-based algorithm can improve the efficiency of convolution by reducing its algorithm complexity, there are a lot of works about the high-performance implementation of FFT-based convolution on many-core CPUs. However, there is no optimization for the non-uniform memory access (NUMA) characteristics in many-core CPUs. In this paper, we present a NUMA-aware FFT-based convolution implementation on ARMv8 many-core CPUs with NUMA architectures. The implementation can reduce a number of remote memory access through the data reordering of FFT transformations and the three-level parallelization of the complex matrix multiplication. The experiment results on a ARMv8 many-core CPU with NUMA architectures demonstrate that our NUMA-aware implementation has much better performance than the state-of-the-art work in most cases.
Data detection is among the most crucial process task for massive multi-user (MU) multiple-input multiple-output (MIMO) wireless systems. In this letter, we propose a novel efficient high precision soft-output data de...
详细信息
Since data outsourcing poses privacy concerns with data leakage, searchable symmetric encryption (SSE) has emerged as a powerful solution that enables clients to perform query operations on encrypted data while preser...
Since data outsourcing poses privacy concerns with data leakage, searchable symmetric encryption (SSE) has emerged as a powerful solution that enables clients to perform query operations on encrypted data while preserving their privacy. Dynamic SSE schemes have been proposed to handle update operations. However, it is shown that updates might increase the risk of information leakage. Meanwhile, to meet the requirement of real-world applications, it is desirable to have the searchable encryption scheme which supports both multiple clients and multi-keyword queries. To address these issues, this paper proposes MMDSSE, a multi-client forward secure dynamic SSE scheme that supports multi-keyword queries. MMDSSE allows the clients narrow down the results by providing an arbitrary subset of the entire archive, and thus suitable for cloud storage environment. Security analysis and experimental evaluations show that MMDSSE is secure and efficient.
Human head detection is a widely used task and suitable for identifying persons in practical applications. Although existing methods have achieved significant progress, the problems of false alarm and miss detection a...
详细信息
ISBN:
(数字)9781728130798
ISBN:
(纸本)9781728130804
Human head detection is a widely used task and suitable for identifying persons in practical applications. Although existing methods have achieved significant progress, the problems of false alarm and miss detection are still challenging, which arise from weak classification power of detector in the face of variability in occlusion, illumination, etc. In this paper, we present an effective end-to-end head detector called Spatial Attention Network with feature Mimicking(SANM) that can obtain better feature and enhanced classification power, through attention mechanism and a feature mimic method. The spatial-wise attention is extracted from several levels of feature and supervised by the bounding-box annotated heat map. The attention improves the quality of the features in the head and opposite area. To further improve the classification ability, we utilize the feature mimicking method to drive network learning the feature refined by a deep cascading classifier. Compared with the baseline model, our method achieves better performance and produces leading results on head detection benchmarks.
With the exponential growth of mobile traffic data, mobile traffic classification is in a great need. It is an essential step to improve the performance of network services such as QoS and security monitoring. However...
详细信息
ISBN:
(数字)9781728186955
ISBN:
(纸本)9781728186962
With the exponential growth of mobile traffic data, mobile traffic classification is in a great need. It is an essential step to improve the performance of network services such as QoS and security monitoring. However, the widespread use of encrypted protocols, especially the TLS protocol, has posed great challenges to traditional traffic classification techniques. As the rule-based deep packet inspection approaches are ineffective for encrypted traffic classification, various machine learning methods have been studied and used. Recently, deep learning solutions which enable automatic feature extraction are also proposed to classify encrypted traffic. In this paper we propose App-Net, an end-to-end hybrid neural network, to learn effective features from raw TLS flows for mobile app identification. App-Net is designed by combining RNN and CNN in a parallel way. So that it can learn a joint flow-app embedding to characterize both flow sequence patterns and unique app signatures. We evaluate App-Net on a real-world dataset that covering 80 apps. The results show that our method can achieve an excellent performance and outperform the state-of-the-art methods.
Convolutional neural networks (CNNs) have been extensively used in artificial intelligence fields such as computer vision and natural language processing. Winograd-based fast convolution algorithms can effectively red...
详细信息
Code clone helps improving programming productivity, while at the same time leads to many negative effects on software maintenance. Many approaches have been proposed to detect clones, but most of them fail on detecti...
详细信息
ISBN:
(数字)9781728195537
ISBN:
(纸本)9781728195544
Code clone helps improving programming productivity, while at the same time leads to many negative effects on software maintenance. Many approaches have been proposed to detect clones, but most of them fail on detecting low similarity code snippets. In this paper, we propose a Siamese network which links two recursive autoencoders (RAE) with a comparator network for clone detection. The unweighted recursive autoencoder is designed to learn code representation and then the comparator network is employed for similarity evaluation. In this Siamese network, it takes full advantages of lexical, semantic and structure information, and achieves high accuracy in revealing tiny similarity. We conduct comprehensive experiments on BigCloneBench using tagged clones as well as the whole repository respectively. The results suggest that our approach achieves good accuracy, and its recall reaches 93.02 % in WT3/T4, which outperforms state-of-the-art.
暂无评论