arXiv subjects

Li Zhou

Publications and source records attributed to Li Zhou.

At least 145 records · Page 8Linked to original sources

arXiv2021

Generating Self-Contained and Summary-Centric Question Answer Pairs via Differentiable Reward Imitation Learning

Motivated by suggested question generation in conversational news recommendation systems, we propose a model for generating question-answer pairs (QA pairs) with self-contained, summary-centric questions and length-constrained, article-summarizing answers. We begin by collecting a new dataset of news articles with questions as titles and pairing them with summaries of varying length. This dataset is used to learn a QA pair generation model producing summaries as answers that balance brevity with sufficiency jointly with their corresponding questions. We then reinforce the QA pair generation process with a differentiable reward function to mitigate exposure bias, a common problem in natural language generation. Both automatic metrics and human evaluation demonstrate these QA pairs successfully capture the central gists of the articles and achieve high answer accuracy.

cs.CL↗

arXiv2021

Spatial-Temporal Deep Intention Destination Networks for Online Travel Planning

Nowadays, artificial neural networks are widely used for users' online travel planning. Personalized travel planning has many real applications and is affected by various factors, such as transportation type, intention destination estimation, budget limit and crowdness prediction. Among those factors, users' intention destination prediction is an essential task in online travel platforms. The reason is that, the user may be interested in the travel plan only when the plan matches his real intention destination. Therefore, in this paper, we focus on predicting users' intention destinations in online travel platforms. In detail, we act as online travel platforms (such as Fliggy and Airbnb) to recommend travel plans for users, and the plan consists of various vacation items including hotel package, scenic packages and so on. Predicting the actual intention destination in travel planning is challenging. Firstly, users' intention destination is highly related to their travel status (e.g., planning for a trip or finishing a trip). Secondly, users' actions (e.g. clicking, searching) over different product types (e.g. train tickets, visa application) have different indications in destination prediction. Thirdly, users may mostly visit the travel platforms just before public holidays, and thus user behaviors in online travel platforms are more sparse, low-frequency and long-period. Therefore, we propose a Deep Multi-Sequences fused neural Networks (DMSN) to predict intention destinations from fused multi-behavior sequences. Real datasets are used to evaluate the performance of our proposed DMSN models. Experimental results indicate that the proposed DMSN models can achieve high intention destination prediction accuracy.

cs.AI↗

arXiv2021

Summary-Oriented Question Generation for Informational Queries

Users frequently ask simple factoid questions for question answering (QA) systems, attenuating the impact of myriad recent works that support more complex questions. Prompting users with automatically generated suggested questions (SQs) can improve user understanding of QA system capabilities and thus facilitate more effective use. We aim to produce self-explanatory questions that focus on main document topics and are answerable with variable length passages as appropriate. We satisfy these requirements by using a BERT-based Pointer-Generator Network trained on the Natural Questions (NQ) dataset. Our model shows SOTA performance of SQ generation on the NQ dataset (20.1 BLEU-4). We further apply our model on out-of-domain news articles, evaluating with a QA system due to the lack of gold questions and demonstrate that our model produces better SQs for news articles -- with further confirmation via a human evaluation.

cs.CL↗

arXiv2021

Cooperative Multi-Agent Reinforcement Learning Based Distributed Dynamic Spectrum Access in Cognitive Radio Networks

With the development of the 5G and Internet of Things, amounts of wireless devices need to share the limited spectrum resources. Dynamic spectrum access (DSA) is a promising paradigm to remedy the problem of inefficient spectrum utilization brought upon by the historical command-and-control approach to spectrum allocation. In this paper, we investigate the distributed DSA problem for multi-user in a typical multi-channel cognitive radio network. The problem is formulated as a decentralized partially observable Markov decision process (Dec-POMDP), and we proposed a centralized off-line training and distributed on-line execution framework based on cooperative multi-agent reinforcement learning (MARL). We employ the deep recurrent Q-network (DRQN) to address the partial observability of the state for each cognitive user. The ultimate goal is to learn a cooperative strategy which maximizes the sum throughput of cognitive radio network in distributed fashion without coordination information exchange between cognitive users. Finally, we validate the proposed algorithm in various settings through extensive experiments. From the simulation results, we can observe that the proposed algorithm can converge fast and achieve almost the optimal performance.

cs.NI↗

arXiv2021

Deep Convolutional Neural Networks to Predict Mutual Coupling Effects in Metasurfaces

Metasurfaces have provided a novel and promising platform for the realization of compact and large-scale optical devices. The conventional metasurface design approach assumes periodic boundary conditions for each element, which is inaccurate in most cases since the near-field coupling effects between elements will change when surrounded by non-identical structures. In this paper, we propose a deep learning approach to predict the actual electromagnetic (EM) responses of each target meta-atom placed in a large array with near-field coupling effects taken into account. The predicting neural network takes the physical specifications of the target meta-atom and its neighbors as input, and calculates its phase and amplitude in milliseconds. This approach can be applied to explain metasurfaces' performance deterioration caused by mutual coupling and further used to optimize their efficiencies once combined with optimization algorithms. To demonstrate the efficacy of this methodology, we obtain large improvements in efficiency for a beam deflector and a metalens over the conventional design approach. Moreover, we show the correlations between a metasurface's performance and its design errors caused by mutual coupling are not bound to certain specifications (materials, shapes, etc.). As such, we envision that this approach can be readily applied to explore the mutual coupling effects and improve the performance of various metasurface designs.

physics.optics↗

arXiv2021

A Quantum Interpretation of Bunched Logic for Quantum Separation Logic

We propose a model of the substructural logic of Bunched Implications (BI) that is suitable for reasoning about quantum states. In our model, the separating conjunction of BI describes separable quantum states. We develop a program logic where pre- and post-conditions are BI formulas describing quantum states -- the program logic can be seen as a counterpart of separation logic for imperative quantum programs. We exercise the logic for proving the security of quantum one-time pad and secret sharing, and we show how the program logic can be used to discover a flaw in Google Cirq's tutorial on the Variational Quantum Algorithm (VQA).

cs.LO↗

arXiv2020

Inverse Reinforcement Learning with Natural Language Goals

Humans generally use natural language to communicate task requirements to each other. Ideally, natural language should also be usable for communicating goals to autonomous machines (e.g., robots) to minimize friction in task specification. However, understanding and mapping natural language goals to sequences of states and actions is challenging. Specifically, existing work along these lines has encountered difficulty in generalizing learned policies to new natural language goals and environments. In this paper, we propose a novel adversarial inverse reinforcement learning algorithm to learn a language-conditioned policy and reward function. To improve generalization of the learned policy and reward function, we use a variational goal generator to relabel trajectories and sample diverse goals during training. Our algorithm outperforms multiple baselines by a large margin on a vision-based natural language instruction following dataset (Room-2-Room), demonstrating a promising advance in enabling the use of natural language instructions in specifying agent goals.

cs.LG↗

arXiv2020

The replacement system of the JUNO liquid scintillator pilot experiment at Daya Bay

The Jiangmen Underground Neutrino Observatory (JUNO), a multi-purpose neutrino experiment, will use 20 kt liquid scintillator (LS). To achieve the physics goal of determining the neutrino mass ordering, 3$\%$ energy resolution at 1 MeV is required. This puts strict requirements on the LS light yield and the transparency. Four LS purification steps have been designed and mid-scale plants have been built at Daya Bay. To examine the performance of the purified LS and find the optimized LS composition, the purified LS was injected to the antineutrino detector 1 in the experimental hall 1 (EH1-AD1) of the Daya Bay neutrino experiment. To pump out the original gadolinium loaded LS and fill the new LS, a LS replacement system has been built in EH1 in 2017. By replacing the Gd-LS with purified water, then replacing the water with purified LS, the replacement system successfully achieved the designed goal. Subsequently, the fluorescence and the wavelength shifter were added to higher concentrations via the replacement system. The data taken at various LS compositions helped JUNO determine the final LS cocktail. Details of the design, the construction, and the operation of the replacement system are reported in this paper.

physics.ins-det↗

arXiv2020

Research on AI Composition Recognition Based on Music Rules

The development of artificial intelligent composition has resulted in the increasing popularity of machine-generated pieces, with frequent copyright disputes consequently emerging. There is an insufficient amount of research on the judgement of artificial and machine-generated works; the creation of a method to identify and distinguish these works is of particular importance. Starting from the essence of the music, the article constructs a music-rule-identifying algorithm through extracting modes, which will identify the stability of the mode of machine-generated music, to judge whether it is artificial intelligent. The evaluation datasets used are provided by the Conference on Sound and Music Technology(CSMT). Experimental results demonstrate the algorithm to have a successful distinguishing ability between datasets with different source distributions. The algorithm will also provide some technological reference to the benign development of the music copyright and artificial intelligent music.

cs.AI↗

arXiv2020

Solving the k-sparse Eigenvalue Problem with Reinforcement Learning

We examine the possibility of using a reinforcement learning (RL) algorithm to solve large-scale eigenvalue problems in which the desired the eigenvector can be approximated by a sparse vector with at most $k$ nonzero elements, where $k$ is relatively small compare to the dimension of the matrix to be partially diagonalized. This type of problem arises in applications in which the desired eigenvector exhibits localization properties and in large-scale eigenvalue computations in which the amount of computational resource is limited. When the positions of these nonzero elements can be determined, we can obtain the $k$-sparse approximation to the original problem by computing eigenvalues of a $k\times k$ submatrix extracted from $k$ rows and columns of the original matrix. We review a previously developed greedy algorithm for incrementally probing the positions of the nonzero elements in a $k$-sparse approximate eigenvector and show that the greedy algorithm can be improved by using an RL method to refine the selection of $k$ rows and columns of the original matrix. We describe how to represent states, actions, rewards and policies in an RL algorithm designed to solve the $k$-sparse eigenvalue problem and demonstrate the effectiveness of the RL algorithm on two examples originating from quantum many-body physics.

physics.comp-ph↗

arXiv2020

Discovering the Sky at the Longest wavelengths with a lunar orbit array

Due to ionosphere absorption and the interference by natural and artificial radio emissions, astronomical observation from the ground becomes very difficult at the wavelengths of decametre or longer, which we shall refer as the ultralong wavelengths. This unexplored part of electromagnetic spectrum has the potential of great discoveries, notably in the study of cosmic dark ages and dawn, but also in heliophysics and space weather, planets and exoplanets, cosmic ray and neutrinos, pulsar and interstellar medium (ISM), extragalactic radio sources, and so on. The difficulty of the ionosphere can be overcome by space observation, and the Moon can shield the radio frequency interferences (RFIs) from the Earth. A lunar orbit array can be a practical first step of opening up the ultralong wave band. Compared with a lunar surface observatory on the far side, the lunar orbit array is simpler and more economical, as it does not need to make the risky and expensive landing, can be easily powered with solar energy, and the data can be transmitted back to the Earth when it is on the near-side part of the orbit. Here I describe the Discovering Sky at the Longest wavelength (DSL) project, which will consist of a mother satellite and 6~9 daughter satellites, flying on the same circular orbit around the Moon, and forming a linear interferometer array. The data are collected by the mother satellite which computes the interferometric cross-correlations (visibilities) and transmits the data back to the Earth. The whole array can be deployed on the lunar orbit with a single rocket launch. The project is under intensive study in China.

astro-ph.IM↗

arXiv2020

Multi-domain Dialogue State Tracking as Dynamic Knowledge Graph Enhanced Question Answering

Multi-domain dialogue state tracking (DST) is a critical component for conversational AI systems. The domain ontology (i.e., specification of domains, slots, and values) of a conversational AI system is generally incomplete, making the capability for DST models to generalize to new slots, values, and domains during inference imperative. In this paper, we propose to model multi-domain DST as a question answering problem, referred to as Dialogue State Tracking via Question Answering (DSTQA). Within DSTQA, each turn generates a question asking for the value of a (domain, slot) pair, thus making it naturally extensible to unseen domains, slots, and values. Additionally, we use a dynamically-evolving knowledge graph to explicitly learn relationships between (domain, slot) pairs. Our model has a 5.80% and 12.21% relative improvement over the current state-of-the-art model on MultiWOZ 2.0 and MultiWOZ 2.1 datasets, respectively. Additionally, our model consistently outperforms the state-of-the-art model in domain adaptation settings. (Code is released at https://github.com/alexa/dstqa )

cs.CL↗

arXiv2020

XiaoiceSing: A High-Quality and Integrated Singing Voice Synthesis System

This paper presents XiaoiceSing, a high-quality singing voice synthesis system which employs an integrated network for spectrum, F0 and duration modeling. We follow the main architecture of FastSpeech while proposing some singing-specific design: 1) Besides phoneme ID and position encoding, features from musical score (e.g.note pitch and length) are also added. 2) To attenuate off-key issues, we add a residual connection in F0 prediction. 3) In addition to the duration loss of each phoneme, the duration of all the phonemes in a musical note is accumulated to calculate the syllable duration loss for rhythm enhancement. Experiment results show that XiaoiceSing outperforms the baseline system of convolutional neural networks by 1.44 MOS on sound quality, 1.18 on pronunciation accuracy and 1.38 on naturalness respectively. In two A/B tests, the proposed F0 and duration modeling methods achieve 97.3% and 84.3% preference rate over baseline respectively, which demonstrates the overwhelming advantages of XiaoiceSing.

eess.AS↗

arXiv2020

Proq: Projection-based Runtime Assertions for Debugging on a Quantum Computer

In this paper, we propose Proq, a runtime assertion scheme for testing and debugging quantum programs on a quantum computer. The predicates in Proq are represented by projections (or equivalently, closed subspaces of the state space), following Birkhoff-von Neumann quantum logic. The satisfaction of a projection by a quantum state can be directly checked upon a small number of projective measurements rather than a large number of repeated executions. On the theory side, we rigorously prove that checking projection-based assertions can help locate bugs or statistically assure that the semantic function of the tested program is close to what we expect, for both exact and approximate quantum programs. On the practice side, we consider hardware constraints and introduce several techniques to transform the assertions, making them directly executable on the measurement-restricted quantum computers. We also propose to achieve simplified assertion implementation using local projection technique with soundness guaranteed. We compare Proq with existing quantum program assertions and demonstrate the effectiveness and efficiency of Proq by its applications to assert two ingenious quantum algorithms, the Harrow-Hassidim-Lloyd algorithm and Shor's algorithm.

cs.PL↗

arXiv2020

RNNFast: An Accelerator for Recurrent Neural Networks Using Domain Wall Memory

Recurrent Neural Networks (RNNs) are an important class of neural networks designed to retain and incorporate context into current decisions. RNNs are particularly well suited for machine learning problems in which context is important, such as speech recognition and language translation. This work presents RNNFast, a hardware accelerator for RNNs that leverages an emerging class of non-volatile memory called domain-wall memory (DWM). We show that DWM is very well suited for RNN acceleration due to its very high density and low read/write energy. At the same time, the sequential nature of input/weight processing of RNNs mitigates one of the downsides of DWM, which is the linear (rather than constant) data access time.RNNFast is very efficient and highly scalable, with flexible mapping of logical neurons to RNN hardware blocks. The basic hardware primitive, the RNN processing element (PE) includes custom DWM-based multiplication, sigmoid and tanh units for high density and low-energy. The accelerator is designed to minimize data movement by closely interleaving DWM storage and computation. We compare our design with a state-of-the-art GPGPU and find21.8x higher performance with70x lower energy

cs.NE↗

arXiv2020

The local and global properties of different types of supernova host galaxies

By using Data Analysis Pipeline (DAP) products of Mapping Nearby Galaxies at Apache Point Observatory (MaNGA), which are publicly available from the SDSS Data Release 15, we analyze the local properties at the SN explosion sites and global properties of different types of SN host galaxies to explore the explosion environments of different types of SNe. In our sample, there are 67 SN host galaxies in the field of view of MaNGA, including 32 Type Ia, 29 CCSNe, 1 super-luminous SN (SLSN), 1 Type I and 4 unclassified type of SNe, with which we can perform the K-S test for analysis and derive statistically robust results. Due to the limited sample size, we couldn't remove the mass dependence in this work, which is likely the true driver of the trends for the properties presented in this work. The global star formation rate (SFR) and EW(H$α$) for SN Ia hosts is slightly lower than that for CCSN hosts on average. SN Ia host galaxies are $\sim$ 0.3 dex more massive than CCSN hosts, which implies that the number ratio of CCSNe to Type Ia SNe will decrease with the increasing of stellar mass of host galaxies. The stellar population age of SN Ia host galaxies is older than that of CCSN hosts on average. There is no significant difference between different types of SN hosts for some properties, including local SFR density ($Σ\rm SFR$), local and global gas-phase oxygen abundance. For most galaxies in our sample, the global gas-phase oxygen abundance estimated from the integrated spectra of SN hosts can represent the local gas-phase oxygen abundance at the SN explosion sites with small bias.

astro-ph.GA↗

arXiv2020

Multifunctional Metasurface Design with a Generative Adversarial Network

Metasurfaces have enabled precise electromagnetic wave manipulation with strong potential to obtain unprecedented functionalities and multifunctional behavior in flat optical devices. These advantages in precision and functionality come at the cost of tremendous difficulty in finding individual meta-atom structures based on specific requirements (commonly formulated in terms of electromagnetic responses), which makes the design of multifunctional metasurfaces a key challenge in this field. In this paper, we present a Generative Adversarial Networks (GAN) that can tackle this problem and generate meta-atom/metasurface designs to meet multifunctional design goals. Unlike conventional trial-and-error or iterative optimization design methods, this new methodology produces on-demand free-form structures involving only a single design iteration. More importantly, the network structure and the robust training process are independent of the complexity of design objectives, making this approach ideal for multifunctional device design. Additionally, the ability of the network to generate distinct classes of structures with similar electromagnetic responses but different physical features could provide added latitude to accommodate other considerations such as fabrication constraints and tolerances. We demonstrate the network's ability to produce a variety of multifunctional metasurface designs by presenting a bifocal metalens, a polarization-multiplexed beam deflector, a polarization-multiplexed metalens and a polarization-independent metalens.

physics.optics↗

arXiv2020

Gamma-ray Burst Spectrum with a Time-dependent Injection Rate of High-energy Electrons

Although the physical origin of prompt emission in gamma-ray bursts (GRBs) remains inconclusive, previous studies have considered the synchrotron radiation of relativistic electrons as a promising mechanism. These works usually adopted a invariable injection rate of electrons ($Q$) which may be discordant with that in a Poynting-flux dominated jet. In a Poynting-flux dominated jet (e.g., ICMART model, Zhang & Yan 2011), the number of magnetic reconnections occurred simultaneously may grow rapidly with time and results in an increase of $Q$ with time. This paper is dedicated to study the synchrotron radiation spectrum in this scenario. It is found that the radiation spectrum would obviously get harder if an increasing $Q$ is adopted and a Band-like radiation spectrum can be obtained if the increase of $Q$ is fast enough. The latter is related to the fact that a bump-shape rather than a power-law spectrum appears in the low-energy regime of the obtained electron spectrum. This effect can strongly harden the low-energy radiation spectrum. It indicates that an increasing $Q$ can help to alleviate the "fast-cooling problem" of synchrotron radiation for GRBs. Our studies also reveal that a Poynting-flux dominated jet with a large emission radius, a small length of the magnetic reconnection region, or a low-minimum energy of injected electron would prefer to form a Band-like radiation spectrum. We suggest that the Band spectrum found in GRBs may be the synchrotron emission of the electrons with a bump-shape distribution in its low-energy regime.

astro-ph.HE↗