arXiv subjects

Yi Zhang

Publications and source records attributed to Yi Zhang.

At least 847 records · Page 47Linked to original sources

arXiv2022

DFEE: Interactive DataFlow Execution and Evaluation Kit

DataFlow has been emerging as a new paradigm for building task-oriented chatbots due to its expressive semantic representations of the dialogue tasks. Despite the availability of a large dataset SMCalFlow and a simplified syntax, the development and evaluation of DataFlow-based chatbots remain challenging due to the system complexity and the lack of downstream toolchains. In this demonstration, we present DFEE, an interactive DataFlow Execution and Evaluation toolkit that supports execution, visualization and benchmarking of semantic parsers given dialogue input and backend database. We demonstrate the system via a complex dialog task: event scheduling that involves temporal reasoning. It also supports diagnosing the parsing results via a friendly interface that allows developers to examine dynamic DataFlow and the corresponding execution results. To illustrate how to benchmark SoTA models, we propose a novel benchmark that covers more sophisticated event scheduling scenarios and a new metric on task success evaluation. The codes of DFEE have been released on https://github.com/amazonscience/dataflow-evaluation-toolkit.

cs.CL↗

arXiv2022

Prototype matching: children's preference for forming scientific concepts

Inspired by a sample lesson, this paper studies and discusses children's preferences in learning scientific concepts. In a "Dissolution" lesson, one of the students took the demonstration experiment of "carmine dissolves in Water" demonstrated by the teacher as the prototype to judge whether a new phenomenon belongs to dissolution, instead of analyzing and judging the phenomenon by using the dissolution definition. Therefore, we propose a conjecture that "prototype matching" may be a more preferred way for children to learn concepts than thinking through inquiry experiment, analysis, deduction, etc. To this end, we conducted a targeted test on 160 fifth grade students (all of whom had learned this lesson) from a primary school in Beijing, and used goodness of fit test to statistically analyze the results. The results showed that: 1. the Chi square of the general result is 73.865, P<0.001, indicating that children did have obvious prototype preference; 2. We "tampered" some of the prototypes, that is, they looked like the prototypes that the teacher had told students, but they were actually wrong. However, the results showed that children still preferred these so-called "prototypes" (chi square is 21.823, P<0.001). Conclusion: 1. Children have an obvious preference for "prototype matching" in scientific concept learning, which is not only obviously deviated from the current general understanding of science education that emphasizes discovery/inquiry construction, but also points out that there may be a priority relationship among various ways of concept organization (such as definition theory, prototype theory, schema theory, etc.). 2. Children's preference for prototypes seems to be unthinking, and they will not identify the authenticity of prototypes, which is particularly noteworthy in front-line teaching.

q-bio.NC↗

arXiv2022

The relationship between the interdisciplinary activation of children's scientific concepts and their mastery of basic knowledges: a pre study based on reaction times

The activation of scientific concepts (such as association) is not only an important way for children to organize scientific knowledges, but also an important way for them to learn complex concepts (such as compound concepts composed of multiple knowledge points). Inspired by the details of a primary electrical lesson, we used the E-Prime software to study the activation of concepts inside and outside the electrical unit by students with different electrical knowledge levels (taking reaction time as the main index). The results showed that: 1. the levels of basic knowledge was negatively correlated with the cross domain activation ability of concepts, that is, the worse the basic knowledge, the faster the cross domain activation speed (P<0.05); 2. The better the basic knowledges, the closer the activation behavior is to science teachers. Conclusion: 1. the poorer the basic knowledges, the stronger the cross domain association ability and the more active the thinking; 2. The reason for this phenomenon may be human's thinking is patterned; 3. Therefore, there is a potential logical contradiction in the view that divergent thinking is the psychological basis of creativity.

physics.ed-ph↗

arXiv2022

Adaptive Safety Evaluation for Connected and Automated Vehicles with Sparse Control Variates

Safety performance evaluation is critical for developing and deploying connected and automated vehicles (CAVs). One prevailing way is to design testing scenarios using prior knowledge of CAVs, test CAVs in these scenarios, and then evaluate their safety performances. However, significant differences between CAVs and prior knowledge could severely reduce the evaluation efficiency. Towards addressing this issue, most existing studies focus on the adaptive design of testing scenarios during the CAV testing process, but so far they cannot be applied to high-dimensional scenarios. In this paper, we focus on the adaptive safety performance evaluation by leveraging the testing results, after the CAV testing process. It can significantly improve the evaluation efficiency and be applied to high-dimensional scenarios. Specifically, instead of directly evaluating the unknown quantity (e.g., crash rates) of CAV safety performances, we evaluate the differences between the unknown quantity and known quantity (i.e., control variates). By leveraging the testing results, the control variates could be well designed and optimized such that the differences are close to zero, so the evaluation variance could be dramatically reduced for different CAVs. To handle the high-dimensional scenarios, we propose the sparse control variates method, where the control variates are designed only for the sparse and critical variables of scenarios. According to the number of critical variables in each scenario, the control variates are stratified into strata and optimized within each stratum using multiple linear regression techniques. We justify the proposed method's effectiveness by rigorous theoretical analysis and empirical study of high-dimensional overtaking scenarios.

eess.SY↗

arXiv2022

A Guideline for Silicon Carbide MOSFET Thermal Characterization based on Source-Drain Voltage

Thermal transient measurement based on source-drain voltage is a standard method to characterize thermal properties of silicon semiconductors but is doubtful to be directly applied to silicon carbide (SiC) devices. To evaluate its feasibility and limitations, this paper conducts a comprehensive investigation into its accuracy, resolution, and stability towards yielding the structure information of SiC MOSFET using the source-drain voltage as the temperature sensitive electrical parameter. The whole characterization process involves two main procedures and associated key testing parameters, such as gate voltages, sensing and heating currents, etc. Their impacts on both the static and dynamic performances are also investigated with the aim of providing a guideline for conducting a reproducible thermal transient measurement for SiC MOSFETs.

physics.app-ph↗

arXiv2022

Dialogue Meaning Representation for Task-Oriented Dialogue Systems

Dialogue meaning representation formulates natural language utterance semantics in their conversational context in an explicit and machine-readable form. Previous work typically follows the intent-slot framework, which is easy for annotation yet limited in scalability for complex linguistic expressions. A line of works alleviates the representation issue by introducing hierarchical structures but challenging to express complex compositional semantics, such as negation and coreference. We propose Dialogue Meaning Representation (DMR), a pliable and easily extendable representation for task-oriented dialogue. Our representation contains a set of nodes and edges to represent rich compositional semantics. Moreover, we propose an inheritance hierarchy mechanism focusing on domain extensibility. Additionally, we annotated DMR-FastFood, a multi-turn dialogue dataset with more than 70k utterances, with DMR. We propose two evaluation tasks to evaluate different dialogue models and a novel coreference resolution model GNNCoref for the graph-based coreference resolution task. Experiments show that DMR can be parsed well with pre-trained Seq2Seq models, and GNNCoref outperforms the baseline models by a large margin.

cs.CL↗

arXiv2022

Zero-shot Image Captioning by Anchor-augmented Vision-Language Space Alignment

CLIP (Contrastive Language-Image Pre-Training) has shown remarkable zero-shot transfer capabilities in cross-modal correlation tasks such as visual classification and image retrieval. However, its performance in cross-modal generation tasks like zero-shot image captioning remains unsatisfied. In this work, we discuss that directly employing CLIP for zero-shot image captioning relies more on the textual modality in context and largely ignores the visual information, which we call \emph{contextual language prior}. To address this, we propose Cross-modal Language Models (CLMs) to facilitate unsupervised cross-modal learning. We further propose Anchor Augment to guide the generative model's attention to the fine-grained information in the representation of CLIP. Experiments on MS COCO and Flickr 30K validate the promising performance of proposed approach in both captioning quality and computational efficiency.

cs.CV↗

arXiv2022

Adversarial Attacks and Defenses in Physiological Computing: A Systematic Review

Physiological computing uses human physiological data as system inputs in real time. It includes, or significantly overlaps with, brain-computer interfaces, affective computing, adaptive automation, health informatics, and physiological signal based biometrics. Physiological computing increases the communication bandwidth from the user to the computer, but is also subject to various types of adversarial attacks, in which the attacker deliberately manipulates the training and/or test examples to hijack the machine learning algorithm output, leading to possible user confusion, frustration, injury, or even death. However, the vulnerability of physiological computing systems has not been paid enough attention to, and there does not exist a comprehensive review on adversarial attacks to them. This paper fills this gap, by providing a systematic review on the main research areas of physiological computing, different types of adversarial attacks and their applications to physiological computing, and the corresponding defense strategies. We hope this review will attract more research interests on the vulnerability of physiological computing systems, and more importantly, defense strategies to make them more secure.

cs.LG↗

arXiv2022

Fair Visual Recognition via Intervention with Proxy Features

Deep learning models often learn to make predictions that rely on sensitive social attributes like gender and race, which poses significant fairness risks, especially in societal applications, e.g., hiring, banking, and criminal justice. Existing work tackles this issue by minimizing information about social attributes in models for debiasing. However, the high correlation between target task and social attributes makes bias mitigation incompatible with target task accuracy. Recalling that model bias arises because the learning of features in regard to bias attributes (i.e., bias features) helps target task optimization, we explore the following research question: \emph{Can we leverage proxy features to replace the role of bias feature in target task optimization for debiasing?} To this end, we propose \emph{Proxy Debiasing}, to first transfer the target task's learning of bias information from bias features to artificial proxy features, and then employ causal intervention to eliminate proxy features in inference. The key idea of \emph{Proxy Debiasing} is to design controllable proxy features to on one hand replace bias features in contributing to target task during the training stage, and on the other hand easily to be removed by intervention during the inference stage. This guarantees the elimination of bias features without affecting the target information, thus addressing the fairness-accuracy paradox in previous debiasing solutions. We apply \emph{Proxy Debiasing} to several benchmark datasets, and achieve significant improvements over the state-of-the-art debiasing methods in both of accuracy and fairness.

cs.LG↗

arXiv2022

Reinforcement Learning-based Joint User Scheduling and Link Configuration in Millimeter-wave Networks

In this paper, we develop algorithms for joint user scheduling and three types of mmWave link configuration: relay selection, codebook optimization, and beam tracking in millimeter wave (mmWave) networks. Our goal is to design an online controller that dynamically schedules users and configures their links to minimize the system delay. To solve this complex scheduling problem, we model it as a dynamic decision-making process and develop two reinforcement learning-based solutions. The first solution is based on deep reinforcement learning (DRL), which leverages the proximal policy optimization to train a neural network-based solution. Due to the potential high sample complexity of DRL, we also propose an empirical multi-armed bandit (MAB)-based solution, which decomposes the decision-making process into a sequential of sub-actions and exploits classic maxweight scheduling and Thompson sampling to decide those sub-actions. Our evaluation of the proposed solutions confirms their effectiveness in providing acceptable system delay. It also shows that the DRL-based solution has better delay performance while the MAB-based solution has a faster training process.

cs.NI↗

arXiv2022

What Makes Convolutional Models Great on Long Sequence Modeling?

Convolutional models have been widely used in multiple domains. However, most existing models only use local convolution, making the model unable to handle long-range dependency efficiently. Attention overcomes this problem by aggregating global information but also makes the computational complexity quadratic to the sequence length. Recently, Gu et al. [2021] proposed a model called S4 inspired by the state space model. S4 can be efficiently implemented as a global convolutional model whose kernel size equals the input sequence length. S4 can model much longer sequences than Transformers and achieve significant gains over SoTA on several long-range tasks. Despite its empirical success, S4 is involved. It requires sophisticated parameterization and initialization schemes. As a result, S4 is less intuitive and hard to use. Here we aim to demystify S4 and extract basic principles that contribute to the success of S4 as a global convolutional model. We focus on the structure of the convolution kernel and identify two critical but intuitive principles enjoyed by S4 that are sufficient to make up an effective global convolutional model: 1) The parameterization of the convolutional kernel needs to be efficient in the sense that the number of parameters should scale sub-linearly with sequence length. 2) The kernel needs to satisfy a decaying structure that the weights for convolving with closer neighbors are larger than the more distant ones. Based on the two principles, we propose a simple yet effective convolutional model called Structured Global Convolution (SGConv). SGConv exhibits strong empirical performance over several tasks: 1) With faster speed, SGConv surpasses S4 on Long Range Arena and Speech Command datasets. 2) When plugging SGConv into standard language and vision models, it shows the potential to improve both efficiency and performance.

cs.LG↗

arXiv2022

Engineered second-order nonlinearity in silicon nitride

The lack of a bulk second-order nonlinearity (\c{hi}(2)) in silicon nitride (Si3N4) keeps this low-loss, CMOS-compatible platform from key active functions such as Pockels electro-optic (EO) modulation and efficient second harmonic generation (SHG). We demonstrate a successful induction of \c{hi}(2) in Si3N4 through electrical poling with an externally-applied field to align the Si-N bonds. This alignment breaks the centrosymmetry of Si3N4, and enables the bulk \c{hi}(2). The sample is heated to over 500°C to facilitate the poling. The comparison between the EO responses of poled and non-poled Si3N4, measured using a Si3N4 micro-ring modulator, shows at least a 25X enhancement in the r33 EO component. The maximum \c{hi}(2) we obtain through poling is 0.24pm/V. We observe a remarkable improvement in the speed of the measured EO responses from 3GHz to 15GHz (3dB bandwidth) after the poling, which confirms the \c{hi}(2) nature of the EO response induced by poling. This work paves the way for high-speed active functions on the Si3N4 platform.

physics.optics↗

arXiv2022

DouFu: A Double Fusion Joint Learning Method For Driving Trajectory Representation

Driving trajectory representation learning is of great significance for various location-based services, such as driving pattern mining and route recommendation. However, previous representation generation approaches tend to rarely address three challenges: 1) how to represent the intricate semantic intentions of mobility inexpensively; 2) complex and weak spatial-temporal dependencies due to the sparsity and heterogeneity of the trajectory data; 3) route selection preferences and their correlation to driving behavior. In this paper, we propose a novel multimodal fusion model, DouFu, for trajectory representation joint learning, which applies multimodal learning and attention fusion module to capture the internal characteristics of trajectories. We first design movement, route, and global features generated from the trajectory data and urban functional zones and then analyze them respectively with the attention encoder or feed forward network. The attention fusion module incorporates route features with movement features to create a better spatial-temporal embedding. With the global semantic feature, DouFu produces a comprehensive embedding for each trajectory. We evaluate representations generated by our method and other baseline models on classification and clustering tasks. Empirical results show that DouFu outperforms other models in most of the learning algorithms like the linear regression and the support vector machine by more than 10%.

cs.LG↗

arXiv2022

Measuring and Reducing Model Update Regression in Structured Prediction for NLP

Recent advance in deep learning has led to the rapid adoption of machine learning-based NLP models in a wide range of applications. Despite the continuous gain in accuracy, backward compatibility is also an important aspect for industrial applications, yet it received little research attention. Backward compatibility requires that the new model does not regress on cases that were correctly handled by its predecessor. This work studies model update regression in structured prediction tasks. We choose syntactic dependency parsing and conversational semantic parsing as representative examples of structured prediction tasks in NLP. First, we measure and analyze model update regression in different model update settings. Next, we explore and benchmark existing techniques for reducing model update regression including model ensemble and knowledge distillation. We further propose a simple and effective method, Backward-Congruent Re-ranking (BCR), by taking into account the characteristics of structured prediction. Experiments show that BCR can better mitigate model update regression than model ensemble and knowledge distillation approaches.

cs.CL↗

arXiv2022

General theory of Josephson Diodes

Motivated by recent progress in the superconductivity nonreciprocal phenomena, we study the general theory of Josephson diodes. The central ingredient for Josephson diodes is the asymmetric proximity process inside the tunneling barrier. From the symmetry breaking point of view, there are two types of Josephson diodes, inversion breaking and time-reversal breaking. For the inversion breaking case, applying voltage bias could effectively tune the proximity process like the voltage-dependent Rashba coupling or electric polarization giving rise to $I_c(V)\neq I_c(-V)$ and $I_{r+}\neq I_{r-}$. For the time-reversal breaking case, the current flow could adjust the internal time-reversal breaking field like magnetism or time-reversal breaking electron-electron pairing, which leads to $I_{c+}\neq I_{c-}$. All these results provide a complete understanding and the general principles of realizing Josephson diodes, especially the recently found NbSe$_2$/Nb$_3$Br$_8$/NbSe$_2$ Josephson diodes.

cond-mat.supr-con↗

arXiv2022

Dense-TNT: Efficient Vehicle Type Classification Neural Network Using Satellite Imagery

Accurate vehicle type classification serves a significant role in the intelligent transportation system. It is critical for ruler to understand the road conditions and usually contributive for the traffic light control system to response correspondingly to alleviate traffic congestion. New technologies and comprehensive data sources, such as aerial photos and remote sensing data, provide richer and high-dimensional information. Also, due to the rapid development of deep neural network technology, image based vehicle classification methods can better extract underlying objective features when processing data. Recently, several deep learning models have been proposed to solve the problem. However, traditional pure convolutional based approaches have constraints on global information extraction, and the complex environment, such as bad weather, seriously limits the recognition capability. To improve the vehicle type classification capability under complex environment, this study proposes a novel Densely Connected Convolutional Transformer in Transformer Neural Network (Dense-TNT) framework for the vehicle type classification by stacking Densely Connected Convolutional Network (DenseNet) and Transformer in Transformer (TNT) layers. Three-region vehicle data and four different weather conditions are deployed for recognition capability evaluation. Experimental findings validate the recognition ability of our proposed vehicle classification model with little decay, even under the heavy foggy weather condition.

cs.CV↗

arXiv2022

Hyperspherical approach to atom--dimer collision with the Jacobi boundary condition

In this study, we investigate atom--dimer scattering within the framework of the hyperspherical method. The coupled channel Schrödinger equation is solved using the R-matrix propagation technique combined with the smooth variable discretization method. In the matching procedure, the asymptotic wave functions are expressed in the rotated Jacobi coordinates. We apply this approach to the elastic scattering $^{3}$He(T$\uparrow$) + $^{4}$He$_{2}$ and H$\uparrow$ + H$\uparrow$Li processes. The convergence of the scattering length as a function of the propagation distance is studied. We find that the method is reliable and can provide considerable savings over previous propagators.

physics.atom-ph↗

arXiv2022

Prospective Study on Observations of γ-Ray Sources in the Galaxy Using the HADAR Experiment

The High Altitude Detection of Astronomical Radiation (HADAR) experiment is a refracting terrestrial telescope array based on the atmospheric Cherenkov imaging technique. It focuses the Cherenkov light emitted by extensive air showers through a large aperture water-lens system for observing very-high-energy-rays and cosmic rays. With the advantages of a large field-of-view (FOV) and low energy threshold, the HADAR experiment operates in a large-scale sky scanning mode to observe galactic sources. This study presents the prospects of using the HADAR experiment for the sky survey of TeV γ-ray sources from TeVCat and provids a one-year survey of statistical significance. Results from the simulation show that a total of 23 galactic point sources, including five supernova remnant sources and superbubbles, four pulsar wind nebula sources, and 14 unidentified sources, were detected in the HADAR FOV with a significance greater than 5 standard deviations (σ). The statistical significance for the Crab Nebula during one year of operation reached 346.0 σ and the one-year integral sensitivity of HADAR above 1TeV was ~1.3%-2.4% of the flux from the Crab Nebula.

astro-ph.HE↗