Search Results for author: Wei Zhao

Found 66 papers, 25 papers with code

Evaluation of Coreference Resolution Systems Under Adversarial Attacks

no code implementations EMNLP (CODI) 2020 Haixia Chai, Wei Zhao, Steffen Eger, Michael Strube

A substantial overlap of coreferent mentions in the CoNLL dataset magnifies the recent progress on coreference resolution.

Coreference Resolution

TUDa at WMT21: Sentence-Level Direct Assessment with Adapters

no code implementations WMT (EMNLP) 2021 Gregor Geigle, Jonas Stadtmüller, Wei Zhao, Jonas Pfeiffer, Steffen Eger

This paper presents our submissions to the WMT2021 Shared Task on Quality Estimation, Task 1 Sentence-Level Direct Assessment.

Residual Graph Convolutional Recurrent Networks For Multi-step Traffic Flow Forecasting

no code implementations3 May 2022 Wei Zhao, Shiqi Zhang, Bing Zhou, Bei Wang

The main challenge of traffic forecasting tasks is accurately capturing traffic networks' spatial and temporal correlation.

Time Series

Towards Explainable Evaluation Metrics for Natural Language Generation

1 code implementation21 Mar 2022 Christoph Leiter, Piyawat Lertvittayakumjorn, Marina Fomicheva, Wei Zhao, Yang Gao, Steffen Eger

We also provide a synthesizing overview over recent approaches for explainable machine translation metrics and discuss how they relate to those goals and properties.

Machine Translation Text Generation +1

STCGAT: Spatial-temporal causal networks for complex urban road traffic flow prediction

no code implementations21 Mar 2022 Wei Zhao, Shiqi Zhang, Bing Zhou, Bei Wang

Existing approaches usually use fixed traffic road network topology maps and independent time series modules to capture Spatial-temporal correlations, ignoring the dynamic changes of traffic road networks and the inherent temporal causal relationships between traffic events.

Less is More: Surgical Phase Recognition from Timestamp Supervision

no code implementations16 Feb 2022 Zixun Wang, Xinpeng Ding, Wei Zhao, Xiaomeng Li

Moreover, our proposed approach can be used to clean noisy labels near boundaries and improve the performance of the current surgical phase recognition methods.

What Do They Capture? -- A Structural Analysis of Pre-Trained Language Models for Source Code

1 code implementation14 Feb 2022 Yao Wan, Wei Zhao, Hongyu Zhang, Yulei Sui, Guandong Xu, Hai Jin

In this paper, we conduct a thorough structural analysis aiming to provide an interpretation of pre-trained language models for source code (e. g., CodeBERT, and GraphCodeBERT) from three distinctive perspectives: (1) attention analysis, (2) probing on the word embedding, and (3) syntax tree induction.

Code Completion Code Search +1

Constrained Density Matching and Modeling for Cross-lingual Alignment of Contextualized Representations

no code implementations31 Jan 2022 Wei Zhao, Steffen Eger

In this work, we attribute the data hungriness of previous alignment techniques to two limitations: (i) the inability to sufficiently leverage data and (ii) these techniques are not trained properly.

DiscoScore: Evaluating Text Generation with BERT and Discourse Coherence

1 code implementation26 Jan 2022 Wei Zhao, Michael Strube, Steffen Eger

We find that (i) the majority of BERT-based metrics correlate much worse with human rated coherence than early discourse metrics, invented a decade ago; (ii) the recent state-of-the-art BARTScore is weak when operated at system level -- which is particularly problematic as systems are typically compared in this manner.

Document Level Machine Translation Machine Translation +1

Bi-CLKT: Bi-Graph Contrastive Learning based Knowledge Tracing

no code implementations22 Jan 2022 XiangYu Song, JianXin Li, Qi Lei, Wei Zhao, Yunliang Chen, Ajmal Mian

The goal of Knowledge Tracing (KT) is to estimate how well students have mastered a concept based on their historical learning of related exercises.

Contrastive Learning Knowledge Tracing +1

SkipNode: On Alleviating Over-smoothing for Deep Graph Convolutional Networks

no code implementations22 Dec 2021 Weigang Lu, Yibing Zhan, Ziyu Guan, Liu Liu, Baosheng Yu, Wei Zhao, Yaming Yang, DaCheng Tao

Analytically, 1) skipping the convolutional operation prevents the features from losing diversity; and 2) the "skipped" nodes enable gradients to be directly passed back, thus mitigating the gradient vanishing and model weights over-decaying issues.

Link Prediction Node Classification

Voxelized 3D Feature Aggregation for Multiview Detection

1 code implementation7 Dec 2021 Jiahao Ma, Jinguang Tong, Shan Wang, Wei Zhao, Liang Zheng, Chuong Nguyen

However, we find that these 2D transformations do not take into account the object's height, and with this neglection features along the vertical direction of same object are likely not projected onto the same ground plane point, leading to impure ground-plane features.

Multiview Detection

Better than Average: Paired Evaluation of NLP Systems

1 code implementation ACL 2021 Maxime Peyrard, Wei Zhao, Steffen Eger, Robert West

Evaluation in NLP is usually done by comparing the scores of competing systems independently averaged over a common set of test instances.

Constrained Density Matching and Modeling for Effective Contextualized Alignment

no code implementations29 Sep 2021 Wei Zhao, Steffen Eger

In this work, we analyze the limitations according to which previous alignments become very resource-intensive, \emph{viz.,} (i) the inability to sufficiently leverage data and (ii) that alignments are not trained properly.

Metal Artifact Reduction in 2D CT Images with Self-supervised Cross-domain Learning

no code implementations28 Sep 2021 Lequan Yu, Zhicheng Zhang, Xiaomeng Li, Hongyi Ren, Wei Zhao, Lei Xing

We then design a novel FBP reconstruction loss to encourage the network to generate more perfect completion results and a residual-learning-based image refinement module to reduce the secondary artifacts in the reconstructed CT images.

Image Reconstruction Metal Artifact Reduction

Cross-Site Severity Assessment of COVID-19 from CT Images via Domain Adaptation

no code implementations8 Sep 2021 Geng-Xin Xu, Chen Liu, Jun Liu, Zhongxiang Ding, Feng Shi, Man Guo, Wei Zhao, Xiaoming Li, Ying WEI, Yaozong Gao, Chuan-Xian Ren, Dinggang Shen

Particularly, we propose a domain translator and align the heterogeneous data to the estimated class prototypes (i. e., class centers) in a hyper-sphere manifold.

Computed Tomography (CT) Domain Adaptation +1

Aligning Cross-lingual Sentence Representations with Dual Momentum Contrast

no code implementations EMNLP 2021 Liang Wang, Wei Zhao, Jingming Liu

In this paper, we propose to align sentence representations from different languages into a unified embedding space, where semantic similarities (both cross-lingual and monolingual) can be computed with a simple dot product.

Semantic Textual Similarity Translation

AP-10K: A Benchmark for Animal Pose Estimation in the Wild

4 code implementations28 Aug 2021 Hang Yu, Yufei Xu, Jing Zhang, Wei Zhao, Ziyu Guan, DaCheng Tao

The experimental results provide sound empirical evidence on the superiority of learning from diverse animals species in terms of both accuracy and generalization ability.

Animal Pose Estimation Domain Generalization +1

Graph Routing between Capsules

no code implementations22 Jun 2021 Yang Li, Wei Zhao, Erik Cambria, Suhang Wang, Steffen Eger

Therefore, in this paper, we introduce a new capsule network with graph routing to learn both relationships, where capsules in each layer are treated as the nodes of a graph.

Text Classification

Multi-Agent Cooperative Bidding Games for Multi-Objective Optimization in e-Commercial Sponsored Search

no code implementations8 Jun 2021 Ziyu Guan, Hongchang Wu, Qingyu Cao, Hao liu, Wei Zhao, Sheng Li, Cai Xu, Guang Qiu, Jian Xu, Bo Zheng

Although a few studies use multi-agent reinforcement learning to set up a cooperative game, they still suffer the following drawbacks: (1) They fail to avoid collusion solutions where all the advertisers involved in an auction collude to bid an extremely low price on purpose.

Multi-agent Reinforcement Learning

A Geometry-Informed Deep Learning Framework for Ultra-Sparse 3D Tomographic Image Reconstruction

no code implementations25 May 2021 Liyue Shen, Wei Zhao, Dante Capaldi, John Pauly, Lei Xing

Deep learning affords enormous opportunities to augment the armamentarium of biomedical imaging, albeit its design and implementation have potential flaws.

Image Reconstruction

Self-interpretable Convolutional Neural Networks for Text Classification

no code implementations18 May 2021 Wei Zhao, Rahul Singh, Tarun Joshi, Agus Sudjianto, Vijayan N. Nair

We also study the impact of the complexity of the convolutional layers and the classification layers on the model performance.

Classification Natural Language Processing +1

Importance Weighted Adversarial Discriminative Transfer for Anomaly Detection

1 code implementation14 May 2021 Cangning Fan, Fangyi Zhang, Peng Liu, Xiuyu Sun, Hao Li, Ting Xiao, Wei Zhao, Xianglong Tang

In this way, an obvious gap can be produced between the distributions of normal and abnormal data in the target domain, therefore enabling the anomaly detection in the domain.

Anomaly Detection

TransCT: Dual-path Transformer for Low Dose Computed Tomography

1 code implementation28 Feb 2021 Zhicheng Zhang, Lequan Yu, Xiaokun Liang, Wei Zhao, Lei Xing

Low dose computed tomography (LDCT) has attracted more and more attention in routine clinical diagnosis assessment, therapy planning, etc., which can reduce the dose of X-ray radiation to patients.

Structural Interventions in Networks

no code implementations29 Jan 2021 Yang Sun, Wei Zhao, Junjie Zhou

Two types of interventions are commonly implemented in networks: characteristic intervention, which influences individuals' intrinsic incentives, and structural intervention, which targets the social links among individuals.

A Two-Stage Wavelet Decomposition Method for Instantaneous Power Quality Indices Estimation Considering Interharmonics and Transient Disturbances

no code implementations10 Jan 2021 Yiqing Yu, Wei Zhao, Shisong Li, Songling Huang

As the complexity increases in modern power systems, power quality analysis considering interharmonics has become a challenging and important task.

Regularized Attentive Capsule Network for Overlapped Relation Extraction

no code implementations COLING 2020 Tianyi Liu, Xiangyu Lin, Weijia Jia, Mingliang Zhou, Wei Zhao

Distantly supervised relation extraction has been widely applied in knowledge base construction due to its less requirement of human efforts.

Relation Extraction

SE-ECGNet: A Multi-scale Deep Residual Network with Squeeze-and-Excitation Module for ECG Signal Classification

1 code implementation10 Dec 2020 Haozhen Zhang, Wei Zhao, Shuang Liu

The classification of electrocardiogram (ECG) signals, which takes much time and suffers from a high rate of misjudgment, is recognized as an extremely challenging task for cardiologists.

Classification General Classification

Compressive Circular Polarization Snapshot Spectral Imaging

no code implementations29 Nov 2020 Jianglan Ning, Zhilong Xu, Dan Wu, Rui Zhang, Yuanyuan Wang, Yingge Xie, Wei Zhao, Xu Ma, Wenyi Ren

A compressive sensing based circular polarization snapshot spectral imaging system is proposed in this paper to acquire two-dimensional spatial, one-dimensional circular polarization (the right and left circular polarization), and one-dimensional spectral information, simultaneously.

Compressive Sensing Optics Image and Video Processing 78A10 (Primary) I.4.2; I.4.4; I.4.5

Ape210K: A Large-Scale and Template-Rich Dataset of Math Word Problems

no code implementations24 Sep 2020 Wei Zhao, Mingyue Shang, Yang Liu, Liang Wang, Jingming Liu

We propose a copy-augmented and feature-enriched sequence to sequence (seq2seq) model, which outperforms existing models by 3. 2% on the Math23K dataset and serves as a strong baseline of the Ape210K dataset.

Math Word Problem Solving Natural Language Understanding

Contracting over persistent information

no code implementations12 Jul 2020 Wei Zhao, Claudio Mezzetti, Ludovic Renou, Tristan Tomala

We consider a dynamic moral hazard problem between a principal and an agent, where the sole instrument the principal has to incentivize the agent is the disclosure of information.

Sapphire: Automatic Configuration Recommendation for Distributed Storage Systems

no code implementations7 Jul 2020 Wenhao Lyu, Youyou Lu, Jiwu Shu, Wei Zhao

Modern distributed storage systems come with aplethora of configurable parameters that controlmodule behavior and affect system performance.

Interpretable and Efficient Heterogeneous Graph Convolutional Network

1 code implementation27 May 2020 Yaming Yang, Ziyu Guan, Jian-Xin Li, Wei Zhao, Jiangtao Cui, Quan Wang

However, regarding Heterogeneous Information Network (HIN), existing HIN-oriented GCN methods still suffer from two deficiencies: (1) they cannot flexibly explore all possible meta-paths and extract the most useful ones for a target object, which hinders both effectiveness and interpretability; (2) they often need to generate intermediate meta-path based dense graphs, which leads to high computational complexity.

Synergistic Learning of Lung Lobe Segmentation and Hierarchical Multi-Instance Classification for Automated Severity Assessment of COVID-19 in CT Images

no code implementations8 May 2020 Kelei He, Wei Zhao, Xingzhi Xie, Wen Ji, Mingxia Liu, Zhenyu Tang, Feng Shi, Yang Gao, Jun Liu, Junfeng Zhang, Dinggang Shen

Considering that only a few infection regions in a CT image are related to the severity assessment, we first represent each input image by a bag that contains a set of 2D image patches (with each cropped from a specific slice).

On the Limitations of Cross-lingual Encoders as Exposed by Reference-Free Machine Translation Evaluation

1 code implementation ACL 2020 Wei Zhao, Goran Glavaš, Maxime Peyrard, Yang Gao, Robert West, Steffen Eger

We systematically investigate a range of metrics based on state-of-the-art cross-lingual semantic representations obtained with pretrained M-BERT and LASER.

Language Modelling Machine Translation +4

COVID-19 Chest CT Image Segmentation -- A Deep Convolutional Neural Network Solution

no code implementations23 Apr 2020 Qingsen Yan, Bo wang, Dong Gong, Chuan Luo, Wei Zhao, Jianhu Shen, Qinfeng Shi, Shuo Jin, Liang Zhang, Zheng You

Inspired by the observation that the boundary of the infected lung can be enhanced by adjusting the global intensity, in the proposed deep CNN, we introduce a feature variation block which adaptively adjusts the global properties of the features for segmenting COVID-19 infection.

Computed Tomography (CT) Medical Image Segmentation +1

Severity Assessment of Coronavirus Disease 2019 (COVID-19) Using Quantitative Features from Chest CT Images

no code implementations26 Mar 2020 Zhenyu Tang, Wei Zhao, Xingzhi Xie, Zheng Zhong, Feng Shi, Jun Liu, Dinggang Shen

Purpose: Using machine learning method to realize automatic severity assessment (non-severe or severe) of COVID-19 based on chest CT images, and to explore the severity-related features from the resulting assessment model.

Computed Tomography (CT)

Noise control and utility: from regulatory network to spatial patterning

no code implementations19 Jan 2020 Qing Nie, Lingxia Qiao, Yuchi Qiu, Lei Zhang, Wei Zhao

Stochasticity (or noise) at cellular and molecular levels has been observed extensively as a universal feature for living systems.

Denoising based Sequence-to-Sequence Pre-training for Text Generation

1 code implementation IJCNLP 2019 Liang Wang, Wei Zhao, Ruoyu Jia, Sujian Li, Jingming Liu

This paper presents a new sequence-to-sequence (seq2seq) pre-training method PoDA (Pre-training of Denoising Autoencoders), which learns representations suitable for text generation tasks.

Abstractive Text Summarization Denoising +2

IntentGC: a Scalable Graph Convolution Framework Fusing Heterogeneous Information for Recommendation

1 code implementation24 Jul 2019 Jun Zhao, Zhou Zhou, Ziyu Guan, Wei Zhao, Wei Ning, Guang Qiu, Xiaofei He

In this work, we collect abundant relationships from common user behaviors and item information, and propose a novel framework named IntentGC to leverage both explicit preferences and heterogeneous relationships by graph convolutional networks.

Network Embedding

Towards Scalable and Reliable Capsule Networks for Challenging NLP Applications

5 code implementations ACL 2019 Wei Zhao, Haiyun Peng, Steffen Eger, Erik Cambria, Min Yang

Obstacles hindering the development of capsule networks for challenging NLP applications include poor scalability to large output spaces and less reliable routing processes.

 Ranked #1 on Text Classification on RCV1 (P@1 metric)

General Classification Multi Label Text Classification +2

Time-sync Video Tag Extraction Using Semantic Association Graph

no code implementations3 May 2019 Wenmian Yang, Kun Wang, Na Ruan, Wenyuan Gao, Weijia Jia, Wei Zhao, Nan Liu, Yunyong Zhang

Finally, we gain the weight of each word by combining Semantic Weight (SW) and Inverse Document Frequency (IDF).


Vector and Line Quantization for Billion-scale Similarity Search on GPUs

1 code implementation2 Jan 2019 Wei Chen, Jincai Chen, Fuhao Zou, Yuan-Fang Li, Ping Lu, Qiang Wang, Wei Zhao

The inverted index structure is amenable to GPU-based implementations, and the state-of-the-art systems such as Faiss are able to exploit the massive parallelism offered by GPUs.


Fast Dynamic Routing Based on Weighted Kernel Density Estimation

3 code implementations28 May 2018 Suofei Zhang, Wei Zhao, Xiaofu Wu, Quan Zhou

Capsules as well as dynamic routing between them are most recently proposed structures for deep neural networks.

Density Estimation Image Classification

IoT Security: An End-to-End View and Case Study

no code implementations15 May 2018 Zhen Ling, Kaizheng Liu, Yiling Xu, Chao GAO, Yier Jin, Cliff Zou, Xinwen Fu, Wei Zhao

The work in this paper raises the alarm again for the IoT device manufacturers to better secure their products in order to prevent malware attacks like Mirai.

Cryptography and Security

Security Consideration For Deep Learning-Based Image Forensics

no code implementations29 Mar 2018 Wei Zhao, Pengpeng Yang, Rongrong Ni, Yao Zhao, Haorui Wu

Instead of improving it, in this paper, the safety of deep learning based methods in the field of image forensics is taken into account.

Image Forensics

Identifying and Tracking Sentiments and Topics from Social Media Texts during Natural Disasters

no code implementations EMNLP 2017 Min Yang, Jincheng Mei, Heng Ji, Wei Zhao, Zhou Zhao, Xiaojun Chen

We study the problem of identifying the topics and sentiments and tracking their shifts from social media texts in different geographical regions during emergencies and disasters.

Topic Models

Source Camera Identification Based On Content-Adaptive Fusion Network

no code implementations15 Mar 2017 Pengpeng Yang, Wei Zhao, Rongrong Ni, Yao Zhao

In this paper, we propose a solution to identify the source camera of the small-size images: content-adaptive fusion network.

Cannot find the paper you are looking for? You can Submit a new open access paper.