Search Results for author:
Found 79 papers, 31 papers with code
Saliency as Evidence: Event Detection with Trigger Saliency Attribution
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 Extraction as Machine Reading Comprehension
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.
Machine Reading Comprehension as Data Augmentation: A Case Study on Implicit Event Argument Extraction
Implicit event argument extraction (EAE) is a crucial document-level information extraction task that aims to identify event arguments beyond the sentence level.
Saliency-based Multi-View Mixed Language Training for Zero-shot Cross-lingual Classification
Recent multilingual pre-trained models, like XLM-RoBERTa (XLM-R), have been demonstrated effective in many cross-lingual tasks.
Cross-Lingual Sentiment Classification
Dialogue State Tracking
+4
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)
“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
+1
Iterative Constrained Back-Translation for Unsupervised Domain Adaptation of Machine Translation
In this paper, we propose an Iterative Constrained Back-Translation (ICBT) method to incorporate in-domain lexical knowledge on the basis of BT for unsupervised domain adaptation of NMT.
A Quality-based Syntactic Template Retriever for Syntactically-controlled Paraphrase Generation
Furthermore, for situations requiring multiple paraphrases for each source sentence, we design a Diverse Templates Search (DTS) algorithm, which can enhance the diversity between paraphrases without sacrificing quality.
Label-efficient Segmentation via Affinity Propagation
In this work, we formulate the affinity modeling as an affinity propagation process, and propose a local and a global pairwise affinity terms to generate accurate soft pseudo labels.
Equirectangular image construction method for standard CNNs for Semantic Segmentation
In addition, there are few publicly dataset of equirectangular images with labels, which presents a challenge for standard CNNs models to process equirectangular images effectively.
GLoRE: Evaluating Logical Reasoning of Large Language Models
Recently, large language models (LLMs), including notable models such as GPT-4 and burgeoning community models, have showcased significant general language understanding abilities.
ChatGPT for Computational Topology
This work serves as an initial step towards effectively transforming pure mathematical theories into practical computational tools, with the ultimate goal of enabling real applications across diverse fields.
AffordPose: A Large-scale Dataset of Hand-Object Interactions with Affordance-driven Hand Pose
We collect a total of 26. 7K hand-object interactions, each including the 3D object shape, the part-level affordance label, and the manually adjusted hand poses.
Point2Mask: Point-supervised Panoptic Segmentation via Optimal Transport
Weakly-supervised image segmentation has recently attracted increasing research attentions, aiming to avoid the expensive pixel-wise labeling.
Towards Understanding and Improving Knowledge Distillation for Neural Machine Translation
In this work, we first unravel this mystery from an empirical perspective and show that the knowledge comes from the top-1 predictions of teachers, which also helps us build a potential connection between word- and sequence-level KD.
Full Scaling Automation for Sustainable Development of Green Data Centers
The rapid rise in cloud computing has resulted in an alarming increase in data centers' carbon emissions, which now accounts for >3% of global greenhouse gas emissions, necessitating immediate steps to combat their mounting strain on the global climate.
Exploring the Mutual Influence between Self-Supervised Single-Frame and Multi-Frame Depth Estimation
Although both self-supervised single-frame and multi-frame depth estimation methods only require unlabeled monocular videos for training, the information they leverage varies because single-frame methods mainly rely on appearance-based features while multi-frame methods focus on geometric cues.
False Claims against Model Ownership Resolution
Our core idea is that a malicious accuser can deviate (without detection) from the specified MOR process by finding (transferable) adversarial examples that successfully serve as evidence against independent suspect models.
RecUP-FL: Reconciling Utility and Privacy in Federated Learning via User-configurable Privacy Defense
In this paper, we seek to reconcile utility and privacy in FL by proposing a user-configurable privacy defense, RecUP-FL, that can better focus on the user-specified sensitive attributes while obtaining significant improvements in utility over traditional defenses.
Multi-Sample Consensus Driven Unsupervised Normal Estimation for 3D Point Clouds
Comprehensive experiments demonstrate that the two proposed unsupervised methods are noticeably superior to some supervised deep normal estimators on the most common synthetic dataset.
Evaluating the Logical Reasoning Ability of ChatGPT and GPT-4
With the release of Generative Pretrained Transformer 4 (GPT-4), highlighted as "advanced" at reasoning tasks, we are eager to learn the GPT-4 performance on various logical reasoning tasks.
Speech Privacy Leakage from Shared Gradients in Distributed Learning
Distributed machine learning paradigms, such as federated learning, have been recently adopted in many privacy-critical applications for speech analysis.
Diffusion Models in Bioinformatics: A New Wave of Deep Learning Revolution in Action
This review aims to provide a rather thorough overview of the applications of diffusion models in bioinformatics to aid their further development in bioinformatics and computational biology.
Artificial Intelligence System for Detection and Screening of Cardiac Abnormalities using Electrocardiogram Images
In this study, we present an AI system developed to detect and screen cardiac abnormalities (CAs) from real-world ECG images.
Scene-Aware Label Graph Learning for Multi-Label Image Classification
Multi-label image classification refers to assigning a set of labels for an image.
Protocol selection for second-order consensus against disturbance
Noticing that both the absolute and relative velocity protocols can solve the second-order consensus of multi-agent systems, this paper aims to investigate which of the above two protocols has better anti-disturbance capability, in which the anti-disturbance capability is measured by the L2 gain from the disturbance to the consensus error.
On the Robustness of Dataset Inference
However, in a subspace of the same setting, we prove that DI suffers from high false positives (FPs) -- it can incorrectly identify an independent model trained with non-overlapping data from the same distribution as stolen.
OST: Efficient One-stream Network for 3D Single Object Tracking in Point Clouds
Although recent Siamese network-based trackers have achieved impressive perceptual accuracy for single object tracking in LiDAR point clouds, they advance with some heavy correlation operations on relation modeling and overlook the inherent merit of arbitrariness compared to multiple object tracking.
Improved Data Augmentation for Translation Suggestion
This paper introduces the system used in our submission to the WMT'22 Translation Suggestion shared task.
RIBAC: Towards Robust and Imperceptible Backdoor Attack against Compact DNN
Recently backdoor attack has become an emerging threat to the security of deep neural network (DNN) models.
Multi-Forgery Detection Challenge 2022: Push the Frontier of Unconstrained and Diverse Forgery Detection
In this paper, we present the solutions from the Top 3 teams, in order to boost the research work in the field of image forgery detection.
Multi-parametric Analysis for Mixed Integer Linear Programming: An Application to Transmission Planning and Congestion Control
Finally, the amount of capacity upgrade will be chosen by balancing the cost-reduction rate of the objective function on parameters and the cost of the line upgrade.
Watermark Vaccine: Adversarial Attacks to Prevent Watermark Removal
Inspired by the vulnerability of DNNs on adversarial perturbations, we propose a novel defence mechanism by adversarial machine learning for good.
DProQ: A Gated-Graph Transformer for Protein Complex Structure Assessment
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.
EGR: Equivariant Graph Refinement and Assessment of 3D Protein Complex Structures
Protein complexes are macromolecules essential to the functioning and well-being of all living organisms.
Visual Attention-based Self-supervised Absolute Depth Estimation using Geometric Priors in Autonomous Driving
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.
VPNets: Volume-preserving neural networks for learning source-free dynamics
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
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.
Conditional Bilingual Mutual Information Based Adaptive Training for Neural Machine Translation
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).
Label Relation Graphs Enhanced Hierarchical Residual Network for Hierarchical Multi-Granularity Classification
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.
Solving Aspect Category Sentiment Analysis as a Text Generation Task
Aspect category sentiment analysis has attracted increasing research attention.
Spatio-temporal-spectral-angular observation model that integrates observations from UAV and mobile mapping vehicle for better urban mapping
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
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
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
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.
Template-Based Named Entity Recognition Using BART
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.
OFEI: A Semi-black-box Android Adversarial Sample Attack Framework Against DLaaS
With the growing popularity of Android devices, Android malware is seriously threatening the safety of users.
Unsupervised Sentiment Analysis by Transferring Multi-source Knowledge
The first mechanism is a selective domain adaptation (SDA) method, which transfers knowledge from the closest source domain.
CelebA-Spoof Challenge 2020 on Face Anti-Spoofing: Methods and Results
It is the largest face anti-spoofing dataset in terms of the numbers of the data and the subjects.
A hybrid deep-learning approach for complex biochemical named entity recognition
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.
Graph-Based Knowledge Integration for Question Answering over Dialogue
Despite many advances, existing approaches for this task did not consider dialogue structure and background knowledge (e. g., relationships between speakers).
Ranked #6 on
Question Answering
on FriendsQA
Natural Language Inference in Context -- Investigating Contextual Reasoning over Long Texts
Natural language inference (NLI) is a fundamental NLP task, investigating the entailment relationship between two texts.
How Does Context Matter? On the Robustness of Event Detection with Context-Selective Mask Generalization
Event detection (ED) aims to identify and classify event triggers in texts, which is a crucial subtask of event extraction (EE).
Singular equivalences induced by bimodules and quadratic monomial algebras
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
Machine reading is a fundamental task for testing the capability of natural language understanding, which is closely related to human cognition in many aspects.
Adversarial Training Based Multi-Source Unsupervised Domain Adaptation for Sentiment Analysis
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
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).
Learn to Forget: Machine Unlearning via Neuron Masking
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.
Real-time, Universal, and Robust Adversarial Attacks Against Speaker Recognition Systems
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.
Review and Examination of Input Feature Preparation Methods and Machine Learning Models for Turbulence Modeling
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
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.
Neural Cross-Lingual Event Detection with Minimal Parallel Resources
In this paper, we propose a new method for cross-lingual ED, demonstrating a minimal dependency on parallel resources.
Adversarial Attack on Skeleton-based Human Action Recognition
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.
Spearphone: A Speech Privacy Exploit via Accelerometer-Sensed Reverberations from Smartphone Loudspeakers
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
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
Then, we integrate the aesthetic features into a cross-domain network to transfer users' domain independent aesthetic preferences.
Biophysics at the coffee shop: lessons learned working with George Oster
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
We study the problem of multimodal generative modelling of images based on generative adversarial networks (GANs).
iQIYI-VID: A Large Dataset for Multi-modal Person Identification
Multi-modal person identification is a more promising way that we can jointly utilize face, head, body, audio features, and so on.
Faster super-resolution imaging with auto-correlation two-step deconvolution
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.
Optics
Event Detection via Gated Multilingual Attention Mechanism
In specific, to alleviate data scarcity problem, we exploit the consistent information in multilingual data via context attention mechanism.
Hierarchical Attention-Based Recurrent Highway Networks for Time Series Prediction
Time series prediction has been studied in a variety of domains.
Understanding Android Obfuscation Techniques: A Large-Scale Investigation in the Wild
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
Skepxels: Spatio-temporal Image Representation of Human Skeleton Joints for Action Recognition
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.
Defense against Universal Adversarial Perturbations
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.
Viewpoint Invariant Action Recognition using RGB-D Videos
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.
Learning Human Pose Models from Synthesized Data for Robust RGB-D Action Recognition
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.
Ranked #88 on
Skeleton Based Action Recognition
on NTU RGB+D
Improvement of training set structure in fusion data cleaning using Time-Domain Global Similarity method
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.
Preference-based performance measures for Time-Domain Global Similarity method
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.
Context-aware System Service Call-oriented Symbolic Execution of Android Framework with Application to Exploit Generation
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
