At present, deep learning technologies have been widely used in the field of natural language process, such as text summarization. In CQA, the answer summary could help users get a complete answer quickly. There are s...
At present, deep learning technologies have been widely used in the field of natural language process, such as text summarization. In CQA, the answer summary could help users get a complete answer quickly. There are still some problems with the current answer summary scheme, such as semantic inconsistency, repetition of words, etc. In order to solve this, we propose a novel scheme Answer Summarization based on Multi-layer Attention Scheme (ASMAM). Based on the traditional Seq2Seq, we introduce self-attention and multi-head attention scheme respectively during sentence and text encoding, which could improve text representation ability of the model. In order to solve "long distance dependence" of RNN and too many parameters of LSTM, we all use GRU as the neuron at the encoder and decoder sides. Experiments over the Yahoo! Answers dataset demonstrate that the coherence and fluency of the generated summary are all superior to the benchmark model in ROUGE evaluation system.
Bio-medical entity recognition extracts significant entities, for instance cells, proteins and genes, which is an arduous task in an automatic system that mine knowledge in bioinformatics texts. In this thesis, we uti...
详细信息
Syslog records critical information of network when the system is running, and has been used to help practitioners carry out various network maintenance and operation activities. Because of abundance of syslog, automa...
Syslog records critical information of network when the system is running, and has been used to help practitioners carry out various network maintenance and operation activities. Because of abundance of syslog, automated log analysis technology is needed to complete the above activities. Usually, log parsing is an important part of log analysis. Previous log parsing methods have good achievements, but they heavily rely on well-designed regular expressions and ignore semantic information of log. To solve these problems, we propose a novel log parsing method SNNLog, which uses Siamese Network to assess the similarity between log messages, and the similarity is used for the subsequent parsing. In addition, after parsing, SNNLog merges log similar events, reducing the misjudgment rate caused by non-numeric token variables at the beginning of messages. We evaluated on five publicly accessible log datasets and the results show that compared with SOTA algorithms such as LogMine, Spell, Drain and MoLFI, SNNLog has an F1-score of 0.999 on five datasets, and parsing accuracy of four datasets is the highest.
How to perform efficient service migration in a mobile edge environment has become one of the research hotspots in the field of service computing. Most service migration approaches assume that the mobile edge network ...
详细信息
The ticket automation provides crucial support for the normal operation of IT software systems. An essential task of ticket automation is to assign experts to solve upcoming tickets. However, facing thousands of ticke...
详细信息
Group recommendation has received great attention owing to its practical value in real applications. However, group members are implicit and groups are formed occasionally in some scenarios. Existing solutions for lat...
详细信息
ISBN:
(数字)9781728187860
ISBN:
(纸本)9781728187877
Group recommendation has received great attention owing to its practical value in real applications. However, group members are implicit and groups are formed occasionally in some scenarios. Existing solutions for latent group recommendation assumes a user belongs to a specific group, and totally ignore the possible correlation between the user' s preferences and other groups' preferences. In addition, existing methods cannot deal with new items cold-start problem effectively because they only focus on which items are favored by the group without considering the hidden related information between items. These weaknesses usually lead to poor performance of latent group recommendation. To address the problems above, this paper proposes a latent group recommendation method based on double fuzzy clustering and matrix tri-factorization (DFCMTF -LGR). Firstly, this method utilizes unsupervised learning to implement potential feature extraction and double fuzzy clustering for users and items. Secondly, a novel matrix tri-factorization method is presented to adjust the membership of user-to-group, item-to-item category, and the incidence of group-to-item category is obtained. Finally, latent groups are detected according to user-to-group membership, and group rating can be generated in accordance with group-to-item category incidence matrix and item-to-item category membership. Experimental results on real datasets demonstrate that our proposed DFCMTF-LGR has better performance compared with state-of-the art methods.
With the popularity of various smart devices and the application of sensor network technology, message transmission using mobile devices is becoming *** paper focuses on the forwarding in mobile social network(MSN).Th...
With the popularity of various smart devices and the application of sensor network technology, message transmission using mobile devices is becoming *** paper focuses on the forwarding in mobile social network(MSN).The MSN is a special Delay Tolerant Network(DTN) consisting of mobile *** MSN, nodes move and share information with each other through carried short-range wireless communication *** nodes in the MSN typically access some building areas more frequently, such as schools, companies, or apartments, while visiting other areas, such as the roads between buildings, less *** building areas that nodes frequently visit are called *** increase delivery ratio and reduce transmission time in MSN, this paper proposes a novel zero-knowledge multi-copy routing algorithm, Mixed Message Forwarding(MMF) which exploits and improves the metric, namely *** reflects the importance of a node in the *** improves copy diffusion by using different directions of node movement as *** facilities called boundary boxes are added to the network *** boxes are special throw *** boxes are relays with large storage space and fixed *** is designed and evaluated, which utilizes the aforementioned boundary boxes to reduce transmission *** simulation results show that the MMF can improve the delivery ratio and reduce the transmission delay, compared with other algorithms.
Deep neural networks (DNNs) are demonstrated to be vulnerable to the adversarial example crafted by the adversary to fool the target model. Adversarial training and adversarial example detection are two popular method...
详细信息
Bug localization, which aims to automatically locate buggy source code files based on the given bug report, is a critical yet time-consuming task in the software engineering field. Existing advanced bug localization m...
Bug localization, which aims to automatically locate buggy source code files based on the given bug report, is a critical yet time-consuming task in the software engineering field. Existing advanced bug localization methods have successfully leveraged deep learning to bridge the lexical gap between bug reports and source code files at the semantic level. These methods usually first build the entire source code file semantic representation and then match it with the bug report. However, the bug described in the bug report may be related to only part of the source code file semantics. Directly constructing a semantic representation of the entire source code file would increase the difficulty of semantic matching between bug reports and source code files. In this paper, we propose a novel model named S-BugLocator, which decomposes source code file with the help of program slicing. Especially, our proposed S-BugLocator incorporates two distinctly structured slice feature extraction components in processing source code files to cope with the significant discrepancy between multi-row slices and single-row slices. For each multi-row slice, a CNN and Bi-LSTM network is firstly employed to extract its semantics and then a keywords supervised attention mechanism is designed to build its semantic representation by focusing on slices that have strong relevance with the bug report. For each single-row slice, the semantic representation is obtained by fusing word embeddings in single-row slices. The experimental results on four real-world large-scale projects indicate that our proposed model outperforms existing state-of-the-art bug localization methods.
This paper studies the problem of relationship prediction in heterogeneous information networks. Our goal is not only to predict links/relationships more accurately but also to provide more viable paths to facilitate ...
详细信息
暂无评论