Yang Liu - Nanyang Technological University

Yang Liu
Are you Yang Liu?

Claim your profile, edit publications, add additional information:

Contact Details

Yang Liu
Nanyang Technological University

Pubs By Year

External Links

Pub Categories

Computer Science - Computation and Language (12)
Physics - Chemical Physics (4)
Computer Science - Software Engineering (4)
Physics - Physics and Society (3)
Physics - Materials Science (3)
Solar and Stellar Astrophysics (3)
Computer Science - Learning (3)
Mathematics - Numerical Analysis (2)
Computer Science - Networking and Internet Architecture (2)
Computer Science - Robotics (2)
Computer Science - Computer Vision and Pattern Recognition (2)
Computer Science - Cryptography and Security (2)
Nonlinear Sciences - Adaptation and Self-Organizing Systems (2)
Quantum Physics (2)
Physics - Biological Physics (2)
Computer Science - Artificial Intelligence (2)
Mathematics - Information Theory (1)
Statistics - Applications (1)
Mathematics - Number Theory (1)
Computer Science - Information Theory (1)
Mathematics - Complex Variables (1)
Physics - Soft Condensed Matter (1)
Physics - Fluid Dynamics (1)
Mathematics - Analysis of PDEs (1)
Physics - Computational Physics (1)
Physics - Statistical Mechanics (1)
Computer Science - Logic in Computer Science (1)
Mathematics - Quantum Algebra (1)
Computer Science - Computer Science and Game Theory (1)
Computer Science - Multimedia (1)
Mathematics - Differential Geometry (1)
Mathematics - Operator Algebras (1)
Computer Science - Digital Libraries (1)
Mathematics - Optimization and Control (1)
Statistics - Machine Learning (1)
Quantitative Biology - Populations and Evolution (1)

Publications Authored By Yang Liu

In this paper, we focus on learning structure-aware document representations from data without recourse to a discourse parser or additional annotations. Drawing inspiration from recent efforts to empower neural networks with a structural bias, we propose a model that can encode a document while automatically inducing rich structural dependencies. Specifically, we embed a differentiable non-projective parsing algorithm into a neural model and use attention mechanisms to incorporate the structural biases. Read More

In order to prevent loss of control (LOC) accidents, the real-time control performance monitoring (CPM) problem is studied for multicopters. Different from the existing literature, this paper does not try to monitor the performance of the controllers directly. Conversely, the unknown disturbances of the multicopter under off-nominal conditions are modeled and assessed. Read More

For highly interested organolead perovskite based solar cells, the photoproducts are regarded as the co-existed exciton and free carriers. In this study, we carefully re-examined this conclusion with our recently developed density-resolved spectroscopic method. Heat-annealing related two photoproduct systems are observed. Read More

While end-to-end neural machine translation (NMT) has made remarkable progress recently, it still suffers from the data scarcity problem for low-resource language pairs and domains. In this paper, we propose a method for zero-resource NMT by assuming that parallel sentences have close probabilities of generating a sentence in a third language. Based on this assumption, our method is able to train a source-to-target NMT model ("student") without parallel corpora available, guided by an existing pivot-to-target NMT model ("teacher") on a source-pivot parallel corpus. Read More

While part-of-speech (POS) tagging and dependency parsing are observed to be closely related, existing work on joint modeling with manually crafted feature templates suffers from the feature sparsity and incompleteness problems. In this paper, we propose an approach to joint POS tagging and dependency parsing using transition-based neural networks. Three neural network based classifiers are designed to resolve shift/reduce, tagging, and labeling conflicts. Read More

Using angle-resolved photoemission spectroscopy (ARPES), we studied bulk and surface electronic band structures of narrow-gap semiconductor lead telluride (PbTe) thin films grown by molecular beam epitaxy both perpendicular and parallel to the {\Gamma}-L direction. The comparison of ARPES data with the first-principles calculation reveals the details of band structures, orbital characters, spin-orbit splitting energies, and surface states. The photon-energy-dependent spectra show the bulk character. Read More

Music emotion recognition (MER) is usually regarded as a multi-label tagging task, and each segment of music can inspire specific emotion tags. Most researchers extract acoustic features from music and explore the relations between these features and their corresponding emotion tags. Considering the inconsistency of emotions inspired by the same music segment for human beings, seeking for the key acoustic features that really affect on emotions is really a challenging task. Read More

Policy gradient methods have been successfully applied to many complex reinforcement learning problems. However, policy gradient methods suffer from high variance, slow convergence, and inefficient exploration. In this work, we introduce a maximum entropy policy optimization framework which explicitly encourages parameter exploration, and show that this framework can be reduced to a Bayesian inference problem. Read More

Existing Android malware detection approaches use a variety of features such as security sensitive APIs, system calls, control-flow structures and information flows in conjunction with Machine Learning classifiers to achieve accurate detection. Each of these feature sets provides a unique semantic perspective (or view) of apps' behaviours with inherent strengths and limitations. Meaning, some views are more amenable to detect certain attacks but may not be suitable to characterise several other attacks. Read More

Quantum digital signatures (QDS) provide a means for signing electronic communications with informationtheoretic security. However, all previous demonstrations of quantum digital signatures assume trusted measurement devices. This renders them vulnerable against detector side-channel attacks, just like quantum key distribution. Read More

We have developed a data-driven magnetohydrodynamic (MHD) model of the global solar corona which uses characteristically-consistent boundary conditions (BCs) at the inner boundary. Our global solar corona model can be driven by different observational data including Solar Dynamics Observatory/Helioseismic and Magnetic Imager (SDO/HMI) synoptic vector magnetograms together with the horizontal velocity data in the photosphere obtained by the time-distance helioseismology method, and the line-of-sight (LOS) magnetogram data obtained by HMI, Solar and Heliospheric Observatory/Michelson Doppler Imager (SOHO/MDI), National Solar Observatory/Global Oscillation Network Group (NSO/GONG) and Wilcox Solar Observatory (WSO). We implemented our model in the Multi-Scale Fluid-Kinetic Simulation Suite (MS-FLUKSS) - a suite of adaptive mesh refinement (AMR) codes built upon the Chombo AMR framework developed at the Lawrence Berkeley National Laboratory. Read More

The solar active region photospheric magnetic field evolves rapidly during major eruptive events, suggesting appreciable feedback from the corona. Previous studies of these "magnetic imprints" are mostly based on line-of-sight only or lower-cadence vector observations; a temporally resolved depiction of the vector field evolution is hitherto lacking. Here, we introduce the high-cadence (90~s or 135~s) vector magnetogram dataset from the Helioseismic and Magnetic Imager (HMI) that is well suited for investigating the phenomenon. Read More

Assurance of information-flow security by formal methods is mandated in security certification of separation kernels. As an industrial standard for improving safety, ARINC 653 has been complied with by mainstream separation kernels. Due to the new trend of integrating safe and secure functionalities into one separation kernel, security analysis of ARINC 653 as well as a formal specification with security proofs are thus significant for the development and certification of ARINC 653 compliant Separation Kernels (ARINC SKs). Read More

For argumentation mining, there are several sub-tasks such as argumentation component type classification, relation classification. Existing research tends to solve such sub-tasks separately, but ignore the close relation between them. In this paper, we present a joint framework incorporating logical relation between sub-tasks to improve the performance of argumentation structure generation. Read More

We study the approach to obtaining least squares solutions to systems of linear algebraic equations over networks by using distributed algorithms. Each node has access to one of the linear equations and holds a dynamic state. The aim for the node states is to reach a consensus as a least squares solution of the linear equations by exchanging their states with neighbors over an underlying interaction graph. Read More

Separation kernels provide temporal/spatial separation and controlled information flow to their hosted applications. They are introduced to decouple the analysis of applications in partitions from the analysis of the kernel itself. More than 20 implementations of separation kernels have been developed and widely applied in critical domains, e. Read More

A bridge in a graph is an edge whose removal disconnects the graph and increases the number of connected components. We calculate the fraction of bridges in a wide range of real-world networks and their randomized counterparts. We find that real networks typically have more bridges than their completely randomized counterparts, but very similar fraction of bridges as their degree-preserving randomizations. Read More

Identifying and correcting grammatical errors in the text written by non-native writers has received increasing attention in recent years. Although a number of annotated corpora have been established to facilitate data-driven grammatical error detection and correction approaches, they are still limited in terms of quantity and coverage because human annotation is labor-intensive, time-consuming, and expensive. In this work, we propose to utilize unlabeled data to train neural network based grammatical error detection models. Read More

Peer prediction mechanisms are often adopted to elicit truthful contributions from crowd workers when no ground-truth verification is available. Recently, mechanisms of this type have been developed to incentivize effort exertion, in addition to truthful elicitation. In this paper, we study a sequential peer prediction problem where a data requester wants to dynamically determine the reward level to optimize the trade-off between the quality of information elicited from workers and the total expected payment. Read More

We first propose a conformal geometry for Connes-Landi noncommutative manifolds and study the associated scalar curvature. The new scalar curvature contains its Riemannian counterpart as the commutative limit. Similar to the results on noncommutative two tori, the quantum part of the curvature consists of actions of the modular derivation through two local curvature functions. Read More

Random numbers are indispensable for a variety of applications ranging from testing physics foundation to information encryption. In particular, nonlocality tests provide a strong evidence to our current understanding of nature -- quantum mechanics. All the random number generators (RNG) used for the existing tests are constructed locally, making the test results vulnerable to the freedom-of-choice loophole. Read More

While recent neural machine translation approaches have delivered state-of-the-art performance for resource-rich language pairs, they suffer from the data scarcity problem for resource-scarce language pairs. Although this problem can be alleviated by exploiting a pivot language to bridge the source and target languages, the source-to-pivot and pivot-to-target translation models are usually independently trained. In this work, we introduce a joint training algorithm for pivot-based neural machine translation. Read More

Although end-to-end Neural Machine Translation (NMT) has achieved remarkable progress in the past two years, it suffers from a major drawback: translations generated by NMT systems often lack of adequacy. It has been widely observed that NMT tends to repeatedly translate some source words while mistakenly ignoring other words. To alleviate this problem, we propose a novel encoder-decoder-reconstructor framework for NMT. Read More

We propose a novel training algorithm for reinforcement learning which combines the strength of deep Q-learning with a constrained optimization approach to tighten optimality and encourage faster reward propagation. Our novel technique makes deep reinforcement learning more practical by drastically reducing the training time. We evaluate the performance of our approach on the 49 games of the challenging Arcade Learning Environment, and report significant improvements in both training time and accuracy. Read More

Scalable and automatic formal verification for concurrent systems is always demanding, but yet to be developed. In this paper, we propose a verification framework to support automated compositional reasoning for concurrent programs with shared variables. Our framework models concurrent programs as succinct automata and supports the verification of multiple important properties. Read More

We report a THz emitter with excellent performances based on nonmagnetic (NM) and ferromagnetic (FM) heterostructures. The spin currents are first excited by the femtosecond laser beam in the NM/FM bilayer, and then transient charge currents are generated by inverse spin Hall effect, leading to THz emission out of the structure. The broadband THz waves emitted from our film stacks have a peak intensity exceeding 500 um thick ZnTe crystals (standard THz emitters). Read More

The sensitivity (i.e. dynamic response) of complex networked systems has not been well understood, making difficult to predict whether new macroscopic dynamic behavior will emerge even if we know exactly how individual nodes behave and how they are coupled. Read More

Academic leadership is essential for research innovation and impact. Until now, there has been no dedicated measure of leadership by bibliometrics. Popular bibliometric indices are mainly based on academic output, such as the journal impact factor and the number of citations. Read More

Magnetic helicity is a conserved quantity of ideal magneto-hydrodynamics characterized by an inverse turbulent cascade. Accordingly, it is often invoked as one of the basic physical quantities driving the generation and structuring of magnetic fields in a variety of astrophysical and laboratory plasmas. We provide here the first systematic comparison of six existing methods for the estimation of the helicity of magnetic fields known in a finite volume. Read More

Energy efficiency is essential for Wireless Body Area Network (WBAN) applications because of the battery-operated nodes. Other requirements such as throughput, delay, quality of service, and security levels also need to be considered in optimizing the network design. In this paper, we study the case in which the nodes access the medium probabilistically and we formulate an energy efficiency optimization problem under the rate and access probability constraints for IEEE 802. Read More

A lot of prior work on event extraction has exploited a variety of features to represent events. Such methods have several drawbacks: 1) the features are often specific for a particular domain and do not generalize well; 2) the features are derived from various linguistic analyses and are error-prone; and 3) some features may be expensive and require domain expert. In this paper, we develop a Chinese event extraction system that uses word embedding vectors to represent language, and deep neural networks to learn the abstract feature representation in order to greatly reduce the effort of feature engineering. Read More

A butterfly-based direct combined-field integral equation (CFIE) solver for analyzing scattering from electrically large, perfect electrically conducting objects is presented. The proposed solver leverages the butterfly scheme to compress blocks of the hierarchical LU-factorized discretized CFIE operator and uses randomized butterfly reconstruction schemes to expedite the factorization. The memory requirements and computational cost of the direct butterfly-CFIE solver scale as $O(N\mathrm{log}^2N)$ and $O(N^{1. Read More

The structure of social networks is a key determinant in fostering cooperation and other altruistic behavior among naturally selfish individuals. However, most real social interactions are temporal, being both finite in duration and spread out over time. This raises the question of whether stable cooperation can form despite an intrinsically fragmented social fabric. Read More

Single feature is inefficient to describe content of an image, which is a shortcoming in traditional image retrieval task. We know that one image can be described by different features. Multi-feature fusion ranking can be utilized to improve the ranking list of query. Read More

Neural machine translation (NMT) heavily relies on word-level modelling to learn semantic representations of input sentences. However, for languages without natural word delimiters (e.g. Read More

We have demonstrated that a supersonic beam of methyl radicals (CH$_3$) in the ground rotational state of both $para$ and $ortho$ species has been slowed down to standstill with a magnetic molecular decelerator, and successfully captured spatially in an anti-Helmholtz magnetic trap for $>$ 1 s. The trapped CH$_3$ radicals have a mean translational temperature of about 200 mK with an estimated density of $>5.0\times10^7$ cm$^{-3}$. Read More

Incompatibility of image descriptor and ranking is always neglected in image retrieval. In this paper, manifold learning and Gestalt psychology theory are involved to solve the incompatibility problem. A new holistic descriptor called Perceptual Uniform Descriptor (PUD) based on Gestalt psychology is proposed, which combines color and gradient direction to imitate the human visual uniformity. Read More

Recognizing implicit discourse relations is a challenging but important task in the field of Natural Language Processing. For such a complex text processing task, different from previous studies, we argue that it is necessary to repeatedly read the arguments and dynamically exploit the efficient features useful for recognizing discourse relations. To mimic the repeated reading strategy, we propose the neural networks with multi-level attention (NNMA), combining the attention mechanism and external memories to gradually fix the attention on some specific words helpful to judging the discourse relations. Read More

Advances in sensor networks enable pervasive health monitoring and patient-specific treatments that take into account the patients medical history, current state, genetic background, and personal habits. However, sensors are often battery power limited and vastly differ in their application related requirements. In this paper, we address both of these problems. Read More

Air pollution is a major risk factor for global health, with both ambient and household air pollution contributing substantial components of the overall global disease burden. One of the key drivers of adverse health effects is fine particulate matter ambient pollution (PM$_{2.5}$) to which an estimated 3 million deaths can be attributed annually. Read More

An articulation point in a network is a node whose removal disconnects the network. Those nodes play key roles in ensuring connectivity of many real-world networks, from infrastructure networks to protein interaction networks and terrorist communication networks. Despite their fundamental importance, a general framework of studying articulation points in complex networks is lacking. Read More

This paper studies the local existence of strong solutions to the Cauchy problem of the 2D fluid-particle interaction model with vacuum as far field density. Notice that the technique used by Ding et al.\cite{SBH} for the corresponding 3D local well-posedness of strong solutions fails treating the 2D case, because the $L^p$-norm ($p>2$) of the velocity $u$ cannot be controlled in terms only of $\sqrt{\rho}u$ and $\nabla u$ here. Read More

The quest of an exact and nonperturbative treatment of quantum dissipation in non-Gaussian coupling environments remains in general an untractable task. In this work we address the key issues on the solutions to a class of non-Gaussian coupling environments. As an illustration we consider explicitly a harmonic bath coupled quadratically with an arbitrary system, at finite temperature, and construct a novel dissipaton-equation-of-motion (DEOM) formalism. Read More

In neural machine translation (NMT), generation of a target word depends on both source and target contexts. We find that source contexts have a direct impact on the adequacy of a translation while target contexts affect the fluency. Intuitively, generation of a content word should rely more on the source context and generation of a functional word should rely more on the target context. Read More

Reordering poses a major challenge in machine translation (MT) between two languages with significant differences in word order. In this paper, we present a novel reordering approach utilizing sparse features based on dependency word pairs. Each instance of these features captures whether two words, which are related by a dependency link in the source sentence dependency parse tree, follow the same order or are swapped in the translation output. Read More

A butterfly-based fast direct integral equation solver for analyzing high-frequency scattering from two-dimensional objects is presented. The solver leverages a randomized butterfly scheme to compress blocks corresponding to near- and far-field interactions in the discretized forward and inverse electric field integral operators. The observed memory requirements and computational cost of the proposed solver scale as O(Nlog^2N) and O(N^1. Read More

This work reveals a counter-intuitive but basic process of ionic screening in nano-fluidic channels. Steady-state numerical simulations and mathematical analysis show that, under significant longitudinal ionic transport, the screening ionic charges can be locally inverted in the channels: their charge sign becomes the same as that of the channel surface charges. The process is identified to originate from the coupling of ionic electro-diffusion transport and junction 2-D electrostatics. Read More

Despite the traditional focus of network science on static networks, most networked systems of scientific interest are characterized by temporal links. By disrupting the paths, link temporality has been shown to frustrate many dynamical processes on networks, from information spreading to accessibility. Considering the ubiquity of temporal networks in nature, we must ask: Are there any advantages of the networks' temporality? Here we develop an analytical framework to explore the control properties of temporal networks, arriving at the counterintuitive conclusion that temporal networks, compared to their static (i. Read More

Existing techniques for motion imitation often suffer a certain level of latency due to their computational overhead or a large set of correspondence samples to search. To achieve real-time imitation with small latency, we present a framework in this paper to reconstruct motion on humanoids based on sparsely sampled correspondence. The imitation problem is formulated as finding the projection of a point from the configuration space of a human's poses into the configuration space of a humanoid. Read More

The period polynomial $r_f(z)$ for a weight $k \geq 3$ newform $f \in S_k(\Gamma_0(N),\chi)$ is the generating function for special values of $L(s,f)$. The functional equation for $L(s, f)$ induces a functional equation on $r_f(z)$. Jin, Ma, Ono, and Soundararajan proved that for all newforms $f$ of even weight $k \ge 4$ and trivial nebetypus, the "Riemann Hypothesis" holds for $r_f(z)$: that is, all roots of $r_f(z)$ lie on the circle of symmetry $|z| =1/\sqrt{N}$. Read More