Search Results for author: Jian Liu

Found 52 papers, 15 papers with code

Machine Reading Comprehension as Data Augmentation: A Case Study on Implicit Event Argument Extraction

no code implementations EMNLP 2021 Jian Liu, Yufeng Chen, Jinan Xu

Implicit event argument extraction (EAE) is a crucial document-level information extraction task that aims to identify event arguments beyond the sentence level.

Data Augmentation Event Argument Extraction +2

Event Extraction as Machine Reading Comprehension

no code implementations EMNLP 2020 Jian Liu, Yubo Chen, Kang Liu, Wei Bi, Xiaojiang Liu

ii) Our model is excelled in the data-scarce scenario, for example, obtaining 49. 8{\%} in F1 for event argument extraction with only 1{\%} data, compared with 2. 2{\%} of the previous method.

Event Argument Extraction Event Extraction +3

Saliency as Evidence: Event Detection with Trigger Saliency Attribution

no code implementations ACL 2022 Jian Liu, Yufeng Chen, Jinan Xu

Event detection (ED) is a critical subtask of event extraction that seeks to identify event triggers of certain types in texts. Despite significant advances in ED, existing methods typically follow a “one model fits all types” approach, which sees no differences between event types and often results in a quite skewed performance. Finding the causes of skewed performance is crucial for the robustness of an ED model, but to date there has been little exploration of this problem. This research examines the issue in depth and presents a new concept termed trigger salience attribution, which can explicitly quantify the underlying patterns of events.

Event Detection Event Extraction

基于多任务标签一致性机制的中文命名实体识别(Chinese Named Entity Recognition based on Multi-task Label Consistency Mechanism)

no code implementations CCL 2021 Shuning Lv, Jian Liu, Jinan Xu, Yufeng Chen, Yujie Zhang

“实体边界预测对中文命名实体识别至关重要。现有研究为改善边界识别效果提出的多任务学习方法仅考虑与分词任务结合, 缺少多任务标签训练数据, 无法学到任务的标签一致性关系。本文提出一种新的基于多任务标签一致性机制的中文命名实体识别方法:将分词和词性信息融入命名实体识别模型, 使三种任务联合训练;建立基于标签一致性机制的多任务学习模式, 来捕获标签一致性关系及学习多任务表示。全样本和小样本实验表明了方法的有效性。”

Chinese Named Entity Recognition named-entity-recognition

DProQ: A Gated-Graph Transformer for Protein Complex Structure Assessment

1 code implementation21 May 2022 Xiao Chen, Alex Morehead, Jian Liu, Jianlin Cheng

We challenge this significant task with DProQ, which introduces a gated neighborhood-modulating Graph Transformer (GGT) designed to predict the quality of 3D protein complex structures.

Drug Discovery

EGR: Equivariant Graph Refinement and Assessment of 3D Protein Complex Structures

1 code implementation20 May 2022 Alex Morehead, Xiao Chen, Tianqi Wu, Jian Liu, Jianlin Cheng

Protein complexes are macromolecules essential to the functioning and well-being of all living organisms.

Drug Discovery

Visual Attention-based Self-supervised Absolute Depth Estimation using Geometric Priors in Autonomous Driving

1 code implementation18 May 2022 Jie Xiang, Yun Wang, Lifeng An, Haiyang Liu, Zijun Wang, Jian Liu

Although existing monocular depth estimation methods have made great progress, predicting an accurate absolute depth map from a single image is still challenging due to the limited modeling capacity of networks and the scale ambiguity issue.

Autonomous Driving Monocular Depth Estimation

VPNets: Volume-preserving neural networks for learning source-free dynamics

1 code implementation29 Apr 2022 Aiqing Zhu, Beibei Zhu, Jiawei Zhang, Yifa Tang, Jian Liu

We propose volume-preserving networks (VPNets) for learning unknown source-free dynamical systems using trajectory data.

Auditing Privacy Defenses in Federated Learning via Generative Gradient Leakage

1 code implementation CVPR 2022 Zhuohang Li, Jiaxin Zhang, Luyang Liu, Jian Liu

Federated Learning (FL) framework brings privacy benefits to distributed learning systems by allowing multiple clients to participate in a learning task under the coordination of a central server without exchanging their private data.

Federated Learning

Conditional Bilingual Mutual Information Based Adaptive Training for Neural Machine Translation

1 code implementation ACL 2022 Songming Zhang, Yijin Liu, Fandong Meng, Yufeng Chen, Jinan Xu, Jian Liu, Jie zhou

Token-level adaptive training approaches can alleviate the token imbalance problem and thus improve neural machine translation, through re-weighting the losses of different target tokens based on specific statistical metrics (e. g., token frequency or mutual information).

Language Modelling Machine Translation +1

Label Relation Graphs Enhanced Hierarchical Residual Network for Hierarchical Multi-Granularity Classification

no code implementations CVPR 2022 Jingzhou Chen, Peng Wang, Jian Liu, Yuntao Qian

Hierarchical multi-granularity classification (HMC) assigns hierarchical multi-granularity labels to each object and focuses on encoding the label hierarchy, e. g., ["Albatross", "Laysan Albatross"] from coarse-to-fine levels.

Fine-Grained Image Classification

Spatio-temporal-spectral-angular observation model that integrates observations from UAV and mobile mapping vehicle for better urban mapping

no code implementations24 Aug 2021 Zhenfeng Shao, Gui Cheng, Deren Li, Xiao Huang, Zhipeng Lu, Jian Liu

The integrated results combined both the characteristic of UAV and mobile mapping vehicle point cloud, confirming the practicability of the proposed joint data acquisition platform and the effectiveness of spatio-temporal-spectral-angular observation model.

"Adversarial Examples" for Proof-of-Learning

no code implementations21 Aug 2021 Rui Zhang, Jian Liu, Yuan Ding, Zhibo Wu, Qingbiao Wang, Kui Ren

Jia et al. claimed that an adversary merely knowing the final model and training dataset cannot efficiently find a set of intermediate models with correct data points.

The Effect of Dust and Sand on the 5G Terrestrial Links

no code implementations20 Aug 2021 Esmail M M Abuhdima, Gurcan Comert, Pierluigi Pisu, Chin-Tser Huang, Ahmed El Qaouaq, Chunheng Zhao, Shakendra Alston, Kirk Ambrose, Jian Liu

A recent study investigates the effect of rain and snow on the 5G communication channel to reduce the challenge of using high millimeter-wave frequencies.

Byzantine-robust Federated Learning through Spatial-temporal Analysis of Local Model Updates

no code implementations3 Jul 2021 Zhuohang Li, Luyang Liu, Jiaxin Zhang, Jian Liu

Federated Learning (FL) enables multiple distributed clients (e. g., mobile devices) to collaboratively train a centralized model while keeping the training data locally on the client.

Federated Learning

Template-Based Named Entity Recognition Using BART

1 code implementation Findings (ACL) 2021 Leyang Cui, Yu Wu, Jian Liu, Sen yang, Yue Zhang

To address the issue, we propose a template-based method for NER, treating NER as a language model ranking problem in a sequence-to-sequence framework, where original sentences and statement templates filled by candidate named entity span are regarded as the source sequence and the target sequence, respectively.

few-shot-ner Few-shot NER +4

OFEI: A Semi-black-box Android Adversarial Sample Attack Framework Against DLaaS

no code implementations25 May 2021 Guangquan Xu, GuoHua Xin, Litao Jiao, Jian Liu, Shaoying Liu, Meiqi Feng, Xi Zheng

With the growing popularity of Android devices, Android malware is seriously threatening the safety of users.

Unsupervised Sentiment Analysis by Transferring Multi-source Knowledge

no code implementations9 May 2021 Yong Dai, Jian Liu, Jian Zhang, Hongguang Fu, Zenglin Xu

The first mechanism is a selective domain adaptation (SDA) method, which transfers knowledge from the closest source domain.

Domain Adaptation Sentiment Analysis

A hybrid deep-learning approach for complex biochemical named entity recognition

no code implementations20 Dec 2020 Jian Liu, Lei Gao, Sujie Guo, Rui Ding, Xin Huang, Long Ye, Qinghua Meng, Asef Nazari, Dhananjay Thiruvady

In this approach, the MHATT mechanism aims to improve the recognition accuracy of abbreviations to efficiently deal with the problem of inconsistency in full-text labels.

named-entity-recognition NER +1

Graph-Based Knowledge Integration for Question Answering over Dialogue

no code implementations COLING 2020 Jian Liu, Dianbo Sui, Kang Liu, Jun Zhao

Despite many advances, existing approaches for this task did not consider dialogue structure and background knowledge (e. g., relationships between speakers).

Machine Reading Comprehension Question Answering +1

Natural Language Inference in Context -- Investigating Contextual Reasoning over Long Texts

1 code implementation10 Nov 2020 Hanmeng Liu, Leyang Cui, Jian Liu, Yue Zhang

Natural language inference (NLI) is a fundamental NLP task, investigating the entailment relationship between two texts.

Natural Language Inference

Singular equivalences induced by bimodules and quadratic monomial algebras

no code implementations20 Sep 2020 Xiao-Wu Chen, Jian Liu, Ren Wang

We investigate the problem when the tensor functor by a bimodule yields a singular equivalence.

Representation Theory Rings and Algebras 18G80, 16E45, 16D20, 16G20

LogiQA: A Challenge Dataset for Machine Reading Comprehension with Logical Reasoning

1 code implementation16 Jul 2020 Jian Liu, Leyang Cui, Hanmeng Liu, Dandan Huang, Yile Wang, Yue Zhang

Machine reading is a fundamental task for testing the capability of natural language understanding, which is closely related to human cognition in many aspects.

Machine Reading Comprehension Natural Language Understanding

Adversarial Training Based Multi-Source Unsupervised Domain Adaptation for Sentiment Analysis

no code implementations10 Jun 2020 Yong Dai, Jian Liu, Xiancong Ren, Zenglin Xu

Existing algorithms of MS-UDA either only exploit the shared features, i. e., the domain-invariant information, or based on some weak assumption in NLP, e. g., smoothness assumption.

Multi-Source Unsupervised Domain Adaptation Sentiment Analysis +2

Enabling Fast and Universal Audio Adversarial Attack Using Generative Model

no code implementations26 Apr 2020 Yi Xie, Zhuohang Li, Cong Shi, Jian Liu, Yingying Chen, Bo Yuan

These idealized assumptions, however, makes the existing audio adversarial attacks mostly impossible to be launched in a timely fashion in practice (e. g., playing unnoticeable adversarial perturbations along with user's streaming input).

Adversarial Attack

Learn to Forget: Machine Unlearning via Neuron Masking

no code implementations24 Mar 2020 Yang Liu, Zhuo Ma, Ximeng Liu, Jian Liu, Zhongyuan Jiang, Jianfeng Ma, Philip Yu, Kui Ren

To this end, machine unlearning becomes a popular research topic, which allows users to eliminate memorization of their private data from a trained machine learning model. In this paper, we propose the first uniform metric called for-getting rate to measure the effectiveness of a machine unlearning method.

Federated Learning

Real-time, Universal, and Robust Adversarial Attacks Against Speaker Recognition Systems

no code implementations4 Mar 2020 Yi Xie, Cong Shi, Zhuohang Li, Jian Liu, Yingying Chen, Bo Yuan

As the popularity of voice user interface (VUI) exploded in recent years, speaker recognition system has emerged as an important medium of identifying a speaker in many security-required applications and services.

Adversarial Attack Speaker Recognition

Review and Examination of Input Feature Preparation Methods and Machine Learning Models for Turbulence Modeling

1 code implementation15 Jan 2020 Shirui Luo, Jiahuan Cui, Madhu Vellakal, Jian Liu, Enyi Jiang, Seid Koric, Volodymyr Kindratenko

Model extrapolation to unseen flow is one of the biggest challenges facing data-driven turbulence modeling, especially for models with high dimensional inputs that involve many flow features.

Fluid Dynamics Computational Physics

Free-riders in Federated Learning: Attacks and Defenses

no code implementations28 Nov 2019 Jierui Lin, Min Du, Jian Liu

Although the incentive model for federated learning has not been fully developed, it is supposed that participants are able to get rewards or the privilege to use the final global model, as a compensation for taking efforts to train the model.

Anomaly Detection Federated Learning

Adversarial Attack on Skeleton-based Human Action Recognition

no code implementations14 Sep 2019 Jian Liu, Naveed Akhtar, Ajmal Mian

We also explore the possibility of semantically imperceptible localized attacks with CIASA, and succeed in fooling the state-of-the-art skeleton action recognition models with high confidence.

Action Recognition Adversarial Attack +1

Spearphone: A Speech Privacy Exploit via Accelerometer-Sensed Reverberations from Smartphone Loudspeakers

1 code implementation12 Jul 2019 S Abhishek Anand, Chen Wang, Jian Liu, Nitesh Saxena, Yingying Chen

In this paper, we build a speech privacy attack that exploits speech reverberations generated from a smartphone's inbuilt loudspeaker captured via a zero-permission motion sensor (accelerometer).

Cryptography and Security

Temporally Coherent Full 3D Mesh Human Pose Recovery from Monocular Video

no code implementations1 Jun 2019 Jian Liu, Naveed Akhtar, Ajmal Mian

A major challenge in this regard is the lack of appropriately annotated video data for learning the desired deep models.

Deep Cross Networks with Aesthetic Preference for Cross-domain Recommendation

no code implementations29 May 2019 Jian Liu, Pengpeng Zhao, Yanchi Liu, Victor S. Sheng, Fuzheng Zhuang, Jiajie Xu, Xiaofang Zhou, Hui Xiong

Then, we integrate the aesthetic features into a cross-domain network to transfer users' domain independent aesthetic preferences.

Transfer Learning

Biophysics at the coffee shop: lessons learned working with George Oster

no code implementations20 Feb 2019 Oleg Igoshin, Jing Chen, Jianhua Xing, Jian Liu, Timothy C. Elston, Michael Grabe, Kenneth S. Kim, Jasmine Nirody, Padmini Rangamani, Sean Sun, Hongyun Wang, Charles Wolgemuth

Over the past 50 years, the use of mathematical models, derived from physical reasoning, to describe molecular and cellular systems has evolved from an art of the few to a cornerstone of biological inquiry.

Latent Dirichlet Allocation in Generative Adversarial Networks

no code implementations17 Dec 2018 Lili Pan, Shen Cheng, Jian Liu, Yazhou Ren, Zenglin Xu

We study the problem of multimodal generative modelling of images based on generative adversarial networks (GANs).

Image Generation Stochastic Optimization

Faster super-resolution imaging with auto-correlation two-step deconvolution

2 code implementations19 Sep 2018 Weisong Zhao, Jian Liu, Chenqi Kong, Yixuan Zhao, Changliang Guo, Chen-Guang Liu, Xiangyan Ding, Xumin Ding, Jiubin Tan, Haoyu Li

Despite super-resolution fluorescence blinking microscopes break the diffraction limit, the intense phototoxic illumination and long-term image sequences thus far still pose to major challenges in visualizing live-organisms.


Event Detection via Gated Multilingual Attention Mechanism

no code implementations AAAI-18 2018 Jian Liu, Yubo Chen, Kang Liu, Jun Zhao

In specific, to alleviate data scarcity problem, we exploit the consistent information in multilingual data via context attention mechanism.

Event Detection

Understanding Android Obfuscation Techniques: A Large-Scale Investigation in the Wild

no code implementations5 Jan 2018 Shuaike Dong, Menghao Li, Wenrui Diao, Xiangyu Liu, Jian Liu, Zhou Li, Fenghao Xu, Kai Chen, Xiao-Feng Wang, Kehuan Zhang

In this paper, we seek to better understand Android obfuscation and depict a holistic view of the usage of obfuscation through a large-scale investigation in the wild.

Cryptography and Security

Defense against Universal Adversarial Perturbations

no code implementations CVPR 2018 Naveed Akhtar, Jian Liu, Ajmal Mian

A rigorous evaluation shows that our framework can defend the network classifiers against unseen adversarial perturbations in the real-world scenarios with up to 97. 5% success rate.

Skepxels: Spatio-temporal Image Representation of Human Skeleton Joints for Action Recognition

no code implementations16 Nov 2017 Jian Liu, Naveed Akhtar, Ajmal Mian

The proposed action recognition exploits the representation in a hierarchical manner by first capturing the micro-temporal relations between the skeleton joints with the Skepxels and then exploiting their macro-temporal relations by computing the Fourier Temporal Pyramids over the CNN features of the skeletal images.

Action Analysis Action Recognition

Viewpoint Invariant Action Recognition using RGB-D Videos

no code implementations15 Sep 2017 Jian Liu, Naveed Akhtar, Ajmal Mian

The proposed technique capitalizes on the spatio-temporal information available in the two data streams to the extract action features that are largely insensitive to the viewpoint variations.

Action Recognition Transfer Learning

Learning Human Pose Models from Synthesized Data for Robust RGB-D Action Recognition

no code implementations4 Jul 2017 Jian Liu, Naveed Akhtar, Ajmal Mian

We propose Human Pose Models that represent RGB and depth images of human poses independent of clothing textures, backgrounds, lighting conditions, body shapes and camera viewpoints.

Action Recognition Skeleton Based Action Recognition

Improvement of training set structure in fusion data cleaning using Time-Domain Global Similarity method

no code implementations30 Jun 2017 Jian Liu, Ting Lan, Hong Qin

Traditional data cleaning identifies dirty data by classifying original data sequences, which is a class$-$imbalanced problem since the proportion of incorrect data is much less than the proportion of correct ones for most diagnostic systems in Magnetic Confinement Fusion (MCF) devices.

Classification General Classification

Preference-based performance measures for Time-Domain Global Similarity method

no code implementations30 Jun 2017 Ting Lan, Jian Liu, Hong Qin

To obtain the general expressions of performance measures based on the preferences of tasks, the mapping relations between performance of TDGS method about physical similarity and correctness of data sequences are investigated by probability theory in this paper.

General Classification

Context-aware System Service Call-oriented Symbolic Execution of Android Framework with Application to Exploit Generation

no code implementations2 Nov 2016 Lannan Luo, Qiang Zeng, Chen Cao, Kai Chen, Jian Liu, Limin Liu, Neng Gao, Min Yang, Xinyu Xing, Peng Liu

We present novel ideas and techniques to resolve the challenges, and have built the first system for symbolic execution of Android Framework.

Cryptography and Security Software Engineering

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