Searcharxiv⌕ Search

arXiv subjects

Ying Xu

Publications and source records attributed to Ying Xu.

At least 73 records · Page 4Linked to original sources
arXiv2022

GEMv2: Multilingual NLG Benchmarking in a Single Line of Code

Evaluation in machine learning is usually informed by past choices, for example which datasets or metrics to use. This standardization enables the comparison on equal footing using leaderboards, but the evaluation choices become sub-optimal as better alternatives arise. This problem is especially pertinent in natural language generation which requires ever-improving suites of datasets, metrics, and human evaluation to make definitive claims. To make following best model evaluation practices easier, we introduce GEMv2. The new version of the Generation, Evaluation, and Metrics Benchmark introduces a modular infrastructure for dataset, model, and metric developers to benefit from each others work. GEMv2 supports 40 documented datasets in 51 languages. Models for all datasets can be evaluated online and our interactive data card creation and rendering tools make it easier to add new datasets to the living benchmark.

cs.CL↗
arXiv2022

An optimised deep spiking neural network architecture without gradients

We present an end-to-end trainable modular event-driven neural architecture that uses local synaptic and threshold adaptation rules to perform transformations between arbitrary spatio-temporal spike patterns. The architecture represents a highly abstracted model of existing Spiking Neural Network (SNN) architectures. The proposed Optimized Deep Event-driven Spiking neural network Architecture (ODESA) can simultaneously learn hierarchical spatio-temporal features at multiple arbitrary time scales. ODESA performs online learning without the use of error back-propagation or the calculation of gradients. Through the use of simple local adaptive selection thresholds at each node, the network rapidly learns to appropriately allocate its neuronal resources at each layer for any given problem without using a real-valued error measure. These adaptive selection thresholds are the central feature of ODESA, ensuring network stability and remarkable robustness to noise as well as to the selection of initial system parameters. Network activations are inherently sparse due to a hard Winner-Take-All (WTA) constraint at each layer. We evaluate the architecture on existing spatio-temporal datasets, including the spike-encoded IRIS and TIDIGITS datasets, as well as a novel set of tasks based on International Morse Code that we created. These tests demonstrate the hierarchical spatio-temporal learning capabilities of ODESA. Through these tests, we demonstrate ODESA can optimally solve practical and highly challenging hierarchical spatio-temporal learning tasks with the minimum possible number of computing nodes.

cs.NE↗
arXiv2022

Big Tech Companies Impact on Research at the Faculty of Information Technology and Electrical Engineering

Artificial intelligence is gaining momentum, ongoing pandemic is fuel to that with more opportunities in every sector specially in health and education sector. But with the growth in technology, challenges associated with ethics also grow (Katharine Schwab, 2021). Whenever a new AI product is developed, companies publicize that their systems are transparent, fair, and are in accordance with the existing laws and regulations as the methods and procedures followed by a big tech company for ensuring AI ethics, not only affect the trust and perception of public, but it also challenges the capabilities of the companies towards business strategies in different regions, and the kind of brains it can attract for their projects. AI Big Tech companies have influence over AI ethics as many influencing ethical-AI researchers have roots in Big Tech or its associated labs.

cs.CY↗
arXiv2022

It is AI's Turn to Ask Humans a Question: Question-Answer Pair Generation for Children's Story Books

Existing question answering (QA) techniques are created mainly to answer questions asked by humans. But in educational applications, teachers often need to decide what questions they should ask, in order to help students to improve their narrative understanding capabilities. We design an automated question-answer generation (QAG) system for this education scenario: given a story book at the kindergarten to eighth-grade level as input, our system can automatically generate QA pairs that are capable of testing a variety of dimensions of a student's comprehension skills. Our proposed QAG model architecture is demonstrated using a new expert-annotated FairytaleQA dataset, which has 278 child-friendly storybooks with 10,580 QA pairs. Automatic and human evaluations show that our model outperforms state-of-the-art QAG baseline systems. On top of our QAG system, we also start to build an interactive story-telling application for the future real-world deployment in this educational scenario.

cs.CL↗
arXiv2022

Fantastic Questions and Where to Find Them: FairytaleQA -- An Authentic Dataset for Narrative Comprehension

Question answering (QA) is a fundamental means to facilitate assessment and training of narrative comprehension skills for both machines and young children, yet there is scarcity of high-quality QA datasets carefully designed to serve this purpose. In particular, existing datasets rarely distinguish fine-grained reading skills, such as the understanding of varying narrative elements. Drawing on the reading education research, we introduce FairytaleQA, a dataset focusing on narrative comprehension of kindergarten to eighth-grade students. Generated by educational experts based on an evidence-based theoretical framework, FairytaleQA consists of 10,580 explicit and implicit questions derived from 278 children-friendly stories, covering seven types of narrative elements or relations. Our dataset is valuable in two folds: First, we ran existing QA models on our dataset and confirmed that this annotation helps assess models' fine-grained learning skills. Second, the dataset supports question generation (QG) task in the education domain. Through benchmarking with QG models, we show that the QG model trained on FairytaleQA is capable of asking high-quality and more diverse questions.

cs.CL↗
arXiv2022

Novel Materials and Concepts for Next-Generation High Power Target Applications

Novel beam-intercepting materials and targetry concepts are essential to improve the performance, reliability and operation lifetimes of next generation multi-megawatt (multi-MW) accelerator target facilities. The beam-intercepting materials and components must sustain an order-of-magnitude increase in particle beam intensities and are beyond the current state-of-the-art. With conventional materials already limiting the scope of experiments, it is crucial to investigate novel target materials, technologies and concepts that will satisfy the requirements and maximize the physics benefits of future energy and intensity frontier experiments. This paper provides an overview of the related targetry R&D required over the next 10 years to support and enable future high-power accelerator target facilities.

physics.acc-ph↗
arXiv2022

Measurement of DC Magneto-Optical Kerr Effect with Sensitivity of $10^{-7} \text{Rad}/\sqrt{\text{Hz}}$

A high-sensitive DC Magneto-Optical Kerr Effect (MOKE) apparatus is described in this letter. Via detailed analysis on several dominating noise sources, we have proposed solutions that significantly lower the MOKE noise, and a sensitivity of $1.5\times10^{-7} \text{rad}/\sqrt{\text{Hz}}$ is achieved with long-term stability. The sensitivity of the apparatus is tested by measuring a wedge-shaped Ni thin film on $\text{SiO}_2$ with Ni thickness varying from 0 to 3 nm. A noise floor of $1.5\times10^{-8}$ rad is demonstrated. The possibility of further improving sensitivity to $10^{-9}$ rad via applying ac modulation is also discussed.

physics.ins-det↗
arXiv2022

StoryBuddy: A Human-AI Collaborative Chatbot for Parent-Child Interactive Storytelling with Flexible Parental Involvement

Despite its benefits for children's skill development and parent-child bonding, many parents do not often engage in interactive storytelling by having story-related dialogues with their child due to limited availability or challenges in coming up with appropriate questions. While recent advances made AI generation of questions from stories possible, the fully-automated approach excludes parent involvement, disregards educational goals, and underoptimizes for child engagement. Informed by need-finding interviews and participatory design (PD) results, we developed StoryBuddy, an AI-enabled system for parents to create interactive storytelling experiences. StoryBuddy's design highlighted the need for accommodating dynamic user needs between the desire for parent involvement and parent-child bonding and the goal of minimizing parent intervention when busy. The PD revealed varied assessment and educational goals of parents, which StoryBuddy addressed by supporting configuring question types and tracking child progress. A user study validated StoryBuddy's usability and suggested design insights for future parent-AI collaboration systems.

cs.HC↗
arXiv2022

The Role of Permanent and Induced Electrostatic Dipole Moments for Schottky Barriers in Janus MXY/Graphene Heterostructures: a First Principles Study

The Schottky barrier height ($E_{SBH}$) is a crucial factor in determining the transport properties of semiconductor materials as it directly regulates the carrier mobility in opto-electronics devices. In principle, van der Waals (vdW) Janus heterostructures offer an appealing avenue to controlling the ESBH. However, the underlying atomistic mechanisms are far from understood conclusively, which prompts for further research in the topic. To this end, here, we carry out an extensive first principles study of the electronic properties and $E_{SBH}$ of several vdW Janus MXY/Graphene (M=Mo, W; X, Y=S, Se, Te) heterostructures. The results of the simulations show that by changing the composition and geometry of the heterostructure's interface, it is possible to control its electrical contact, thence electron transport properties, from Ohmic to Schottky with nearly one order of magnitude variations in the $E_{SBH}$. Detailed analysis of the simulations enables rationalization of this highly attractive property on the basis of the interplay between the permanent dipole moment of the Janus MXY sheet and the induced one due to interfacial charge redistribution at the MXY/Gr interface. Such an interplay is shown to be highly effective in altering the electrostatic potential difference across the vdW Janus heterostructure, determining its ESBH, thence Schottky (Ohmic) contact type. These computational findings contribute guidelines to control electrical contacts in Janus heterostructures towards rational design of electrical contacts in nanoscale devices.

cond-mat.mes-hall↗
arXiv2021

UIBert: Learning Generic Multimodal Representations for UI Understanding

To improve the accessibility of smart devices and to simplify their usage, building models which understand user interfaces (UIs) and assist users to complete their tasks is critical. However, unique challenges are proposed by UI-specific characteristics, such as how to effectively leverage multimodal UI features that involve image, text, and structural metadata and how to achieve good performance when high-quality labeled data is unavailable. To address such challenges we introduce UIBert, a transformer-based joint image-text model trained through novel pre-training tasks on large-scale unlabeled UI data to learn generic feature representations for a UI and its components. Our key intuition is that the heterogeneous features in a UI are self-aligned, i.e., the image and text features of UI components, are predictive of each other. We propose five pretraining tasks utilizing this self-alignment among different features of a UI component and across various components in the same UI. We evaluate our method on nine real-world downstream UI tasks where UIBert outperforms strong multimodal baselines by up to 9.26% accuracy.

cs.CV↗
arXiv2021

Multimodal Icon Annotation For Mobile Applications

Annotating user interfaces (UIs) that involves localization and classification of meaningful UI elements on a screen is a critical step for many mobile applications such as screen readers and voice control of devices. Annotating object icons, such as menu, search, and arrow backward, is especially challenging due to the lack of explicit labels on screens, their similarity to pictures, and their diverse shapes. Existing studies either use view hierarchy or pixel based methods to tackle the task. Pixel based approaches are more popular as view hierarchy features on mobile platforms are often incomplete or inaccurate, however it leaves out instructional information in the view hierarchy such as resource-ids or content descriptions. We propose a novel deep learning based multi-modal approach that combines the benefits of both pixel and view hierarchy features as well as leverages the state-of-the-art object detection techniques. In order to demonstrate the utility provided, we create a high quality UI dataset by manually annotating the most commonly used 29 icons in Rico, a large scale mobile design dataset consisting of 72k UI screenshots. The experimental results indicate the effectiveness of our multi-modal approach. Our model not only outperforms a widely used object classification baseline but also pixel based object detection models. Our study sheds light on how to combine view hierarchy with pixel features for annotating UI elements.

cs.CV↗
arXiv2021

Grey-box Adversarial Attack And Defence For Sentiment Classification

We introduce a grey-box adversarial attack and defence framework for sentiment classification. We address the issues of differentiability, label preservation and input reconstruction for adversarial attack and defence in one unified framework. Our results show that once trained, the attacking model is capable of generating high-quality adversarial examples substantially faster (one order of magnitude less in time) than state-of-the-art attacking methods. These examples also preserve the original sentiment according to human evaluation. Additionally, our framework produces an improved classifier that is robust in defending against multiple adversarial attacking methods. Code is available at: https://github.com/ibm-aur-nlp/adv-def-text-dist.

cs.LG↗
arXiv2021

Estimating the Number of Infected Cases in COVID-19 Pandemic

The COVID-19 pandemic has caused major disturbance to human life. An important reason behind the widespread social anxiety is the huge uncertainty about the pandemic. A fundamental uncertainty is how many or what percentage of people have been infected. There are published and frequently updated data on various statistics of the pandemic, at local, country or global level. However, due to various reasons, many cases were not included in those reported numbers. We propose a structured approach for the estimation of the number of unreported cases, where we distinguish cases that arrive late in the reported numbers and those who had mild or no symptoms and thus were not captured by any medical system at all. We use post-report data for the estimation of the former and population matching to the latter. We estimate that the reported number of infected cases in the US should be corrected by multiplying a factor of 220.54% as of Apr 20, 2020, while the infection ratio out of the US population is estimated to be 0.53%, implying a case mortality rate at 2.85% which is close to the 3.4% suggested by the WHO in Mar 2020. Towards the end of the summer of 2020, the overall infection ratio of the US rises to 2.49% while the case mortality decreases to 2.09%, and the ratio of asymptomatic cases out of all infected cases reduces from the pre-summer 35-40% to around 20-25%.

q-bio.PE↗
arXiv2021

ActionBert: Leveraging User Actions for Semantic Understanding of User Interfaces

As mobile devices are becoming ubiquitous, regularly interacting with a variety of user interfaces (UIs) is a common aspect of daily life for many people. To improve the accessibility of these devices and to enable their usage in a variety of settings, building models that can assist users and accomplish tasks through the UI is vitally important. However, there are several challenges to achieve this. First, UI components of similar appearance can have different functionalities, making understanding their function more important than just analyzing their appearance. Second, domain-specific features like Document Object Model (DOM) in web pages and View Hierarchy (VH) in mobile applications provide important signals about the semantics of UI elements, but these features are not in a natural language format. Third, owing to a large diversity in UIs and absence of standard DOM or VH representations, building a UI understanding model with high coverage requires large amounts of training data. Inspired by the success of pre-training based approaches in NLP for tackling a variety of problems in a data-efficient way, we introduce a new pre-trained UI representation model called ActionBert. Our methodology is designed to leverage visual, linguistic and domain-specific features in user interaction traces to pre-train generic feature representations of UIs and their components. Our key intuition is that user actions, e.g., a sequence of clicks on different UI components, reveals important information about their functionality. We evaluate the proposed model on a wide variety of downstream tasks, ranging from icon classification to UI component retrieval based on its natural language description. Experiments show that the proposed ActionBert model outperforms multi-modal baselines across all downstream tasks by up to 15.5%.

cs.CL↗
arXiv2021

Voltage Inference for and Coordination of Distributed Voltage Controls in Extremely-High DER-Penetration Distribution Networks

The unique problems and phenomena in the distributed voltage control of large-scale power distribution systems with extremely-high DER-penetration are targeted in this paper. First, a DER-explicit distribution network model and voltage sensitivity are derived. Based on that, a voltage inference method is implemented to fill the gap of measurement insufficiency in the grid-edge areas. Then, autonomous Q control being implemented in each local area, a $\overline{Q}$-coordinated P control is designed to coordinate the reactive and real power controls. All the algorithms have been tested in standard and synthetic systems, and have expected results. Moreover, an open-source software platform, which integrates the modeling of communication networks, DER controls, and power networks, is developed to enable the distributed control and optimization algorithms in the grid simulation of the large-scale distribution systems.

eess.SY↗
arXiv2021

Understanding in Artificial Intelligence

Current Artificial Intelligence (AI) methods, most based on deep learning, have facilitated progress in several fields, including computer vision and natural language understanding. The progress of these AI methods is measured using benchmarks designed to solve challenging tasks, such as visual question answering. A question remains of how much understanding is leveraged by these methods and how appropriate are the current benchmarks to measure understanding capabilities. To answer these questions, we have analysed existing benchmarks and their understanding capabilities, defined by a set of understanding capabilities, and current research streams. We show how progress has been made in benchmark development to measure understanding capabilities of AI methods and we review as well how current methods develop understanding capabilities.

cs.AI↗
arXiv2020

Bubble Storytelling with Automated Animation: A Brexit Hashtag Activism Case Study

Hashtag data are common and easy to acquire. Thus, they are widely used in studies and visual data storytelling. For example, a recent story by China Central Television Europe (CCTV Europe) depicts Brexit as a hashtag movement displayed on an animated bubble chart. However, creating such a story is usually laborious and tedious, because narrators have to switch between different tools and discuss with different collaborators. To reduce the burden, we develop a prototype system to help explore the bubbles' movement by automatically inserting animations connected to the storytelling of the video creators and the interaction of viewers to those videos. We demonstrate the usability of our method through both use cases and a semi-structured user study.

cs.CY↗