Search

Rule-based dialogue management is still the most popular solution for industrial task-oriented dialogue systems for their interpretablility. However, it is hard for developers to maintain the dialogue logic when the scenarios get more and more complex. On the other hand, data-driven dialogue systems, usually with end-to-end structures, are popular in academic research and easier to deal with complex conversations, but such methods require plenty of training data and the behaviors are less interpretable. In this paper, we propose a method to leverages the strength of both rule-based and data-driven dialogue managers (DM). We firstly introduce the DM of Carina Dialog System (CDS, an advanced industrial dialogue system built by Microsoft). Then we propose the "model-trigger" design to make the DM trainable thus scalable to scenario changes. Furthermore, we integrate pre-trained models and empower the DM with few-shot capability. The experimental results demonstrate the effectiveness and strong few-shot capability of our method., Comment: AAAI 2021 Demo Paper

The triple-based knowledge in large-scale knowledge bases is most likely lacking in structural logic and problematic of conducting knowledge hierarchy. In this paper, we introduce the concept of metaknowledge to knowledge engineering research for the purpose of structural knowledge construction. Therefore, the Metaknowledge Extraction Framework and Document Structure Tree model are presented to extract and organize metaknowledge elements (titles, authors, abstracts, sections, paragraphs, etc.), so that it is feasible to extract the structural knowledge from multi-modal documents. Experiment results have proved the effectiveness of metaknowledge elements extraction by our framework. Meanwhile, detailed examples are given to demonstrate what exactly metaknowledge is and how to generate it. At the end of this paper, we propose and analyze the task flow of metaknowledge applications and the associations between knowledge and metaknowledge.

The paths leading to future networks are pointing towards a data-driven paradigm to better cater to the explosive growth of mobile services as well as the increasing heterogeneity of mobile devices, many of which generate and consume large volumes and variety of data. These paths are also hampered by significant challenges in terms of security, privacy, services provisioning, and network management. Blockchain, which is a technology for building distributed ledgers that provide an immutable log of transactions recorded in a distributed network, has become prominent recently as the underlying technology of cryptocurrencies and is revolutionizing data storage and processing in computer network systems. For future data-driven networks (DDNs), blockchain is considered as a promising solution to enable the secure storage, sharing, and analytics of data, privacy protection for users, robust, trustworthy network control, and decentralized routing and resource managements. However, many important challenges and open issues remain to be addressed before blockchain can be deployed widely to enable future DDNs. In this article, we present a survey on the existing research works on the application of blockchain technologies in computer networks, and identify challenges and potential solutions in the applications of blockchains in future DDNs. We identify application scenarios in which future blockchain-empowered DDNs could improve the efficiency and security, and generally the effectiveness of network services.

Recently, deep learning based image deblurring has been well developed. However, exploiting the detailed image features in a deep learning framework always requires a mass of parameters, which inevitably makes the network suffer from high computational burden. To solve this problem, we propose a lightweight multiinformation fusion network (LMFN) for image deblurring. The proposed LMFN is designed as an encoder-decoder architecture. In the encoding stage, the image feature is reduced to various smallscale spaces for multi-scale information extraction and fusion without a large amount of information loss. Then, a distillation network is used in the decoding stage, which allows the network benefit the most from residual learning while remaining sufficiently lightweight. Meanwhile, an information fusion strategy between distillation modules and feature channels is also carried out by attention mechanism. Through fusing different information in the proposed approach, our network can achieve state-of-the-art image deblurring result with smaller number of parameters and outperforms existing methods in model complexity.

To achieve the joint active and passive beamforming gains in the reconfigurable intelligent surface assisted millimeter wave system, the reflected cascade channel needs to be accurately estimated. Many strategies have been proposed in the literature to solve this issue. However, whether the Cram\'er-Rao lower bound (CRLB) of such estimation is achievable still remains uncertain. To fill this gap, we first convert the channel estimation problem into a sparse signal recovery problem by utilizing the properties of discrete Fourier transform matrix and Kronecker product. Then, a joint typicality based estimator is utilized to carry out the signal recovery task. We show that, through both mathematical proofs and numerical simulations, the solution proposed in this letter can in fact asymptotically achieve the CRLB., Comment: 5 pages, 3 figures, 1 table. To be published in IEEE Wireless Communications Letters

Perfect channel state information (CSI) is usually required when considering relay selection and power allocation in cooperative communication. However, it is difficult to get an accurate CSI in practical situations. In this letter, we study the outage probability minimizing problem based on optimizing relay selection and transmission power. We propose a prioritized experience replay aided deep deterministic policy gradient learning framework, which can find an optimal solution by dealing with continuous action space, without any prior knowledge of CSI. Simulation results reveal that our approach outperforms reinforcement learning based methods in existing literatures, and improves the communication success rate by about 4%.

Cooperative communication is an effective approach to improve spectrum utilization. In order to reduce outage probability of communication system, most studies propose various schemes for relay selection and power allocation, which are based on the assumption of channel state information (CSI). However, it is difficult to get an accurate CSI in practice. In this paper, we study the outage probability minimizing problem subjected to a total transmission power constraint in a two-hop cooperative relay network. We use reinforcement learning (RL) methods to learn strategies for relay selection and power allocation, which do not need any prior knowledge of CSI but simply rely on the interaction with communication environment. It is noted that conventional RL methods, including most deep reinforcement learning (DRL) methods, cannot perform well when the search space is too large. Therefore, we first propose a DRL framework with an outage-based reward function, which is then used as a baseline. Then, we further propose a hierarchical reinforcement learning (HRL) framework and training algorithm. A key difference from other RL-based methods in existing literatures is that, our proposed HRL approach decomposes relay selection and power allocation into two hierarchical optimization objectives, which are trained in different levels. With the simplification of search space, the HRL approach can solve the problem of sparse reward, while the conventional RL method fails. Simulation results reveal that compared with traditional DRL method, the HRL training algorithm can reach convergence 30 training iterations earlier and reduce the outage probability by 5% in two-hop relay network with the same outage threshold.

Route planning is important in transportation. Existing works focus on finding the shortest path solution or using metrics such as safety and energy consumption to determine the planning. It is noted that most of these studies rely on prior knowledge of road network, which may be not available in certain situations. In this paper, we design a route planning algorithm based on deep reinforcement learning (DRL) for pedestrians. We use travel time consumption as the metric, and plan the route by predicting pedestrian flow in the road network. We put an agent, which is an intelligent robot, on a virtual map. Different from previous studies, our approach assumes that the agent does not need any prior information about road network, but simply relies on the interaction with the environment. We propose a dynamically adjustable route planning (DARP) algorithm, where the agent learns strategies through a dueling deep Q network to avoid congested roads. Simulation results show that the DARP algorithm saves 52% of the time under congestion condition when compared with traditional shortest path planning algorithms.

The advantages of millimeter-wave and large antenna arrays technologies for accurate wireless localization received extensive attentions recently. However, how to further improve the accuracy of wireless localization, even in the case of obstructed line-of-sight, is largely undiscovered. In this paper, the reconfigurable intelligent surface (RIS) is introduced into the system to make the positioning more accurate. First, we establish the three-dimensional RIS-assisted wireless localization channel model. After that, we derive the Fisher information matrix and the Cramer-Rao lower bound for evaluating the estimation of absolute mobile station position. Finally, we propose an alternative optimization method and a gradient decent method to optimize the reflect beamforming, which aims to minimize the Cramer-Rao lower bound to obtain a more accurate estimation. Our results show that the proposed methods significantly improve the accuracy of positioning, and decimeter-level or even centimeter-level positioning can be achieved by utilizing the RIS with a large number of reflecting elements.

We consider the positivity bounds on dimension-8 four-electron operators and study two related phenomenological aspects at future lepton colliders. First, if positivity is violated, probing such violations will revolutionize our understanding of the fundamental pillars of quantum field theory and the $S$-matrix theory. We observe that positivity violation at scales of 1--10 TeV can potentially be probed at future lepton colliders even if one assumes that dimension-6 operators are also present. Second, the positive nature of the dimension-8 parameter space often allows us to either directly infer the existence of UV-scale particles together with their quantum numbers or exclude them up to certain scales in a model-independent way. In particular, dimension-8 positivity plays an important role in the test of the Standard Model. If no deviations from the Standard Model are observed, it allows for simultaneous exclusion limits on all kinds of potential UV-complete models. Unlike the dimension-6 case, these limits apply regardless of the UV model setup and cannot be removed by possible cancellations among various UV contributions. This thus consists of a novel and universal test to confirm the Standard Model. We demonstrate with realistic examples how all the previously mentioned possibilities, including the test of positivity violation, can be achieved. Hence, we provide an important motivation for studying dimension-8 operators more comprehensively., Comment: 24 pages, 6 figures; typos corrected

Measuring the fermion Yukawa coupling constants is important for understanding the origin of the fermion masses and its relationship to the spontaneously electroweak symmetry breaking. On the other hand, some new physics models will change the Lorentz structure of the Yukawa interactions between the standard model (SM) fermions and the SM-like Higgs boson even in their decoupling limit. Thus the precisely measurement of the fermion Yukawa interactions is a powerful tool of new physics searching in the decoupling limit. In this work, we show the possibility of investigating the Lorentz structure of the bottom-quark Yukawa interaction with the 125GeV SM-like Higgs boson at future $e^+e^-$ colliders., Comment: 8 pages, 7 figures

Ozone (O$_{3}$) is a key oxidant and pollutant in the lower atmosphere. Significant increases in surface O$_{3}$ have been reported in many cities during the COVID-19 lockdown. Here we conduct comprehensive observation and modeling analyses of surface O$_{3}$ across China for periods before and during the lockdown. We find that daytime O$_{3}$ decreased in the subtropical south, in contrast to increases in most other regions. Meteorological changes and emission reductions both contributed to the O$_{3}$ changes, with a larger impact from the former especially in central China. The plunge in nitrogen oxide (NO$_{x}$) emission contributed to O$_{3}$ increases in populated regions, whereas the reduction in volatile organic compounds (VOC) contributed to O$_{3}$ decreases across the country. Due to a decreasing level of NO$_{x}$ saturation from north to south, the emission reduction in NO$_{x}$ (46%) and VOC (32%) contributed to net O$_{3}$ increases in north China; the opposite effects of NO$_{x}$ decrease (49%) and VOC decrease (24%) balanced out in central China, whereas the comparable decreases (45-55%) in these two precursors contributed to net O$_{3}$ declines in south China. Our study highlights the complex dependence of O$_{3}$ on its precursors and the importance of meteorology in the short-term O$_{3}$ variability., Comment: 36 pages, 16 figures. Published in Science of the Total Environment

Reconfigurable intelligent surface (RIS) can effectively control the wavefront of the impinging signals and has emerged as a cost-effective promising solution to improve the spectrum and energy efficiency of wireless systems. Most existing researches on RIS assume that the hardware operations are perfect. However, both physical transceiver and RIS suffer from inevitable hardware impairments in practice, which can lead to severe system performance degradation and increase the complexity of beamforming optimization. Consequently, the existing researches on RIS, including channel estimation, beamforming optimization, spectrum and energy efficiency analysis, etc., cannot directly apply to the case of hardware impairments. In this paper, by taking hardware impairments into consideration, we conduct the joint transmit and reflect beamforming optimization, and reevaluate the system performance. First, we characterize the closed-form estimators of direct and cascaded channels in both single-user and multi-user cases, and analyze the impact of hardware impairments on channel estimation accuracy. Then, the optimal transmit beamforming solution is derived, and a gradient descent method-based algorithm is also proposed to optimize the reflect beamforming. Moreover, we analyze the three types of asymptotic channel capacities with respect to the transmit power, the antenna number, and the reflecting element number. Finally, in terms of the system energy consumption, we analyze the power scaling law and the energy efficiency. Our experimental results also reveal an encouraging phenomenon that the RIS-assisted wireless system with massive reflecting elements can achieve both high spectrum and energy efficiency without the need for massive antennas and without allocating too many resources to optimize the reflect beamforming.

Recently, as explosive growth of mobile data traffic, the performance of wireless communication systems requires to be enhanced significantly in future. Intelligent reflecting surface (IRS) can be used as a promising way to improve the energy efficiency of wireless communications with less complexity and hardware cost. Most existing studies consider the cases with ideal hardware, however, both physical transceiver and IRS suffer from non-negligible hardware impairments which may greatly degrade the system performance. In this paper, by taking hardware impairments into consideration, we focus on the energy efficiency analysis of IRS system. Our first contribution is to derive the optimal receive combining and transmit beamforming vectors. After that, we characterize the asymptotic channel capacity. With the derived asymptotic channel capacity and the power consumption model, the analytical upper and lower bounds of energy efficiency are provided. Our results show that an IRS system can achieve both high spectral efficiency and high energy efficiency with moderate number of antennas. This observation is encouraging for that there is no need to cost a lot on expensive high-quality antennas, which corresponds to the requirements of new communication paradigms.

Large reflecting surface (LRS) has emerged as a new solution to improve the energy and spectrum efficiency of wireless communication system. Most existing studies were conducted with an assumption of ideal hardware, and the impact of hardware impairments receives little attention. However, the non-negligible hardware impairments should be taken into consideration when we evaluate the system performance. In this paper, we consider an LRS assisted communication system with hardware impairments, and focus on the channel estimation study and the power scaling law analysis. First, with linear minimum mean square error estimation, we theoretically characterize the relationship between channel estimation performance and impairment level, number of reflecting elements, and pilot power. After that, we analyze the power scaling law and reveal that if the base station (BS) has perfect channel state information, the transmit power of user can be made inversely proportional to the number of BS antennas and the square of the number of reflecting elements with no reduction in performance; If the BS has imperfectly estimated channel state information, to achieve the same performance, the transmit power of user can be made inversely proportional to the square-root of the number of BS antennas and the square of the number of reflecting elements.