Generating Questions Based on Semi-Automated and End-to-End Neural Network

With the emergence of large-scale knowledge base, how to use triple information to generate natural questions is a key technology in question answering systems. The traditional way of generating questions require a lot of manual intervention and produce lots of noise. To solve these problems, we propose a joint model based on semi-automated model and End-to-End neural network to automatically generate questions. The semi-automated model can generate question templates and real questions combining the knowledge base and center graph. The End-to-End neural network directly sends the knowledge base and real questions to BiLSTM network. Meanwhile, the attention mechanism is utilized in the decoding layer, which makes the triples and generated questions more relevant. Finally, the experimental results on SimpleQuestions demonstrate the effectiveness of the proposed approach.     

An index structure supporting rule activation in pervasive applications

World Wide Web - Rule mechanism has been widely used in many areas, such as databases, artificial intelligent and pervasive computing. In a rule mechanism, rule activation decides which rules are...     

Anaerobic co-digestion of food waste and FOG with sewage sludge – realising its potential in Ireland

The severe environmental pollution in many countries is caused by indiscriminate discharge of large quantities of food waste (FW), fat oil and grease (FOG) and sewage sludge (SS) to the environment. There are many possible treatment routes, but anaerobic digestion (AD) is now well accepted for treating several kinds of organic wastes. But AD of FW alone presents some operational challenges because of substrates and variability. Anaerobic co-digestion of two or more substrates is better than single substrate digestion. This can use a plant’s unused capacity, in line with the trend to renewable energy. Co-digestion technology, although well established in many European countries, is still in its infancy in Ireland. There are problems with different regulatory arrangements. They should be resolved. The paper reviews anaerobic co-digestion technology is reviewed, with special focus on possible application in Ireland.     

MPE: a mobility pattern embedding model for predicting next locations

World Wide Web - The wide spread use of positioning and photographing devices gives rise to a deluge of traffic trajectory data (e.g., vehicle passage records and taxi trajectory data), with each...     

SDN中基于KMOBPSO的高可靠性控制器部署算法

针对SDN中控制器系统的单节点故障问题,兼顾系统成本和系统时延,应用N+1冗余备份模型来提高SDN控制器部署的可靠性,并将其抽象为多目标优化问题.同时,提出了一种融合K-means聚类算法和遗传算子的多目标二进制粒子群算法——KMOBPSO算法,以求解SDN控制器高可靠性部署问题的解.仿真结果表明,所提算法具有求解精度高、分布均匀、沿Pareto前沿面覆盖广的特点,能够显著提高SDN中控制器部署的可靠性.     

铝合金熔炼铸造能源与资源节约

在铝材生产中,熔炼、铸造工序是能源与资源消耗多的工序,因此,节约资源、降低烧损与能耗有着重要意义。降低能耗还可以相应地减少温室气体与有害、有毒物质排放,对环保有利。中国当前铝合金熔炼铸造能源与资源节约的主要措施:调整加工用锭坯供应结构,大幅提高电解铝厂供应的锭坯,由2013年供应的42%提高到"十三五"末的65%-70%;加快走出去的力度,到国外去办铝厂,将在国外生产的铝合金锭坯运回来,争取2020年出口的铝材与铝制品全部以进口锭坯加工,这是最大的资源与能源节约;加强废铝回收与有效再生利用;加强创新,大力采用新装备、新技术与新工艺;加强管理,精心操作,管理中还有较大的能源与资源节约潜力。