Search Results for author: Qi Zhang

Found 170 papers, 62 papers with code

CQG: A Simple and Effective Controlled Generation Framework for Multi-hop Question Generation

1 code implementation ACL 2022 Zichu Fei, Qi Zhang, Tao Gui, Di Liang, Sirui Wang, Wei Wu, Xuanjing Huang

CQG employs a simple method to generate the multi-hop questions that contain key entities in multi-hop reasoning chains, which ensure the complexity and quality of the questions.

Question Generation

Robust Lottery Tickets for Pre-trained Language Models

1 code implementation ACL 2022 Rui Zheng, Bao Rong, Yuhao Zhou, Di Liang, Sirui Wang, Wei Wu, Tao Gui, Qi Zhang, Xuanjing Huang

Recent works on Lottery Ticket Hypothesis have shown that pre-trained language models (PLMs) contain smaller matching subnetworks(winning tickets) which are capable of reaching accuracy comparable to the original models.

Adversarial Robustness

An Empirical Assessment of the Qualitative Aspects of Misinformation in Health News

no code implementations NAACL (NLP4IF) 2021 Chaoyuan Zuo, Qi Zhang, Ritwik Banerjee

We present a health news classification task to determine whether medical news articles satisfy a set of review criteria deemed important by medical experts and health care journalists.

Fact Checking Misinformation +1

Iterative GNN-based Decoder for Question Generation

1 code implementation EMNLP 2021 Zichu Fei, Qi Zhang, Yaqian Zhou

However, (1) they ignore the rich structure information that is hidden in the previously generated text.

Question Generation

Cross-View Cross-Scene Multi-View Crowd Counting

no code implementations CVPR 2021 Qi Zhang, Wei Lin, Antoni B. Chan

Multi-view crowd counting has been previously proposed to utilize multi-cameras to extend the field-of-view of a single camera, capturing more people in the scene, and improve counting performance for occluded people or those in low resolution.

Camera Calibration Crowd Counting

Rapid Phase Ambiguity Elimination Methods for DOA Estimator via Hybrid Massive MIMO Receive Array

no code implementations27 Apr 2022 Xichao Zhan, YiWen Chen, Feng Shu, Xin Cheng, Yuanyuan Wu, Qi Zhang, Yifang Li, Peng Zhang

In the proposed Max-RP-QI, a quadratic interpolation scheme is adopted to interpolate the three DOA values corresponding to the largest three receive powers of Max-RP.

Process Knowledge-infused Learning for Suicidality Assessment on Social Media

no code implementations26 Apr 2022 Kaushik Roy, Manas Gaur, Qi Zhang, Amit Sheth

Improving the performance and natural language explanations of deep learning algorithms is a priority for adoption by humans in the real world.

Multi-view Information Bottleneck Without Variational Approximation

1 code implementation22 Apr 2022 Qi Zhang, Shujian Yu, Jingmin Xin, Badong Chen

By "intelligently" fusing the complementary information across different views, multi-view learning is able to improve the performance of classification tasks.

MULTI-VIEW LEARNING

A Benchmark for Automatic Medical Consultation System: Frameworks, Tasks and Datasets

1 code implementation19 Apr 2022 Wei Chen, Zhiwei Li, Hongyi Fang, Qianyuan Yao, Cheng Zhong, Jianye Hao, Qi Zhang, Xuanjing Huang, Jiajie Peng, Zhongyu Wei

In recent years, interest has arisen in using machine learning to improve the efficiency of automatic medical consultation and enhance patient experience.

Dialogue Act Classification Dialogue Understanding +2

PixelFolder: An Efficient Progressive Pixel Synthesis Network for Image Generation

1 code implementation2 Apr 2022 Jing He, Yiyi Zhou, Qi Zhang, Yunhang Shen, Xiaoshuai Sun, Chao Chen, Rongrong Ji

Pixel synthesis is a promising research paradigm for image generation, which can well exploit pixel-wise prior knowledge for generation.

Image Generation

CMMD: Cross-Metric Multi-Dimensional Root Cause Analysis

no code implementations30 Mar 2022 Shifu Yan, Caihua Shan, Wenyi Yang, Bixiong Xu, Dongsheng Li, Lili Qiu, Jie Tong, Qi Zhang

To this end, we propose a cross-metric multi-dimensional root cause analysis method, named CMMD, which consists of two key components: 1) relationship modeling, which utilizes graph neural network (GNN) to model the unknown complex calculation among metrics and aggregation function among dimensions from historical data; 2) root cause localization, which adopts the genetic algorithm to efficiently and effectively dive into the raw data and localize the abnormal dimension(s) once the KPI anomalies are detected.

UV Volumes for Real-time Rendering of Editable Free-view Human Performance

1 code implementation27 Mar 2022 Yue Chen, Xuan Wang, Qi Zhang, Xiaoyu Li, Xingyu Chen, Yu Guo, Jue Wang, Fei Wang

Neural volume rendering has been proven to be a promising method for efficient and photo-realistic rendering of a human performer in free-view, a critical task in many immersive VR/AR applications.

Chaos is a Ladder: A New Theoretical Understanding of Contrastive Learning via Augmentation Overlap

1 code implementation25 Mar 2022 Yifei Wang, Qi Zhang, Yisen Wang, Jiansheng Yang, Zhouchen Lin

Our theory suggests an alternative understanding of contrastive learning: the role of aligning positive samples is more like a surrogate task than an ultimate goal, and the overlapped augmented views (i. e., the chaos) create a ladder for contrastive learning to gradually learn class-separated representations.

Contrastive Learning Model Selection +1

PEAR: Personalized Re-ranking with Contextualized Transformer for Recommendation

no code implementations23 Mar 2022 Yi Li, Jieming Zhu, Weiwen Liu, Liangcai Su, Guohao Cai, Qi Zhang, Ruiming Tang, Xi Xiao, Xiuqiang He

Specifically, PEAR not only captures feature-level and item-level interactions, but also models item contexts from both the initial ranking list and the historical clicked item list.

Recommendation Systems Re-Ranking

Divide and Conquer: Text Semantic Matching with Disentangled Keywords and Intents

1 code implementation Findings (ACL) 2022 Yicheng Zou, Hongwei Liu, Tao Gui, Junzhe Wang, Qi Zhang, Meng Tang, Haixiang Li, Daniel Wang

Text semantic matching is a fundamental task that has been widely used in various scenarios, such as community question answering, information retrieval, and recommendation.

Community Question Answering Information Retrieval

An Effective Way for Cross-Market Recommendation with Hybrid Pre-Ranking and Ranking Models

1 code implementation2 Mar 2022 Qi Zhang, Zijian Yang, Yilun Huang, Jiarong He, Lixiang Wang

The Cross-Market Recommendation task of WSDM CUP 2022 is about finding solutions to improve individual recommendation systems in resource-scarce target markets by leveraging data from similar high-resource source markets.

Recommendation Systems

HousE: Knowledge Graph Embedding with Householder Parameterization

1 code implementation16 Feb 2022 Rui Li, Jianan Zhao, Chaozhuo Li, Di He, Yiqi Wang, Yuming Liu, Hao Sun, Senzhang Wang, Weiwei Deng, Yanming Shen, Xing Xie, Qi Zhang

The effectiveness of knowledge graph embedding (KGE) largely depends on the ability to model intrinsic relation patterns and mapping properties.

Knowledge Graph Embedding

Post-Training Quantization for Cross-Platform Learned Image Compression

no code implementations15 Feb 2022 Dailan He, Ziming Yang, Yuan Chen, Qi Zhang, Hongwei Qin, Yan Wang

It has been witnessed that learned image compression has outperformed conventional image coding techniques and tends to be practical in industrial applications.

Image Compression Quantization

Progressively Optimized Bi-Granular Document Representation for Scalable Embedding Based Retrieval

2 code implementations14 Jan 2022 Shitao Xiao, Zheng Liu, Weihao Han, Jianjin Zhang, Yingxia Shao, Defu Lian, Chaozhuo Li, Hao Sun, Denvy Deng, Liangjie Zhang, Qi Zhang, Xing Xie

In this work, we tackle this problem with Bi-Granular Document Representation, where the lightweight sparse embeddings are indexed and standby in memory for coarse-grained candidate search, and the heavyweight dense embeddings are hosted in disk for fine-grained post verification.

Quantization

PromptBERT: Improving BERT Sentence Embeddings with Prompts

1 code implementation12 Jan 2022 Ting Jiang, Shaohan Huang, Zihan Zhang, Deqing Wang, Fuzhen Zhuang, Furu Wei, Haizhen Huang, Liangjie Zhang, Qi Zhang

To this end, we propose a prompt based sentence embeddings method which can reduce token embeddings biases and make the original BERT layers more effective.

Denoising Semantic Similarity +2

A Multi-agent Reinforcement Learning Approach for Efficient Client Selection in Federated Learning

no code implementations9 Jan 2022 Sai Qian Zhang, Jieyu Lin, Qi Zhang

Federated learning (FL) is a training technique that enables client devices to jointly learn a shared model by aggregating locally-computed models without exposing their raw data.

Federated Learning Multi-agent Reinforcement Learning +1

Hallucinated Neural Radiance Fields in the Wild

no code implementations30 Nov 2021 Xingyu Chen, Qi Zhang, Xiaoyu Li, Yue Chen, Ying Feng, Xuan Wang, Jue Wang

This paper studies the problem of hallucinated NeRF: i. e. recovering a realistic NeRF at a different time of day from a group of tourism images.

Novel View Synthesis

HDR-NeRF: High Dynamic Range Neural Radiance Fields

no code implementations29 Nov 2021 Xin Huang, Qi Zhang, Ying Feng, Hongdong Li, Xuan Wang, Qing Wang

The key to our method is to model the physical imaging process, which dictates that the radiance of a scene point transforms to a pixel value in the LDR image with two implicit functions: a radiance field and a tone mapper.

Deblur-NeRF: Neural Radiance Fields from Blurry Images

no code implementations29 Nov 2021 Li Ma, Xiaoyu Li, Jing Liao, Qi Zhang, Xuan Wang, Jue Wang, Pedro V. Sander

We demonstrate that our method can be used on both camera motion blur and defocus blur: the two most common types of blur in real scenes.

3D Scene Reconstruction Novel View Synthesis

MQBench: Towards Reproducible and Deployable Model Quantization Benchmark

1 code implementation5 Nov 2021 Yuhang Li, Mingzhu Shen, Jian Ma, Yan Ren, Mingxin Zhao, Qi Zhang, Ruihao Gong, Fengwei Yu, Junjie Yan

Surprisingly, no existing algorithm wins every challenge in MQBench, and we hope this work could inspire future research directions.

Quantization

Improving Non-autoregressive Generation with Mixup Training

1 code implementation21 Oct 2021 Ting Jiang, Shaohan Huang, Zihan Zhang, Deqing Wang, Fuzhen Zhuang, Furu Wei, Haizhen Huang, Liangjie Zhang, Qi Zhang

While pre-trained language models have achieved great success on various natural language understanding tasks, how to effectively leverage them into non-autoregressive generation tasks remains a challenge.

Natural Language Understanding Paraphrase Generation +1

Plug-Tagger: A Pluggable Sequence Labeling Framework Using Language Models

no code implementations14 Oct 2021 Xin Zhou, Ruotian Ma, Tao Gui, Yiding Tan, Qi Zhang, Xuanjing Huang

Specifically, for each task, a label word set is first constructed by selecting a high-frequency word for each class respectively, and then, task-specific vectors are inserted into the inputs and optimized to manipulate the model predictions towards the corresponding label words.

Language Modelling Text Generation

Dimension Reduction and Data Visualization for Fréchet Regression

no code implementations1 Oct 2021 Qi Zhang, Lingzhou Xue, Bing Li

In this paper, we introduce a flexible sufficient dimension reduction (SDR) method for Fr\'echet regression to achieve two purposes: to mitigate the curse of dimensionality caused by high-dimensional predictors, and to provide a tool for data visualization for Fr\'echet regression.

Data Visualization Dimensionality Reduction

SAM: A Self-adaptive Attention Module for Context-Aware Recommendation System

no code implementations1 Oct 2021 Jiabin Liu, Zheng Wei, Zhengpin Li, Xiaojun Mao, Jian Wang, Zhongyu Wei, Qi Zhang

In this work, we propose a novel and general self-adaptive module, the Self-adaptive Attention Module (SAM), which adjusts the selection bias by capturing contextual information based on its representation.

Recommendation Systems Representation Learning +1

Robust High-Dimensional Regression with Coefficient Thresholding and its Application to Imaging Data Analysis

no code implementations30 Sep 2021 Bingyuan Liu, Qi Zhang, Lingzhou Xue, Peter X. K. Song, Jian Kang

It is of importance to develop statistical techniques to analyze high-dimensional data in the presence of both complex dependence and possible outliers in real-world applications such as imaging data analyses.

Post-Training Quantization Is All You Need to Perform Cross-Platform Learned Image Compression

no code implementations29 Sep 2021 Dailan He, Ziming Yang, Yan Wang, Yuan Chen, Qi Zhang, Hongwei Qin

It has been witnessed that learned image compression has outperformed conventional image coding techniques and tends to be practical in industrial applications.

Image Compression Quantization

Chaos is a Ladder: A New Understanding of Contrastive Learning

no code implementations ICLR 2022 Yifei Wang, Qi Zhang, Yisen Wang, Jiansheng Yang, Zhouchen Lin

Our work suggests an alternative understanding of contrastive learning: the role of aligning positive samples is more like a surrogate task than an ultimate goal, and it is the overlapping augmented views (i. e., the chaos) that create a ladder for contrastive learning to gradually learn class-separated representations.

Contrastive Learning Self-Supervised Learning

Template-free Prompt Tuning for Few-shot NER

1 code implementation28 Sep 2021 Ruotian Ma, Xin Zhou, Tao Gui, Yiding Tan, Linyang Li, Qi Zhang, Xuanjing Huang

Prompt-based methods have been successfully applied in sentence-level few-shot learning tasks, mostly owing to the sophisticated design of templates and label words.

Few-Shot Learning few-shot-ner +2

Why Do We Click: Visual Impression-aware News Recommendation

1 code implementation26 Sep 2021 Jiahao Xun, Shengyu Zhang, Zhou Zhao, Jieming Zhu, Qi Zhang, Jingjie Li, Xiuqiang He, Xiaofei He, Tat-Seng Chua, Fei Wu

In this work, inspired by the fact that users make their click decisions mostly based on the visual impression they perceive when browsing news, we propose to capture such visual impression information with visual-semantic modeling for news recommendation.

Decision Making News Recommendation

A Relation-Oriented Clustering Method for Open Relation Extraction

1 code implementation EMNLP 2021 Jun Zhao, Tao Gui, Qi Zhang, Yaqian Zhou

The clustering-based unsupervised relation discovery method has gradually become one of the important methods of open relation extraction (OpenRE).

Relation Extraction

Heterogeneous Graph Neural Networks for Keyphrase Generation

1 code implementation EMNLP 2021 Jiacheng Ye, Ruijian Cai, Tao Gui, Qi Zhang

The encoder-decoder framework achieves state-of-the-art results in keyphrase generation (KG) tasks by predicting both present keyphrases that appear in the source document and absent keyphrases that do not.

Keyphrase Generation

Low-Resource Dialogue Summarization with Domain-Agnostic Multi-Source Pretraining

1 code implementation EMNLP 2021 Yicheng Zou, Bolin Zhu, Xingwu Hu, Tao Gui, Qi Zhang

With the rapid increase in the volume of dialogue data from daily life, there is a growing demand for dialogue summarization.

Searching for an Effective Defender: Benchmarking Defense against Adversarial Word Substitution

1 code implementation EMNLP 2021 Zongyi Li, Jianhan Xu, Jiehang Zeng, Linyang Li, Xiaoqing Zheng, Qi Zhang, Kai-Wei Chang, Cho-Jui Hsieh

Recent studies have shown that deep neural networks are vulnerable to intentionally crafted adversarial examples, and various methods have been proposed to defend against adversarial word-substitution attacks for neural NLP models.

MeDiaQA: A Question Answering Dataset on Medical Dialogues

no code implementations18 Aug 2021 Huqun Suri, Qi Zhang, Wenhua Huo, Yan Liu, Chunsheng Guan

In this paper, we introduce MeDiaQA, a novel question answering(QA) dataset, which constructed on real online Medical Dialogues.

Multiple-choice Question Answering

Math Word Problem Solving with Explicit Numerical Values

1 code implementation ACL 2021 Qinzhuo Wu, Qi Zhang, Zhongyu Wei, Xuanjing Huang

In recent years, math word problem solving has received considerable attention and achieved promising results, but previous methods rarely take numerical values into consideration.

Math Word Problem Solving

MedAI at SemEval-2021 Task 10: Negation-aware Pre-training for Source-free Negation Detection Domain Adaptation

no code implementations SEMEVAL 2021 Jinquan Sun, Qi Zhang, Yu Wang, Lei Zhang

Due to the increasing concerns for data privacy, source-free unsupervised domain adaptation attracts more and more research attention, where only a trained source model is assumed to be available, while the labeled source data remain private.

Negation Detection Unsupervised Domain Adaptation

Sleep Staging Based on Multi Scale Dual Attention Network

no code implementations18 Jul 2021 Huafeng Wang, Chonggang Lu, Qi Zhang, Zhimin Hu, Xiaodong Yuan, Pingshu Zhang, Wanquan Liu

In the literature, a large number of sleep staging methods based on single-channel EEG have been proposed with promising results and achieve the preliminary automation of sleep staging.

EEG Sleep Staging

Multi-Exit Vision Transformer for Dynamic Inference

no code implementations29 Jun 2021 Arian Bakhtiarnia, Qi Zhang, Alexandros Iosifidis

In this work, we propose seven different architectures for early exit branches that can be used for dynamic inference in Vision Transformer backbones.

Edge-computing

Knowledge Infused Policy Gradients with Upper Confidence Bound for Relational Bandits

no code implementations25 Jun 2021 Kaushik Roy, Qi Zhang, Manas Gaur, Amit Sheth

Contextual Bandits find important use cases in various real-life scenarios such as online advertising, recommendation systems, healthcare, etc.

Multi-Armed Bandits Recommendation Systems

SENT: Sentence-level Distant Relation Extraction via Negative Training

1 code implementation ACL 2021 Ruotian Ma, Tao Gui, Linyang Li, Qi Zhang, Yaqian Zhou, Xuanjing Huang

In this work, we propose the use of negative training (NT), in which a model is trained using complementary labels regarding that ``the instance does not belong to these complementary labels".

Relation Extraction

One2Set: Generating Diverse Keyphrases as a Set

1 code implementation ACL 2021 Jiacheng Ye, Tao Gui, Yichao Luo, Yige Xu, Qi Zhang

In this work, we propose a new training paradigm One2Set without predefining an order to concatenate the keyphrases.

Keyphrase Generation

Single-Layer Vision Transformers for More Accurate Early Exits with Less Overhead

no code implementations19 May 2021 Arian Bakhtiarnia, Qi Zhang, Alexandros Iosifidis

Deploying deep learning models in time-critical applications with limited computational resources, for instance in edge computing systems and IoT networks, is a challenging task that often relies on dynamic inference methods such as early exiting.

Audio Classification Crowd Counting +1

AdsGNN: Behavior-Graph Augmented Relevance Modeling in Sponsored Search

1 code implementation25 Apr 2021 Chaozhuo Li, Bochen Pang, Yuming Liu, Hao Sun, Zheng Liu, Xing Xie, Tianqi Yang, Yanling Cui, Liangjie Zhang, Qi Zhang

Our motivation lies in incorporating the tremendous amount of unsupervised user behavior data from the historical search logs as the complementary graph to facilitate relevance modeling.

Improving the Accuracy of Early Exits in Multi-Exit Architectures via Curriculum Learning

no code implementations21 Apr 2021 Arian Bakhtiarnia, Qi Zhang, Alexandros Iosifidis

Deploying deep learning services for time-sensitive and resource-constrained settings such as IoT using edge computing systems is a challenging task that requires dynamic adjustment of inference time.

Edge-computing

Keyphrase Generation with Fine-Grained Evaluation-Guided Reinforcement Learning

1 code implementation Findings (EMNLP) 2021 Yichao Luo, Yige Xu, Jiacheng Ye, Xipeng Qiu, Qi Zhang

In response to this problem, we propose a new fine-grained evaluation metric to improve the RL framework, which considers different granularities: token-level $F_1$ score, edit distance, duplication, and prediction quantities.

Keyphrase Generation reinforcement-learning

Who Responded to Whom: The Joint Effects of Latent Topics and Discourse in Conversation Structure

no code implementations17 Apr 2021 Lu Ji, Jing Li, Zhongyu Wei, Qi Zhang, Xuanjing Huang

Numerous online conversations are produced on a daily basis, resulting in a pressing need to conversation understanding.

Larger-Context Tagging: When and Why Does It Work?

no code implementations NAACL 2021 Jinlan Fu, Liangjing Feng, Qi Zhang, Xuanjing Huang, PengFei Liu

The development of neural networks and pretraining techniques has spawned many sentence-level tagging systems that achieved superior performance on typical benchmarks.

Deep-AIR: A Hybrid CNN-LSTM Framework for Air Quality Modeling in Metropolitan Cities

no code implementations25 Mar 2021 Yang Han, Qi Zhang, Victor O. K. Li, Jacqueline C. K. Lam

Our proposed framework creates 1x1 convolution layers to strengthen the learning of cross-feature spatial interaction between air pollution and important urban dynamic features, particularly road density, building density/height, and street canyon effect.

Knowledge Infused Policy Gradients for Adaptive Pandemic Control

no code implementations11 Feb 2021 Kaushik Roy, Qi Zhang, Manas Gaur, Amit Sheth

To this end, we introduce a mathematical framework for KIPG methods that can (a) induce relevant feature counts over multi-relational features of the world, (b) handle latent non-homogeneous counts as hidden variables that are linear combinations of kernelized aggregates over the features, and (b) infuse knowledge as functional constraints in a principled manner.

Decision Making

BRECQ: Pushing the Limit of Post-Training Quantization by Block Reconstruction

2 code implementations ICLR 2021 Yuhang Li, Ruihao Gong, Xu Tan, Yang Yang, Peng Hu, Qi Zhang, Fengwei Yu, Wei Wang, Shi Gu

To further employ the power of quantization, the mixed precision technique is incorporated in our framework by approximating the inter-layer and intra-layer sensitivity.

Image Classification Object Detection +1

Thermodynamic properties of ε-Fe with thermal electronic excitation effects on vibrational spectra

no code implementations1 Feb 2021 Jingyi Zhuang, Hongjin Wang, Qi Zhang, Renata M. Wentzcovitch

The thermodynamic properties of hcp-iron ({\epsilon}-Fe) are essential for investigating planetary cores' internal structure and dynamic properties.

Materials Science Computational Physics

Discovery of unconventional chiral charge order in kagome superconductor KV3Sb5

no code implementations31 Dec 2020 Yu-Xiao Jiang, Jia-Xin Yin, M. Michael Denner, Nana Shumiya, Brenden R. Ortiz, Junyi He, Xiaoxiong Liu, Songtian S. Zhang, Guoqing Chang, Ilya Belopolski, Qi Zhang, Md Shafayat Hossain, Tyler A. Cochran, Daniel Multer, Maksim Litskevich, Zi-Jia Cheng, Xian P. Yang, Zurab Guguchia, Gang Xu, Ziqiang Wang, Titus Neupert, Stephen D. Wilson, M. Zahid Hasan

Here we use high-resolution scanning tunnelling microscopy (STM) to discover an unconventional charge order in a kagome material KV3Sb5, with both a topological band structure and a superconducting ground state.

Superconductivity Materials Science Strongly Correlated Electrons

Uncertainty-Aware Label Refinement for Sequence Labeling

1 code implementation EMNLP 2020 Tao Gui, Jiacheng Ye, Qi Zhang, Zhengyan Li, Zichu Fei, Yeyun Gong, Xuanjing Huang

Conditional random fields (CRF) for label decoding has become ubiquitous in sequence labeling tasks.

Efficient Querying for Cooperative Probabilistic Commitments

no code implementations14 Dec 2020 Qi Zhang, Edmund H. Durfee, Satinder Singh

Multiagent systems can use commitments as the core of a general coordination infrastructure, supporting both cooperative and non-cooperative interactions.

Topic-Oriented Spoken Dialogue Summarization for Customer Service with Saliency-Aware Topic Modeling

1 code implementation14 Dec 2020 Yicheng Zou, Lujun Zhao, Yangyang Kang, Jun Lin, Minlong Peng, Zhuoren Jiang, Changlong Sun, Qi Zhang, Xuanjing Huang, Xiaozhong Liu

In a customer service system, dialogue summarization can boost service efficiency by automatically creating summaries for long spoken dialogues in which customers and agents try to address issues about specific topics.

SenSeNet: Neural Keyphrase Generation with Document Structure

no code implementations12 Dec 2020 Yichao Luo, Zhengyan Li, Bingning Wang, Xiaoyu Xing, Qi Zhang, Xuanjing Huang

Keyphrase Generation (KG) is the task of generating central topics from a given document or literary work, which captures the crucial information necessary to understand the content.

Keyphrase Generation

Study of $qqq\bar{q}Q$ pentaquark system in the Chiral Quark Model

no code implementations3 Dec 2020 Qi Zhang, Xiao-Huang Hu, Bing-Ran He, Jia-Lun Ping

With the discovery of some hidden-charm pentaquark resonances by the LHCb Collaboration, investigations of pentaquark states containing heavy quarks have aroused the interest of theorists.

High Energy Physics - Phenomenology High Energy Physics - Experiment High Energy Physics - Lattice

Wide-Area Crowd Counting: Multi-View Fusion Networks for Counting in Large Scenes

1 code implementation2 Dec 2020 Qi Zhang, Antoni B. Chan

We consider three versions of the fusion framework: the late fusion model fuses camera-view density map; the naive early fusion model fuses camera-view feature maps; and the multi-view multi-scale early fusion model ensures that features aligned to the same ground-plane point have consistent scales.

Crowd Counting

Modeling Evolution of Message Interaction for Rumor Resolution

no code implementations COLING 2020 Lei Chen, Zhongyu Wei, Jing Li, Baohua Zhou, Qi Zhang, Xuanjing Huang

Previous work for rumor resolution concentrates on exploiting time-series characteristics or modeling topology structure separately.

Time Series

RethinkCWS: Is Chinese Word Segmentation a Solved Task?

1 code implementation EMNLP 2020 Jinlan Fu, PengFei Liu, Qi Zhang, Xuanjing Huang

The performance of the Chinese Word Segmentation (CWS) systems has gradually reached a plateau with the rapid development of deep neural networks, especially the successful use of large pre-trained models.

Chinese Word Segmentation

AbdomenCT-1K: Is Abdominal Organ Segmentation A Solved Problem?

1 code implementation28 Oct 2020 Jun Ma, Yao Zhang, Song Gu, Cheng Zhu, Cheng Ge, Yichi Zhang, Xingle An, Congcong Wang, Qiyuan Wang, Xin Liu, Shucheng Cao, Qi Zhang, Shangqing Liu, Yunpeng Wang, Yuhui Li, Jian He, Xiaoping Yang

With the unprecedented developments in deep learning, automatic segmentation of main abdominal organs seems to be a solved problem as state-of-the-art (SOTA) methods have achieved comparable results with inter-rater variability on many benchmark datasets.

Continual Learning Pancreas Segmentation

Succinct and Robust Multi-Agent Communication With Temporal Message Control

1 code implementation NeurIPS 2020 Sai Qian Zhang, Jieyu Lin, Qi Zhang

Recent studies have shown that introducing communication between agents can significantly improve overall performance in cooperative Multi-agent reinforcement learning (MARL).

Multi-agent Reinforcement Learning reinforcement-learning

Multi-Constitutive Neural Network for Large Deformation Poromechanics Problem

no code implementations11 Oct 2020 Qi Zhang, Yilin Chen, ZiYi Yang, Eric Darve

We propose a novel method "multi-constitutive neural network" (MCNN) such that one model can solve several different constitutive laws.

Decomposition and Adaptive Sampling for Data-Driven Inverse Linear Optimization

no code implementations16 Sep 2020 Rishabh Gupta, Qi Zhang

This work addresses inverse linear optimization where the goal is to infer the unknown cost vector of a linear program.

online learning

Tasty Burgers, Soggy Fries: Probing Aspect Robustness in Aspect-Based Sentiment Analysis

1 code implementation EMNLP 2020 Xiaoyu Xing, Zhijing Jin, Di Jin, Bingning Wang, Qi Zhang, Xuanjing Huang

Based on the SemEval 2014 dataset, we construct the Aspect Robustness Test Set (ARTS) as a comprehensive probe of the aspect robustness of ABSA models.

Aspect-Based Sentiment Analysis

Open Benchmarking for Click-Through Rate Prediction

no code implementations12 Sep 2020 Jieming Zhu, Jinyang Liu, Shuai Yang, Qi Zhang, Xiuqiang He

We have publicly released the benchmarking tools, evaluation protocols, and experimental settings of our work to promote reproducible research in this field.

Click-Through Rate Prediction Recommendation Systems

Multivariate Time-series Anomaly Detection via Graph Attention Network

3 code implementations4 Sep 2020 Hang Zhao, Yujing Wang, Juanyong Duan, Congrui Huang, Defu Cao, Yunhai Tong, Bixiong Xu, Jing Bai, Jie Tong, Qi Zhang

Anomaly detection on multivariate time-series is of great importance in both data mining research and industrial applications.

Anomaly Detection Graph Attention +2

Two Step Joint Model for Drug Drug Interaction Extraction

no code implementations28 Aug 2020 Siliang Tang, Qi Zhang, Tianpeng Zheng, Mengdi Zhou, Zhan Chen, Lixing Shen, Xiang Ren, Yueting Zhuang, ShiLiang Pu, Fei Wu

When patients need to take medicine, particularly taking more than one kind of drug simultaneously, they should be alarmed that there possibly exists drug-drug interaction.

Drug–drug Interaction Extraction Named Entity Recognition +2

Bitcoin Transaction Forecasting with Deep Network Representation Learning

no code implementations15 Jul 2020 Wenqi Wei, Qi Zhang, Ling Liu

First, we explore three interesting properties between Bitcoin transaction accounts: topological connectivity pattern of Bitcoin accounts, transaction amount pattern, and transaction dynamics.

Representation Learning

Single-Frame based Deep View Synchronization for Unsynchronized Multi-Camera Surveillance

no code implementations8 Jul 2020 Qi Zhang, Antoni B. Chan

To handle the issue of unsynchronized multi-cameras, in this paper, we propose a synchronization model that works in conjunction with existing DNN-based multi-view models, thus avoiding the redesign of the whole model.

3D Pose Estimation 3D Reconstruction +1

ReCO: A Large Scale Chinese Reading Comprehension Dataset on Opinion

1 code implementation22 Jun 2020 BingningWang, Ting Yao, Qi Zhang, Jingfang Xu, Xiaochuan Wang

The release of ReCO consists of 300k questions that to our knowledge is the largest in Chinese reading comprehension.

Causal Inference Chinese Reading Comprehension +2

Context-Aware Attention Network for Image-Text Retrieval

no code implementations CVPR 2020 Qi Zhang, Zhen Lei, Zhaoxiang Zhang, Stan Z. Li

As a typical cross-modal problem, image-text bi-directional retrieval relies heavily on the joint embedding learning and similarity measure for each image-text pair.

Spatio-Temporal Graph Structure Learning for Traffic Forecasting

no code implementations AAAI 2020 Qi Zhang, Jianlong Chang, Gaofeng Meng, Shiming Xiang, Chunhong Pan

To address these issues, we propose a novel framework named Structure Learning Convolution (SLC) that enables to extend the traditional convolutional neural network (CNN) to graph domains and learn the graph structure for traffic forecasting.

Graph structure learning Time Series +1

3D Crowd Counting via Multi-View Fusion with 3D Gaussian Kernels

no code implementations18 Mar 2020 Qi Zhang, Antoni B. Chan

Unlike MVMS, we propose to solve the multi-view crowd counting task through 3D feature fusion with 3D scene-level density maps, instead of the 2D ground-plane ones.

Crowd Counting

Rethinking Generalization of Neural Models: A Named Entity Recognition Case Study

1 code implementation12 Jan 2020 Jinlan Fu, PengFei Liu, Qi Zhang, Xuanjing Huang

While neural network-based models have achieved impressive performance on a large body of NLP tasks, the generalization behavior of different models remains poorly understood: Does this excellent performance imply a perfect generalization model, or are there still some limitations?

Named Entity Recognition NER

Grid-less Variational Direction of Arrival Estimation in Heteroscedastic Noise Environment

no code implementations26 Dec 2019 Qi Zhang, Jiang Zhu, Yuantao Gu, Zhiwei Xu

This paper studies DOA in heteroscedastic noise (HN) environment, where the variance of noise is varied across the snapshots and the antennas.

Direction of Arrival Estimation

A Machine Learning-enhanced Robust P-Phase Picker for Real-time Seismic Monitoring

no code implementations21 Nov 2019 Dazhong Shen, Qi Zhang, Tong Xu, HengShu Zhu, Wenjia Zhao, Zikai Yin, Peilun Zhou, Lihua Fang, Enhong Chen, Hui Xiong

To this end, in this paper, we present a machine learning-enhanced framework based on ensemble learning strategy, EL-Picker, for the automatic identification of seismic P-phase arrivals on continuous and massive waveforms.

Ensemble Learning

Constructing Multiple Tasks for Augmentation: Improving Neural Image Classification With K-means Features

1 code implementation18 Nov 2019 Tao Gui, Lizhi Qing, Qi Zhang, Jiacheng Ye, HangYan, Zichu Fei, Xuanjing Huang

In order to effectively reduce the impact of non-ideal auxiliary tasks on the main task, we further proposed a novel meta-learning-based multi-task learning approach, which trained the shared hidden layers on auxiliary tasks, while the meta-optimization objective was to minimize the loss on the main task, ensuring that the optimizing direction led to an improvement on the main task.

Data Augmentation General Classification +3

Discrete Argument Representation Learning for Interactive Argument Pair Identification

1 code implementation NAACL 2021 Lu Ji, Zhongyu Wei, Jing Li, Qi Zhang, Xuanjing Huang

In this paper, we focus on extracting interactive argument pairs from two posts with opposite stances to a certain topic.

Representation Learning

A Lexicon-Based Graph Neural Network for Chinese NER

no code implementations IJCNLP 2019 Tao Gui, Yicheng Zou, Qi Zhang, Minlong Peng, Jinlan Fu, Zhongyu Wei, Xuanjing Huang

Recurrent neural networks (RNN) used for Chinese named entity recognition (NER) that sequentially track character and word information have achieved great success.

Chinese Named Entity Recognition NER

Asynchronous Deep Interaction Network for Natural Language Inference

no code implementations IJCNLP 2019 Di Liang, Fubao Zhang, Qi Zhang, Xuanjing Huang

However, in the process of reasoning, the role of the two sentences is obviously different, and the sentence pairs for NLI are asymmetrical corpora.

Natural Language Inference

Weighed Domain-Invariant Representation Learning for Cross-domain Sentiment Analysis

no code implementations COLING 2020 Minlong Peng, Qi Zhang, Xuanjing Huang

To address this problem, we propose a modification to DIRL, obtaining a novel weighted domain-invariant representation learning (WDIRL) framework.

Domain Adaptation Representation Learning +1

Self-driving scale car trained by Deep reinforcement learning

no code implementations8 Sep 2019 Qi Zhang, Tao Du, Changzheng Tian

To improve the generalization ability for the driving behavior, the reinforcement learning method requires extrinsic reward from the real environment, which may damage the car.

Autonomous Driving Q-Learning +2

Efficient Communication in Multi-Agent Reinforcement Learning via Variance Based Control

2 code implementations NeurIPS 2019 Sai Qian Zhang, Qi Zhang, Jieyu Lin

Multi-agent reinforcement learning (MARL) has recently received considerable attention due to its applicability to a wide range of real-world applications.

Multi-agent Reinforcement Learning reinforcement-learning +2

Demystifying Learning Rate Policies for High Accuracy Training of Deep Neural Networks

1 code implementation18 Aug 2019 Yanzhao Wu, Ling Liu, Juhyun Bae, Ka-Ho Chow, Arun Iyengar, Calton Pu, Wenqi Wei, Lei Yu, Qi Zhang

Learning Rate (LR) is an important hyper-parameter to tune for effective training of deep neural networks (DNNs).

Image Classification

Simplify the Usage of Lexicon in Chinese NER

2 code implementations ACL 2020 Ruotian Ma, Minlong Peng, Qi Zhang, Xuanjing Huang

This method avoids designing a complicated sequence modeling architecture, and for any neural NER model, it requires only subtle adjustment of the character representation layer to introduce the lexicon information.

Chinese Named Entity Recognition NER

Person Re-identification in Aerial Imagery

1 code implementation14 Aug 2019 Shizhou Zhang, Qi Zhang, Yifei Yang, Xing Wei, Peng Wang, Bingliang Jiao, Yanning Zhang

Our method can learn a discriminative and compact feature representation for ReID in aerial imagery and can be trained in an end-to-end fashion efficiently.

Object Detection Person Re-Identification

Image Super-Resolution Using a Wavelet-based Generative Adversarial Network

no code implementations24 Jul 2019 Qi Zhang, Huafeng Wang, Sichen Yang

Existing work like Super-Resolution Using a Generative Adversarial Network (SRGAN) can effectively restore the texture details of the image.

Image Super-Resolution

Gridless Variational Line Spectral Estimation with Multiple Measurement Vector from Quantized Samples

no code implementations20 Jun 2019 Jiang Zhu, Qi Zhang, Benzhou Jin, Zhiwei Xu

Utilizing multisnapshot quantized data in line spectral estimation (LSE) for improving the estimation accuracy is of vital importance in signal processing, e. g., channel estimation in energy efficient massive MIMO systems and direction of arrival estimation.

Signal Processing

Joint State Estimation Under Attack of Discrete Event Systems

no code implementations12 Jun 2019 Qi Zhang, Carla Seatzu, Zhiwu Li, Alessandro Giua

The aim of the attacker is that of altering the state estimation of the operator.

Cryptography and Security Formal Languages and Automata Theory

Time-Series Anomaly Detection Service at Microsoft

3 code implementations10 Jun 2019 Hansheng Ren, Bixiong Xu, Yujing Wang, Chao Yi, Congrui Huang, Xiaoyu Kou, Tony Xing, Mao Yang, Jie Tong, Qi Zhang

At Microsoft, we develop a time-series anomaly detection service which helps customers to monitor the time-series continuously and alert for potential incidents on time.

Anomaly Detection Saliency Detection +1

Distantly Supervised Named Entity Recognition using Positive-Unlabeled Learning

1 code implementation ACL 2019 Minlong Peng, Xiaoyu Xing, Qi Zhang, Jinlan Fu, Xuanjing Huang

In this work, we explore the way to perform named entity recognition (NER) using only unlabeled data and named entity dictionaries.

Named Entity Recognition NER

Wide-Area Crowd Counting via Ground-Plane Density Maps and Multi-View Fusion CNNs

no code implementations CVPR 2019 Qi Zhang, Antoni B. Chan

Crowd counting in single-view images has achieved outstanding performance on existing counting datasets.

Crowd Counting

Ray-Space Projection Model for Light Field Camera

no code implementations CVPR 2019 Qi Zhang, Jinbo Ling, Qing Wang, Jingyi Yu

A homogeneous ray-space projection matrix and a fundamental matrix are then proposed to establish ray-ray correspondences among multiple light fields.

Camera Calibration

Address Instance-level Label Prediction in Multiple Instance Learning

no code implementations29 May 2019 Minlong Peng, Qi Zhang

Existent approaches in this field were mainly designed for the bag-level label prediction (predict labels for bags) but not the instance-level (predict labels for instances), with the task loss being only defined at the bag level.

Multiple Instance Learning

Learning Task-specific Representation for Novel Words in Sequence Labeling

1 code implementation29 May 2019 Minlong Peng, Qi Zhang, Xiaoyu Xing, Tao Gui, Jinlan Fu, Xuanjing Huang

However, representations of unseen or rare words trained on the end task are usually poor for appreciable performance.

Named Entity Recognition NER +2

Authenticated Key-Value Stores with Hardware Enclaves

no code implementations26 Apr 2019 Yuzhe Tang, Ju Chen, Kai Li, Jianliang Xu, Qi Zhang

To circumvent the limited enclave memory (128 MB with the latest Intel CPUs), we propose to place the memory buffer of the eLSM store outside the enclave and protect the buffer using a new authenticated data structure by digesting individual LSM-tree levels.

Cryptography and Security Databases Distributed, Parallel, and Cluster Computing Data Structures and Algorithms

Sogou Machine Reading Comprehension Toolkit

1 code implementation28 Mar 2019 Jindou Wu, Yunlun Yang, Chao Deng, Hongyi Tang, Bingning Wang, Haoze Sun, Ting Yao, Qi Zhang

In this paper, we present a Sogou Machine Reading Comprehension (SMRC) toolkit that can be used to provide the fast and efficient development of modern machine comprehension models, including both published models and original prototypes.

Machine Reading Comprehension

A Unified Framework for Marketing Budget Allocation

no code implementations4 Feb 2019 Kui Zhao, Junhao Hua, Ling Yan, Qi Zhang, Huan Xu, Cheng Yang

In our approach, a semi-black-box model is built to forecast the dynamic market response and an efficient optimization method is proposed to solve the complex allocation task.

Decision Making

Learning Fast Matching Models from Weak Annotations

no code implementations30 Jan 2019 Xue Li, Zhipeng Luo, Hao Sun, Jianjin Zhang, Weihao Han, Xianqi Chu, Liangjie Zhang, Qi Zhang

The proposed training framework targets on mitigating both issues, by treating the stronger but undeployable models as annotators, and learning a deployable model from both human provided relevance labels and weakly annotated search log data.

A Comparative Measurement Study of Deep Learning as a Service Framework

1 code implementation29 Oct 2018 Yanzhao Wu, Ling Liu, Calton Pu, Wenqi Cao, Semih Sahin, Wenqi Wei, Qi Zhang

Big data powered Deep Learning (DL) and its applications have blossomed in recent years, fueled by three technological trends: a large amount of digitized data openly accessible, a growing number of DL software frameworks in open source and commercial markets, and a selection of affordable parallel computing hardware devices.

A Survey: Non-Orthogonal Multiple Access with Compressed Sensing Multiuser Detection for mMTC

no code implementations12 Oct 2018 Mehmood Alam, Qi Zhang

One objective of the 5G communication system and beyond is to support massive machine type of communication (mMTC) to propel the fast growth of diverse Internet of Things use cases.

Compressive Sensing

Transferring from Formal Newswire Domain with Hypernet for Twitter POS Tagging

no code implementations EMNLP 2018 Tao Gui, Qi Zhang, Jingjing Gong, Minlong Peng, Di Liang, Keyu Ding, Xuanjing Huang

However, from a linguistic perspective, Twitter users not only tend to mimic the formal expressions of traditional media, like news, but they also appear to be developing linguistically informal styles.

Domain Adaptation Multi-Task Learning +3

Predicting protein inter-residue contacts using composite likelihood maximization and deep learning

1 code implementation31 Aug 2018 Haicang Zhang, Qi Zhang, Fusong Ju, Jianwei Zhu, Yujuan Gao, Ziwei Xie, Minghua Deng, Shiwei Sun, Wei-Mou Zheng, Dongbo Bu

We further present successful application of the predicted contacts to accurately build tertiary structures for proteins in the PSICOV dataset.

Vector Approximate Message Passing Algorithm for Structured Perturbed Sensing Matrix

no code implementations26 Aug 2018 Jiang Zhu, Qi Zhang, Xiangming Meng, Zhiwei Xu

In this paper, we consider a general form of noisy compressive sensing (CS) where the sensing matrix is not precisely known.

Signal Processing

A Generic Multi-Projection-Center Model and Calibration Method for Light Field Cameras

no code implementations7 Aug 2018 Qi Zhang, Chunping Zhang, Jinbo Ling, Qing Wang, Jingyi Yu

Based on the MPC model and projective transformation, we propose a calibration algorithm to verify our light field camera model.

3D Reconstruction

Dynamic Feature Learning for Partial Face Recognition

no code implementations CVPR 2018 Lingxiao He, Haiqing Li, Qi Zhang, Zhenan Sun

Partial face recognition (PFR) in unconstrained environment is a very important task, especially in video surveillance, mobile devices, etc.

Face Recognition

Hybrid Point Cloud Attribute Compression Using Slice-based Layered Structure and Block-based Intra Prediction

no code implementations28 Apr 2018 Yiting Shao, Qi Zhang, Ge Li, Zhu Li

In intra-frame compression of point cloud color attributes, results demonstrate that our method performs better than the state-of-the-art region-adaptive hierarchical transform (RAHT) system, and on average a 29. 37$\%$ BD-rate gain is achieved.

Multimedia

Variational Bayesian Line Spectral Estimation with Multiple Measurement Vectors

no code implementations17 Mar 2018 Jiang Zhu, Qi Zhang, Peter Gerstoft, Mihai-Alin Badiu, Zhiwei Xu

In this paper, the line spectral estimation (LSE) problem with multiple measurement vectors (MMVs) is studied utilizing the Bayesian methods.

Information Theory Information Theory

4D Light Field Superpixel and Segmentation

no code implementations CVPR 2017 Hao Zhu, Qi Zhang, Qing Wang

Superpixel segmentation of 2D image has been widely used in many computer vision tasks.

Minimizing Maximum Regret in Commitment Constrained Sequential Decision Making

no code implementations14 Mar 2017 Qi Zhang, Satinder Singh, Edmund Durfee

In cooperative multiagent planning, it can often be beneficial for an agent to make commitments about aspects of its behavior to others, allowing them in turn to plan their own behaviors without taking the agent's detailed behavior into account.

Decision Making

Hashtag Recommendation Using End-To-End Memory Networks with Hierarchical Attention

no code implementations COLING 2016 Haoran Huang, Qi Zhang, Yeyun Gong, Xuanjing Huang

By incorporating the hierarchical attention mechanism, the relative improvement in the proposed method over the state-of-the-art method is around 67. 9{\%} in the F1-score.

Collaborative Filtering General Classification +3

Learning Word Embeddings from Intrinsic and Extrinsic Views

no code implementations20 Aug 2016 Jifan Chen, Kan Chen, Xipeng Qiu, Qi Zhang, Xuanjing Huang, Zheng Zhang

To prove the effectiveness of our model, we evaluate it on four tasks, including word similarity, reverse dictionaries, Wiki link prediction, and document classification.

Document Classification General Classification +3

Multiscale probability transformation of basic probability assignment

no code implementations6 Jun 2014 Meizhu Li, Qi Zhang, Yong Deng

In this paper, multiscale probability transformation of basic probability assignment based on the belief function and the plausibility function is proposed, which is a generalization of the pignistic probability transformation.

Decision Making

100+ Times Faster Weighted Median Filter (WMF)

no code implementations CVPR 2014 Qi Zhang, Li Xu, Jiaya Jia

Weighted median, in the form of either solver or filter, has been employed in a wide range of computer vision solutions for its beneficial properties in sparsity representation.

Optical Flow Estimation Stereo Matching +1