arXiv subjects

Ji Zhang

Publications and source records attributed to Ji Zhang.

At least 217 records · Page 12Linked to original sources

arXiv2021

GGP: A Graph-based Grouping Planner for Explicit Control of Long Text Generation

Existing data-driven methods can well handle short text generation. However, when applied to the long-text generation scenarios such as story generation or advertising text generation in the commercial scenario, these methods may generate illogical and uncontrollable texts. To address these aforementioned issues, we propose a graph-based grouping planner(GGP) following the idea of first-plan-then-generate. Specifically, given a collection of key phrases, GGP firstly encodes these phrases into an instance-level sequential representation and a corpus-level graph-based representation separately. With these two synergic representations, we then regroup these phrases into a fine-grained plan, based on which we generate the final long text. We conduct our experiments on three long text generation datasets and the experimental results reveal that GGP significantly outperforms baselines, which proves that GGP can control the long text generation by knowing how to say and in what order.

cs.CL↗

arXiv2021

ROSITA: Enhancing Vision-and-Language Semantic Alignments via Cross- and Intra-modal Knowledge Integration

Vision-and-language pretraining (VLP) aims to learn generic multimodal representations from massive image-text pairs. While various successful attempts have been proposed, learning fine-grained semantic alignments between image-text pairs plays a key role in their approaches. Nevertheless, most existing VLP approaches have not fully utilized the intrinsic knowledge within the image-text pairs, which limits the effectiveness of the learned alignments and further restricts the performance of their models. To this end, we introduce a new VLP method called ROSITA, which integrates the cross- and intra-modal knowledge in a unified scene graph to enhance the semantic alignments. Specifically, we introduce a novel structural knowledge masking (SKM) strategy to use the scene graph structure as a priori to perform masked language (region) modeling, which enhances the semantic alignments by eliminating the interference information within and across modalities. Extensive ablation studies and comprehensive analysis verifies the effectiveness of ROSITA in semantic alignments. Pretrained with both in-domain and out-of-domain datasets, ROSITA significantly outperforms existing state-of-the-art VLP methods on three typical vision-and-language tasks over six benchmark datasets.

cs.CV↗

arXiv2021

A Survey on Contact Tracing: the Latest Advancements and Challenges

Infectious diseases are caused by pathogenic microorganisms, such as bacteria, viruses, parasites or fungi, which can be spread, directly or indirectly, from one person to another. Infectious diseases pose a serious threat to human health, especially COVID-19 that has became a serious worldwide health concern since the end of 2019. Contact tracing is the process of identifying, assessing, and managing people who have been exposed to a disease to prevent its onward transmission. Contact tracing can help us better understand the transmission link of the virus, whereby better interrupting its transmission. Given the worldwide pandemic of COVID-19, contact tracing has become one of the most critical measures to effectively curb the spread of the virus. This paper presents a comprehensive survey on contact tracing, with a detailed coverage of the recent advancements the models, digital technologies, protocols and issues involved in contact tracing. The current challenges as well as future directions of contact tracing technologies are also presented.

cs.SI↗

arXiv2021

i3dLoc: Image-to-range Cross-domain Localization Robust to Inconsistent Environmental Conditions

We present a method for localizing a single camera with respect to a point cloud map in indoor and outdoor scenes. The problem is challenging because correspondences of local invariant features are inconsistent across the domains between image and 3D. The problem is even more challenging as the method must handle various environmental conditions such as illumination, weather, and seasonal changes. Our method can match equirectangular images to the 3D range projections by extracting cross-domain symmetric place descriptors. Our key insight is to retain condition-invariant 3D geometry features from limited data samples while eliminating the condition-related features by a designed Generative Adversarial Network. Based on such features, we further design a spherical convolution network to learn viewpoint-invariant symmetric place descriptors. We evaluate our method on extensive self-collected datasets, which involve \textit{Long-term} (variant appearance conditions), \textit{Large-scale} (up to $2km$ structure/unstructured environment), and \textit{Multistory} (four-floor confined space). Our method surpasses other current state-of-the-arts by achieving around $3$ times higher place retrievals to inconsistent environments, and above $3$ times accuracy on online localization. To highlight our method's generalization capabilities, we also evaluate the recognition across different datasets. With a single trained model, i3dLoc can demonstrate reliable visual localization in random conditions.

cs.CV↗

arXiv2021

Base flow decomposition for complex moving objects in linear hydrodynamics: application to helix-shaped flagellated microswimmers

The motion of microswimmers in complex flows is ruled by the interplay between swimmer propulsion and the dynamics induced by the fluid velocity field. Here we study the motion of a chiral microswimmer whose propulsion is provided by the spinning of a helical tail with respect to its body in a simple shear flow. Thanks to an efficient computational strategy that allowed us to simulate thousands of different trajectories, we show that the tail shape dramatically affects the swimmer's motion. In the shear dominated regime, the swimmers carrying an elliptical helical tail show several different Jeffery-like (tumbling) trajectories depending on their initial configuration. As the propulsion torque increases, a progressive regularization of the motion is observed until, in the propulsion dominated regime, the swimmers converge to the same final trajectory independently on the initial configuration. Overall, our results show that elliptical helix swimmer presents a much richer variety of trajectories with respect to the usually studied circular helix tails.

physics.flu-dyn↗

arXiv2021

Reversible optical-microwave quantum conversion assisted by optomechanical dynamically-dark modes

We propose a dynamically-dark-mode (DDM) scheme to realize the reversible quantum conversion between microwave and optical photons in an electro-optomechanical (EOM) model. It is shown that two DDMs appear at certain times during the dynamical evolution of the EOM model. It is demonstrated that the DDMs can induce two kinds of reversible and highly efficient quantum conversion between the microwave and optical fields, the conditional quantum conversion (CQC) and the entanglement-assisted quantum conversion (EAQC). The CQC happens at the condition of vanishing of the initial-state mean value of one of the microwave and optical fields, and only depends on the coupling ratio of the system under consideration. The EAQC occurs in the presence of the initial-state entanglement between the microwave and optical fields. It is found that the EAQC can be manipulated by engineering the initial-state entanglement and the coupling ratio. It is indicated that it is possible to realize the entanglement-enhanced (or suppressed) quantum conversion through controlling the phase of the initial-state parameter. Our work highlights the power of generating reversible and highly efficient quantum conversion between microwave and optical photons by the DDMs.

quant-ph↗

arXiv2021

State-Promoted Investment for Industrial Reforms: an Information Design Approach

We analyze the optimal strategy for a government to promote large-scale investment projects under information frictions. Specifically, we propose a model where the government collects information on probability of each investment and discloses it to private investors a la Kamenica and Gentzkow (2011). We derive the government's optimal information policy, which is characterized as threshold values for the unknown probability of the projects released to the private investors, and study how the underlying features of the economy affect the optimal policies. We find that when multiple projects are available, the government promotes the project with a bigger spillover effect by fully revealing the true state of the economy only when its probability is substantially high. Moreover, the development of the financial/information market also affects the optimal rule.

econ.TH↗

arXiv2021

AdaVQA: Overcoming Language Priors with Adapted Margin Cosine Loss

A number of studies point out that current Visual Question Answering (VQA) models are severely affected by the language prior problem, which refers to blindly making predictions based on the language shortcut. Some efforts have been devoted to overcoming this issue with delicate models. However, there is no research to address it from the angle of the answer feature space learning, despite of the fact that existing VQA methods all cast VQA as a classification task. Inspired by this, in this work, we attempt to tackle the language prior problem from the viewpoint of the feature space learning. To this end, an adapted margin cosine loss is designed to discriminate the frequent and the sparse answer feature space under each question type properly. As a result, the limited patterns within the language modality are largely reduced, thereby less language priors would be introduced by our method. We apply this loss function to several baseline models and evaluate its effectiveness on two VQA-CP benchmarks. Experimental results demonstrate that our adapted margin cosine loss can greatly enhance the baseline models with an absolute performance gain of 15\% on average, strongly verifying the potential of tackling the language prior problem in VQA from the angle of the answer feature space learning.

cs.CV↗

arXiv2021

OneStop QAMaker: Extract Question-Answer Pairs from Text in a One-Stop Approach

Large-scale question-answer (QA) pairs are critical for advancing research areas like machine reading comprehension and question answering. To construct QA pairs from documents requires determining how to ask a question and what is the corresponding answer. Existing methods for QA pair generation usually follow a pipeline approach. Namely, they first choose the most likely candidate answer span and then generate the answer-specific question. This pipeline approach, however, is undesired in mining the most appropriate QA pairs from documents since it ignores the connection between question generation and answer extraction, which may lead to incompatible QA pair generation, i.e., the selected answer span is inappropriate for question generation. However, for human annotators, we take the whole QA pair into account and consider the compatibility between question and answer. Inspired by such motivation, instead of the conventional pipeline approach, we propose a model named OneStop generate QA pairs from documents in a one-stop approach. Specifically, questions and their corresponding answer span is extracted simultaneously and the process of question generation and answer extraction mutually affect each other. Additionally, OneStop is much more efficient to be trained and deployed in industrial scenarios since it involves only one model to solve the complex QA generation task. We conduct comprehensive experiments on three large-scale machine reading comprehension datasets: SQuAD, NewsQA, and DuReader. The experimental results demonstrate that our OneStop model outperforms the baselines significantly regarding the quality of generated questions, quality of generated question-answer pairs, and model efficiency.

cs.CL↗

arXiv2021

Using Machine Learning to Automate Mammogram Images Analysis

Breast cancer is the second leading cause of cancer-related death after lung cancer in women. Early detection of breast cancer in X-ray mammography is believed to have effectively reduced the mortality rate. However, a relatively high false positive rate and a low specificity in mammography technology still exist. In this work, a computer-aided automatic mammogram analysis system is proposed to process the mammogram images and automatically discriminate them as either normal or cancerous, consisting of three consecutive image processing, feature selection, and image classification stages. In designing the system, the discrete wavelet transforms (Daubechies 2, Daubechies 4, and Biorthogonal 6.8) and the Fourier cosine transform were first used to parse the mammogram images and extract statistical features. Then, an entropy-based feature selection method was implemented to reduce the number of features. Finally, different pattern recognition methods (including the Back-propagation Network, the Linear Discriminant Analysis, and the Naive Bayes Classifier) and a voting classification scheme were employed. The performance of each classification strategy was evaluated for sensitivity, specificity, and accuracy and for general performance using the Receiver Operating Curve. Our method is validated on the dataset from the Eastern Health in Newfoundland and Labrador of Canada. The experimental results demonstrated that the proposed automatic mammogram analysis system could effectively improve the classification performances.

eess.IV↗

arXiv2021

Method and Dataset Entity Mining in Scientific Literature: A CNN + Bi-LSTM Model with Self-attention

Literature analysis facilitates researchers to acquire a good understanding of the development of science and technology. The traditional literature analysis focuses largely on the literature metadata such as topics, authors, abstracts, keywords, references, etc., and little attention was paid to the main content of papers. In many scientific domains such as science, computing, engineering, etc., the methods and datasets involved in the scientific papers published in those domains carry important information and are quite useful for domain analysis as well as algorithm and dataset recommendation. In this paper, we propose a novel entity recognition model, called MDER, which is able to effectively extract the method and dataset entities from the main textual content of scientific papers. The model utilizes rule embedding and adopts a parallel structure of CNN and Bi-LSTM with the self-attention mechanism. We evaluate the proposed model on datasets which are constructed from the published papers of four research areas in computer science, i.e., NLP, CV, Data Mining and AI. The experimental results demonstrate that our model performs well in all the four areas and it features a good learning capacity for cross-area learning and recognition. We also conduct experiments to evaluate the effectiveness of different building modules within our model which indicate that the importance of different building modules in collectively contributing to the good entity recognition performance as a whole. The data augmentation experiments on our model demonstrated that data augmentation positively contributes to model training, making our model much more robust in dealing with the scenarios where only small number of training samples are available. We finally apply our model on PAKDD papers published from 2009-2019 to mine insightful results from scientific papers published in a longer time span.

cs.AI↗

arXiv2020

A Data-driven Human Responsibility Management System

An ideal safe workplace is described as a place where staffs fulfill responsibilities in a well-organized order, potential hazardous events are being monitored in real-time, as well as the number of accidents and relevant damages are minimized. However, occupational-related death and injury are still increasing and have been highly attended in the last decades due to the lack of comprehensive safety management. A smart safety management system is therefore urgently needed, in which the staffs are instructed to fulfill responsibilities as well as automating risk evaluations and alerting staffs and departments when needed. In this paper, a smart system for safety management in the workplace based on responsibility big data analysis and the internet of things (IoT) are proposed. The real world implementation and assessment demonstrate that the proposed systems have superior accountability performance and improve the responsibility fulfillment through real-time supervision and self-reminder.

cs.AI↗

arXiv2020

Distant Supervision for E-commerce Query Segmentation via Attention Network

The booming online e-commerce platforms demand highly accurate approaches to segment queries that carry the product requirements of consumers. Recent works have shown that the supervised methods, especially those based on deep learning, are attractive for achieving better performance on the problem of query segmentation. However, the lack of labeled data is still a big challenge for training a deep segmentation network, and the problem of Out-of-Vocabulary (OOV) also adversely impacts the performance of query segmentation. Different from query segmentation task in an open domain, e-commerce scenario can provide external documents that are closely related to these queries. Thus, to deal with the two challenges, we employ the idea of distant supervision and design a novel method to find contexts in external documents and extract features from these contexts. In this work, we propose a BiLSTM-CRF based model with an attention module to encode external features, such that external contexts information, which can be utilized naturally and effectively to help query segmentation. Experiments on two datasets show the effectiveness of our approach compared with several kinds of baselines.

cs.AI↗

arXiv2020

AI Marker-based Large-scale AI Literature Mining

The knowledge contained in academic literature is interesting to mine. Inspired by the idea of molecular markers tracing in the field of biochemistry, three named entities, namely, methods, datasets and metrics are used as AI markers for AI literature. These entities can be used to trace the research process described in the bodies of papers, which opens up new perspectives for seeking and mining more valuable academic information. Firstly, the entity extraction model is used in this study to extract AI markers from large-scale AI literature. Secondly, original papers are traced for AI markers. Statistical and propagation analysis are performed based on tracing results. Finally, the co-occurrences of AI markers are used to achieve clustering. The evolution within method clusters and the influencing relationships amongst different research scene clusters are explored. The above-mentioned mining based on AI markers yields many meaningful discoveries. For example, the propagation of effective methods on the datasets is rapidly increasing with the development of time; effective methods proposed by China in recent years have increasing influence on other countries, whilst France is the opposite. Saliency detection, a classic computer vision research scene, is the least likely to be affected by other research scenes.

cs.IR↗

arXiv2020

Keep it Consistent: Topic-Aware Storytelling from an Image Stream via Iterative Multi-agent Communication

Visual storytelling aims to generate a narrative paragraph from a sequence of images automatically. Existing approaches construct text description independently for each image and roughly concatenate them as a story, which leads to the problem of generating semantically incoherent content. In this paper, we propose a new way for visual storytelling by introducing a topic description task to detect the global semantic context of an image stream. A story is then constructed with the guidance of the topic description. In order to combine the two generation tasks, we propose a multi-agent communication framework that regards the topic description generator and the story generator as two agents and learn them simultaneously via iterative updating mechanism. We validate our approach on VIST dataset, where quantitative results, ablations, and human evaluation demonstrate our method's good ability in generating stories with higher quality compared to state-of-the-art methods.

cs.CL↗

arXiv2020

AliMe KG: Domain Knowledge Graph Construction and Application in E-commerce

Pre-sales customer service is of importance to E-commerce platforms as it contributes to optimizing customers' buying process. To better serve users, we propose AliMe KG, a domain knowledge graph in E-commerce that captures user problems, points of interests (POI), item information and relations thereof. It helps to understand user needs, answer pre-sales questions and generate explanation texts. We applied AliMe KG to several online business scenarios such as shopping guide, question answering over properties and recommendation reason generation, and gained positive results. In the paper, we systematically introduce how we construct domain knowledge graph from free text, and demonstrate its business value with several applications. Our experience shows that mining structured knowledge from free text in vertical domain is practicable, and can be of substantial value in industrial settings.

cs.AI↗

arXiv2020

Monocular Camera Localization in Prior LiDAR Maps with 2D-3D Line Correspondences

Light-weight camera localization in existing maps is essential for vision-based navigation. Currently, visual and visual-inertial odometry (VO\&VIO) techniques are well-developed for state estimation but with inevitable accumulated drifts and pose jumps upon loop closure. To overcome these problems, we propose an efficient monocular camera localization method in prior LiDAR maps using direct 2D-3D line correspondences. To handle the appearance differences and modality gaps between LiDAR point clouds and images, geometric 3D lines are extracted offline from LiDAR maps while robust 2D lines are extracted online from video sequences. With the pose prediction from VIO, we can efficiently obtain coarse 2D-3D line correspondences. Then the camera poses and 2D-3D correspondences are iteratively optimized by minimizing the projection error of correspondences and rejecting outliers. Experimental results on the EurocMav dataset and our collected dataset demonstrate that the proposed method can efficiently estimate camera poses without accumulated drifts or pose jumps in structured environments.

cs.CV↗

arXiv2020

Character Matters: Video Story Understanding with Character-Aware Relations

Different from short videos and GIFs, video stories contain clear plots and lists of principal characters. Without identifying the connection between appearing people and character names, a model is not able to obtain a genuine understanding of the plots. Video Story Question Answering (VSQA) offers an effective way to benchmark higher-level comprehension abilities of a model. However, current VSQA methods merely extract generic visual features from a scene. With such an approach, they remain prone to learning just superficial correlations. In order to attain a genuine understanding of who did what to whom, we propose a novel model that continuously refines character-aware relations. This model specifically considers the characters in a video story, as well as the relations connecting different characters and objects. Based on these signals, our framework enables weakly-supervised face naming through multi-instance co-occurrence matching and supports high-level reasoning utilizing Transformer structures. We train and test our model on the six diverse TV shows in the TVQA dataset, which is by far the largest and only publicly available dataset for VSQA. We validate our proposed approach over TVQA dataset through extensive ablation study.

cs.CV↗