Search Results for author:
Found 220 papers, 77 papers with code
Prompt-Based Rule Discovery and Boosting for Interactive Weakly-Supervised Learning
Weakly-supervised learning (WSL) has shown promising results in addressing label scarcity on many NLP tasks, but manually designing a comprehensive, high-quality labeling rule set is tedious and difficult.
AcTune: Uncertainty-Based Active Self-Training for Active Fine-Tuning of Pretrained Language Models
We develop AcTune, a new framework that improves the label efficiency of active PLM fine-tuning by unleashing the power of unlabeled data via self-training.
Transferring SLU Models in Novel Domains
When building models for novel natural language domains, a major challenge is the lack of data in the new domains, no matter whether the data is annotated or not.
Neighborhood-Regularized Self-Training for Learning with Few Labels
Our further analysis demonstrates that our proposed data selection strategy reduces the noise of pseudo labels by 36. 8% and saves 57. 3% of the time when compared with the best baseline.
Fighting Malicious Media Data: A Survey on Tampering Detection and Deepfake Detection
Online media data, in the forms of images and videos, are becoming mainstream communication channels.
AL-iGAN: An Active Learning Framework for Tunnel Geological Reconstruction Based on TBM Operational Data
In tunnel boring machine (TBM) underground projects, an accurate description of the rock-soil types distributed in the tunnel can decrease the construction risk ({\it e. g.} surface settlement and landslide) and improve the efficiency of construction.
Direct-Effect Risk Minimization for Domain Generalization
We study the problem of out-of-distribution (o. o. d.)
End-to-End Stochastic Optimization with Energy-Based Model
Decision-focused learning (DFL) was recently proposed for stochastic optimization problems that involve unknown parameters.
Single-channel EEG completion using Cascade Transformer
It is easy for the electroencephalogram (EEG) signal to be incomplete due to packet loss, electrode falling off, etc.
Goal-Oriented Communications for the IoT and Application to Data Compression
Internet of Things (IoT) devices will play an important role in emerging applications, since their sensing, actuation, processing, and wireless communication capabilities stimulate data collection, transmission and decision processes of smart applications.
Distribution-based Emotion Recognition in Conversation
Automatic emotion recognition in conversation (ERC) is crucial for emotion-aware conversational artificial intelligence.
Unified End-to-End Speech Recognition and Endpointing for Fast and Efficient Speech Systems
In this work, we propose a method to jointly train the ASR and EP tasks in a single end-to-end (E2E) multitask model, improving EP quality by optionally leveraging information from the ASR audio encoder.
Learning Task-Aware Effective Brain Connectivity for fMRI Analysis with Graph Neural Networks
To better adapt GNNs for fMRI analysis, we propose TBDS, an end-to-end framework based on \underline{T}ask-aware \underline{B}rain connectivity \underline{D}AG (short for Directed Acyclic Graph) \underline{S}tructure generation for fMRI analysis.
Teacher-Student Network for 3D Point Cloud Anomaly Detection with Few Normal Samples
Moreover, our method only requires very few normal samples to train the student network due to the teacher-student distillation mechanism.
End-to-end Spoken Language Understanding with Tree-constrained Pointer Generator
Specifically, a tree-constrained pointer generator (TCPGen), a powerful and efficient biasing model component, is studied, which leverages a slot shortlist with corresponding entities to extract biasing lists.
RoChBert: Towards Robust BERT Fine-tuning for Chinese
Despite of the superb performance on a wide range of tasks, pre-trained language models (e. g., BERT) have been proved vulnerable to adversarial texts.
COCO-DR: Combating Distribution Shifts in Zero-Shot Dense Retrieval with Contrastive and Distributionally Robust Learning
We present a new zero-shot dense retrieval (ZeroDR) method, COCO-DR, to improve the generalization ability of dense retrieval by combating the distribution shifts between source training tasks and target scenarios.
Ranked #1 on
Zero-shot Text Search
on TREC-COVID
UnfoldML: Cost-Aware and Uncertainty-Based Dynamic 2D Prediction for Multi-Stage Classification
It achieves within 0. 1% accuracy from the highest-performing multi-class baseline, while saving close to 20X on spatio-temporal cost of inference and earlier (3. 5hrs) disease onset prediction.
ReSel: N-ary Relation Extraction from Scientific Text and Tables by Learning to Retrieve and Select
We study the problem of extracting N-ary relation tuples from scientific articles.
Pronunciation Generation for Foreign Language Words in Intra-Sentential Code-Switching Speech Recognition
In this paper, we make use of limited code-switching data as driving materials and explore a shortcut to quickly develop intra-sentential code-switching recognition skill on the commissioned native language acoustic model, where we propose a data-driven method to make the seed lexicon which is used to train grapheme-to-phoneme model to predict mapping pronunciations for foreign language word in code-switching sentences.
Multi-Objective Personalized Product Retrieval in Taobao Search
These problems promote us to further strengthen the capabilities of our EBR model in both relevance estimation and personalized retrieval.
Expediting Large-Scale Vision Transformer for Dense Prediction without Fine-tuning
Vision transformers have recently achieved competitive results across various vision tasks but still suffer from heavy computation costs when processing a large number of tokens.
Goal-Oriented Quantization: Analysis, Design, and Application to Resource Allocation
The task is modeled by the minimization problem of a general goal function $f(x;g)$ for which the decision $x$ has to be taken from a quantized version of the parameters $g$.
A general-purpose material property data extraction pipeline from large polymer corpora using Natural Language Processing
The ever-increasing number of materials science articles makes it hard to infer chemistry-structure-property relations from published literature.
Cold-Start Data Selection for Few-shot Language Model Fine-tuning: A Prompt-Based Uncertainty Propagation Approach
We propose PATRON, a new method that uses prompt-based uncertainty estimation for data selection for pre-trained language model fine-tuning under cold-start scenarios, i. e., no initial labeled data are available.
Context-Aware Query Rewriting for Improving Users' Search Experience on E-commerce Websites
The model subsequently calculates session representations by combining the contextual information with the instant search query using an aggregation network.
Streaming End-to-End Multilingual Speech Recognition with Joint Language Identification
Language identification is critical for many downstream tasks in automatic speech recognition (ASR), and is beneficial to integrate into multilingual end-to-end ASR as an additional task.
SaleNet: A low-power end-to-end CNN accelerator for sustained attention level evaluation using EEG
This paper proposes SaleNet - an end-to-end convolutional neural network (CNN) for sustained attention level evaluation using prefrontal electroencephalogram (EEG).
Turn-Taking Prediction for Natural Conversational Speech
This makes doing speech recognition with conversational speech, including one with multiple queries, a challenging task.
SciAnnotate: A Tool for Integrating Weak Labeling Sources for Sequence Labeling
Compared to frequently used text annotation tools, our annotation tool allows for the development of weak labels in addition to providing a manual annotation experience.
DETRs with Hybrid Matching
This end-to-end signature is important for the versatility of DETR, and it has been generalized to a wide range of visual problems, including instance/semantic segmentation, human pose estimation, and point cloud/multi-view-images based detection, etc.
Model-Aware Contrastive Learning: Towards Escaping Uniformity-Tolerance Dilemma in Training
It has been identified that the temperature $ \tau $ of CL loss plays an essential role in automatically concentrating on hard negative samples.
Tandem Multitask Training of Speaker Diarisation and Speech Recognition for Meeting Transcription
Self-supervised-learning-based pre-trained models for speech data, such as Wav2Vec 2. 0 (W2V2), have become the backbone of many speech tasks.
Learning Disentangled Representations for Controllable Human Motion Prediction
Specifically, the inductive bias imposed by the extra CVAE path encourages two latent variables in two paths to respectively govern separate representations for each partial-body motion.
Tree-constrained Pointer Generator with Graph Neural Network Encodings for Contextual Speech Recognition
Incorporating biasing words obtained as contextual knowledge is critical for many automatic speech recognition (ASR) applications.
Adaptive Multi-view Rule Discovery for Weakly-Supervised Compatible Products Prediction
We develop AMRule, a multi-view rule discovery framework that can (1) adaptively and iteratively discover novel rulers that can complement the current weakly-supervised model to improve compatibility prediction; (2) discover interpretable rules from both structured attribute tables and unstructured product descriptions.
Self-Supervised Consistent Quantization for Fully Unsupervised Image Retrieval
In global consistent quantization, we employ contrastive learning for both embedding and quantized representations and fuses these representations for consistent contrastive regularization between instances.
PROFHIT: Probabilistic Robust Forecasting for Hierarchical Time-series
We close both these gaps and propose PROFHIT, which is a fully probabilistic hierarchical forecasting model that jointly models forecast distribution of entire hierarchy.
Sparse Conditional Hidden Markov Model for Weakly Supervised Named Entity Recognition
Weakly supervised named entity recognition methods train label models to aggregate the token annotations of multiple noisy labeling functions (LFs) without seeing any manually annotated labels.
Named Entity Recognition
Weakly-Supervised Named Entity Recognition
Minimising Biasing Word Errors for Contextual ASR with the Tree-Constrained Pointer Generator
MBWE and BLMD further improved the effectiveness of TCPGen and achieved more significant WER reductions on the biasing words.
Revisiting PINNs: Generative Adversarial Physics-informed Neural Networks and Point-weighting Method
Physics-informed neural networks (PINNs) provide a deep learning framework for numerically solving partial differential equations (PDEs), and have been widely used in a variety of PDE problems.
CERES: Pretraining of Graph-Conditioned Transformer for Semi-Structured Session Data
User sessions empower many search and recommendation tasks on a daily basis.
FlowFormer: A Transformer Architecture for Optical Flow
We introduce optical Flow transFormer, dubbed as FlowFormer, a transformer-based neural network architecture for learning optical flow.
Ranked #1 on
Optical Flow Estimation
on Sintel-final
Learning a Structured Latent Space for Unsupervised Point Cloud Completion
Specifically, we map a series of related partial point clouds into multiple complete shape and occlusion code pairs and fuse the codes to obtain their representations in the unified latent space.
PRBoost: Prompt-Based Rule Discovery and Boosting for Interactive Weakly-Supervised Learning
Weakly-supervised learning (WSL) has shown promising results in addressing label scarcity on many NLP tasks, but manually designing a comprehensive, high-quality labeling rule set is tedious and difficult.
FORCE: A Framework of Rule-Based Conversational Recommender System
The conversational recommender systems (CRSs) have received extensive attention in recent years.
Abandoning the Bayer-Filter to See in the Dark
Next, a fully convolutional network is proposed to achieve the low-light image enhancement by fusing colored raw data with synthesized monochrome raw data.
Estimating the Uncertainty in Emotion Class Labels with Utterance-Specific Dirichlet Priors
In this paper, a novel Bayesian training loss based on per-utterance Dirichlet prior distributions is proposed for verbal emotion recognition, which models the uncertainty in one-hot labels created when human annotators assign the same utterance to different emotion classes.
Shift-Robust Node Classification via Graph Adversarial Clustering
Then a shift-robust classifier is optimized on training graph and adversarial samples on target graph, which are generated by cluster GNN.
Tail-GAN: Nonparametric Scenario Generation for Tail Risk Estimation
The estimation of loss distributions for dynamic portfolios requires the simulation of scenarios representing realistic joint dynamics of their components, with particular importance devoted to the simulation of tail risk scenarios.
UA-FedRec: Untargeted Attack on Federated News Recommendation
Our study reveals a critical security issue in existing federated news recommendation systems and calls for research efforts to address the issue.
A Survey on Programmatic Weak Supervision
Labeling training data has become one of the major roadblocks to using machine learning.
Volatility forecasting with machine learning and intraday commonality
We apply machine learning models to forecast intraday realized volatility (RV), by exploiting commonality in intraday volatility via pooling stock data together, and by incorporating a proxy for the market volatility.
SIGMA: A Structural Inconsistency Reducing Graph Matching Algorithm
In this paper, we propose a novel criterion to measure the graph matching accuracy, structural inconsistency (SI), which is defined based on the network topological structure.
Improving the fusion of acoustic and text representations in RNN-T
The recurrent neural network transducer (RNN-T) has recently become the mainstream end-to-end approach for streaming automatic speech recognition (ASR).
Towards Transferable Unrestricted Adversarial Examples with Minimum Changes
Extensive experiments verify the effectiveness of our framework on balancing imperceptibility and transferability of the crafted adversarial examples.
Recurring the Transformer for Video Action Recognition
Besides, the proposed RViT can work on both fixed-length and variant-length video clips properly without requiring large GPU memory thanks to the frame by frame processing flow.
Price Impact of Order Flow Imbalance: Multi-level, Cross-asset and Forecasting
Second, we examine the notion of cross-impact and show that, once the information from multiple levels is included in OFI, multi-asset models with cross-impact do not provide additional explanatory power for contemporaneous impact compared to a sparse model without cross-impact terms.
Supervised Multivariate Learning with Simultaneous Feature Auto-grouping and Dimension Reduction
In this paper, new information-theoretical limits are presented to reveal the intrinsic cost of seeking for clusters, as well as the blessing from dimensionality in multivariate learning.
AcTune: Uncertainty-aware Active Self-Training for Semi-Supervised Active Learning with Pretrained Language Models
We propose {\ours}, a new framework that leverages unlabeled data to improve the label efficiency of active PLM fine-tuning.
DPVI: A Dynamic-Weight Particle-Based Variational Inference Framework
We develop a general Dynamic-weight Particle-based Variational Inference (DPVI) framework according to a novel continuous composite flow, which evolves the positions and weights of particles simultaneously.
HRFormer: High-Resolution Vision Transformer for Dense Predict
We present a High-Resolution Transformer (HRFormer) that learns high-resolution representations for dense prediction tasks, in contrast to the original Vision Transformer that produces low-resolution representations and has high memory and computational cost.
PMSSC: Parallelizable Multi-Subset based Self-Expressive Model for Subspace Clustering
Subspace clustering methods embrace a self-expressive model that represents each data point as a linear combination of other data points in the dataset are powerful unsupervised learning techniques.
A Universal End-to-End Approach to Portfolio Optimization via Deep Learning
The designed framework circumvents the traditional forecasting step and avoids the estimation of the covariance matrix, lifting the bottleneck for generalizing to a large amount of instruments.
Soft Sensing Model Visualization: Fine-tuning Neural Network from What Model Learned
To understand how the proposed model works, the deep visualization approach is applied.
Diversity-Promoting Human Motion Interpolation via Conditional Variational Auto-Encoder
In this paper, we present a deep generative model based method to generate diverse human motion interpolation results.
Soft-Sensing ConFormer: A Curriculum Learning-based Convolutional Transformer
Over the last few decades, modern industrial processes have investigated several cost-effective methodologies to improve the productivity and yield of semiconductor manufacturing.
GraSSNet: Graph Soft Sensing Neural Networks
In the era of big data, data-driven based classification has become an essential method in smart manufacturing to guide production and optimize inspection.
Approximating Optimal Transport via Low-rank and Sparse Factorization
Optimal transport (OT) naturally arises in a wide range of machine learning applications but may often become the computational bottleneck.
Soft Sensing Transformer: Hundreds of Sensors are Worth a Single Word
We demonstrate the challenges and effectiveness of modeling industrial big data by a Soft Sensing Transformer model on these data sets.
Callee: Recovering Call Graphs for Binaries with Transfer and Contrastive Learning
Recovering binary programs' call graphs is crucial for inter-procedural analysis tasks and applications based on them. transfer One of the core challenges is recognizing targets of indirect calls (i. e., indirect callees).
Lightweight Mobile Automated Assistant-to-physician for Global Lower-resource Areas
Importance: Lower-resource areas in Africa and Asia face a unique set of healthcare challenges: the dual high burden of communicable and non-communicable diseases; a paucity of highly trained primary healthcare providers in both rural and densely populated urban areas; and a lack of reliable, inexpensive internet connections.
HRFormer: High-Resolution Transformer for Dense Prediction
We present a High-Resolution Transformer (HRFormer) that learns high-resolution representations for dense prediction tasks, in contrast to the original Vision Transformer that produces low-resolution representations and has high memory and computational cost.
Ranked #1 on
Pose Estimation
on AIC
Unrestricted Adversarial Attacks on ImageNet Competition
Many works have investigated the adversarial attacks or defenses under the settings where a bounded and imperceptible perturbation can be added to the input.
Input Length Matters: Improving RNN-T and MWER Training for Long-form Telephony Speech Recognition
Our experiments show that for both losses, the WER on long-form speech reduces substantially as the training utterance length increases.
CAMul: Calibrated and Accurate Multi-view Time-Series Forecasting
We use CAMul for multiple domains with varied sources and modalities and show that CAMul outperforms other state-of-art probabilistic forecasting models by over 25\% in accuracy and calibration.
Self-Training with Differentiable Teacher
In self-training, the student contributes to the prediction performance, and the teacher controls the training process by generating pseudo-labels.
Learning to Predict Diverse Human Motions from a Single Image via Mixture Density Networks
Human motion prediction, which plays a key role in computer vision, generally requires a past motion sequence as input.
Learning from Language Description: Low-shot Named Entity Recognition via Decomposed Framework
In this work, we study the problem of named entity recognition (NER) in a low resource scenario, focusing on few-shot and zero-shot settings.
Training Algorithm Matters for the Performance of Neural Network Potential: A Case Study of Adam and the Kalman Filter Optimizers
Here we compare the performance of two popular training algorithms, the adaptive moment estimation algorithm (Adam) and the Extended Kalman Filter algorithm (EKF), using the Behler-Parrinello neural network (BPNN) and two publicly accessible datasets of liquid water [Proc.
IEEE BigData 2021 Cup: Soft Sensing at Scale
The scope of this challenge is to tackle the task of classifying soft sensing data with machine learning techniques.
Tree-constrained Pointer Generator for End-to-end Contextual Speech Recognition
Contextual knowledge is important for real-world automatic speech recognition (ASR) applications.
Auto-encoder based Model for High-dimensional Imbalanced Industrial Data
However, the successful applications of deep learning in soft sensing are still not widely integrated in factory control systems, because most of the research on soft sensing do not have access to large scale industrial data which are varied, noisy and incomplete.
Towards Making Deep Learning-based Vulnerability Detectors Robust
Automatically detecting software vulnerabilities in source code is an important problem that has attracted much attention.
Adapting GPT, GPT-2 and BERT Language Models for Speech Recognition
Furthermore, on the AMI corpus, the proposed conversion for language prior probabilities enables BERT to obtain an extra 3% relative WERR, and the combination of BERT, GPT and GPT-2 results in further improvements.
Learning Efficient Vision Transformers via Fine-Grained Manifold Distillation
Specifically, we train a tiny student model to match a pre-trained teacher model in the patch-level manifold space.
Combining Frame-Synchronous and Label-Synchronous Systems for Speech Recognition
Commonly used automatic speech recognition (ASR) systems can be classified into frame-synchronous and label-synchronous categories, based on whether the speech is decoded on a per-frame or per-label basis.
MFR 2021: Masked Face Recognition Competition
These teams successfully submitted 18 valid solutions.
GAN-MDF: A Method for Multi-fidelity Data Fusion in Digital Twins
Multi-fidelity data fusion (MDF) methods aims to use massive LF samples and small amounts of HF samples to develop an accurate and efficient model for describing the system with a reasonable computation burden.
Positive-Unlabeled Data Purification in the Wild for Object Detection
In this paper, we present a positive-unlabeled learning based scheme to expand training data by purifying valuable images from massive unlabeled ones, where the original training data are viewed as positive data and the unlabeled images in the wild are unlabeled data.
Towards Transferable Adversarial Perturbations with Minimum Norm
In this work, we propose a \emph{geometry-aware framework} to generate transferable adversarial perturbation with minimum norm for each input.
Image Deformation Estimation via Multi-Objective Optimization
Specifically, by partitioning the template image into several regions and measuring the similarity of each region independently, multiple objectives are built and deformation estimation can thus be realized by solving the MOP with off-the-shelf multi-objective evolutionary algorithms (MOEAs).
When in Doubt: Neural Non-Parametric Uncertainty Quantification for Epidemic Forecasting
We model the forecasting task as a probabilistic generative process and propose a functional neural process model called EPIFNP, which directly models the probability density of the forecast value.
Decision-making Oriented Clustering: Application to Pricing and Power Consumption Scheduling
For this purpose, we formulate the framework of decision-making oriented clustering and propose an algorithm providing a decision-based partition of the data space and good representative decisions.
Efficient Cross-Device Federated Learning Algorithms for Minimax Problems
In many machine learning applications where massive and privacy-sensitive data are generated on numerous mobile or IoT devices, collecting data in a centralized location may be prohibitive.
BERTifying the Hidden Markov Model for Multi-Source Weakly Supervised Named Entity Recognition
To address this challenge, we propose a conditional hidden Markov model (CHMM), which can effectively infer true labels from multi-source noisy labels in an unsupervised way.
Generative Actor-Critic: An Off-policy Algorithm Using the Push-forward Model
Model-free deep reinforcement learning has achieved great success in many domains, such as video games, recommendation systems and robotic control tasks.
PanGu-$α$: Large-scale Autoregressive Pretrained Chinese Language Models with Auto-parallel Computation
To enhance the generalization ability of PanGu-$\alpha$, we collect 1. 1TB high-quality Chinese data from a wide range of domains to pretrain the model.
Ranked #1 on
Reading Comprehension (Zero-Shot)
on CMRC 2018
Cloze (multi-choices) (Few-Shot)
Cloze (multi-choices) (One-Shot)
+19
DeepfakeUCL: Deepfake Detection via Unsupervised Contrastive Learning
Extensive experiments show that our unsupervised learning method enables comparable detection performance to state-of-the-art supervised techniques, in both the intra- and inter-dataset settings.
Sketch-based Normal Map Generation with Geometric Sampling
This paper proposes a deep generative model for generating normal maps from users sketch with geometric sampling.
Analysis of the tradeoff between health and economic impacts of the Covid-19 epidemic
Should the measures be more (or less) restrictive?
Real-time Forecast Models for TBM Load Parameters Based on Machine Learning Methods
In this paper, based on in-situ TBM operational data, we use the machine-learning (ML) methods to build the real-time forecast models for TBM load parameters, which can instantaneously provide the future values of the TBM load parameters as long as the current data are collected.
A Riemannian smoothing steepest descent method for non-Lipschitz optimization on submanifolds
In this paper, we propose a Riemannian smoothing steepest descent method to minimize a nonconvex and non-Lipschitz function on submanifolds.
Semantic Scene Completion via Integrating Instances and Scene in-the-Loop
The key insight is that we decouple the instances from a coarsely completed semantic scene instead of a raw input image to guide the reconstruction of instances and the overall scene.
Ranked #1 on
3D Semantic Scene Completion
on NYUv2
A Distributed Optimisation Framework Combining Natural Gradient with Hessian-Free for Discriminative Sequence Training
This paper presents a novel natural gradient and Hessian-free (NGHF) optimisation framework for neural network training that can operate efficiently in a distributed manner.
Using Cognitive Models to Train Warm Start Reinforcement Learning Agents for Human-Computer Interactions
Reinforcement learning (RL) agents in human-computer interactions applications require repeated user interactions before they can perform well.
Multi-cell NOMA: Coherent Reconfigurable Intelligent Surfaces Model With Stochastic Geometry
Numerical results indicate that 1) although the interference from other cells is enhanced via the RISs, the performance of the RIS-aided user still enhances since the channel quality is strengthened more obviously; and 2) the SIC order can be altered by employing the RISs since the RISs improve the channel quality of the aided user.
Information Theory Information Theory
Self-Adaptive Training: Bridging Supervised and Self-Supervised Learning
We propose self-adaptive training -- a unified training algorithm that dynamically calibrates and enhances training processes by model predictions without incurring an extra computational cost -- to advance both supervised and self-supervised learning of deep neural networks.
Hybrid Quantum-Classical Graph Convolutional Network
This research provides a hybrid quantum-classical graph convolutional network (QGCNN) for learning HEP data.
Theory-based Habit Modeling for Enhancing Behavior Prediction
Psychological theories of habit posit that when a strong habit is formed through behavioral repetition, it can trigger behavior automatically in the same environment.
Quantum Convolutional Neural Networks for High Energy Physics Data Analysis
This work presents a quantum convolutional neural network (QCNN) for the classification of high energy physics events.
Partial Gromov-Wasserstein Learning for Partial Graph Matching
Graph matching finds the correspondence of nodes across two graphs and is a basic task in graph-based machine learning.
Deep Discriminative Feature Learning for Accent Recognition
Accent recognition with deep learning framework is a similar work to deep speaker identification, they're both expected to give the input speech an identifiable representation.
Improving Prosody Modelling with Cross-Utterance BERT Embeddings for End-to-end Speech Synthesis
Despite prosody is related to the linguistic information up to the discourse structure, most text-to-speech (TTS) systems only take into account that within each sentence, which makes it challenging when converting a paragraph of texts into natural and expressive speech.
Emotion recognition by fusing time synchronous and time asynchronous representations
In this paper, a novel two-branch neural network model structure is proposed for multimodal emotion recognition, which consists of a time synchronous branch (TSB) and a time asynchronous branch (TAB).
Calibrated Language Model Fine-Tuning for In- and Out-of-Distribution Data
Fine-tuned pre-trained language models can suffer from severe miscalibration for both in-distribution and out-of-distribution (OOD) data due to over-parameterization.
Combination of Deep Speaker Embeddings for Diarisation
Significant progress has recently been made in speaker diarisation after the introduction of d-vectors as speaker embeddings extracted from neural network (NN) speaker classifiers for clustering speech segments.
Probing and Fine-tuning Reading Comprehension Models for Few-shot Event Extraction
We argue that the event extraction models so trained are inherently label-hungry, and can generalize poorly across domains and text genres. We propose a reading comprehension framework for event extraction. Specifically, we formulate event detection as a textual entailment prediction problem, and argument detection as a question answer-ing problem.
COSEA: Convolutional Code Search with Layer-wise Attention
However, most existing studies overlook the code's intrinsic structural logic, which indeed contains a wealth of semantic information, and fails to capture intrinsic features of codes.
Fine-Tuning Pre-trained Language Model with Weak Supervision: A Contrastive-Regularized Self-Training Approach
To address this problem, we develop a contrastive self-training framework, COSINE, to enable fine-tuning LMs with weak supervision.
Ranked #1 on
Word Sense Disambiguation
on Words in Context
Text Classification Using Label Names Only: A Language Model Self-Training Approach
In this paper, we explore the potential of only using the label name of each class to train classification models on unlabeled data, without using any labeled documents.
Denoising Multi-Source Weak Supervision for Neural Text Classification
We study the problem of learning neural text classifiers without using any labeled data, but only easy-to-provide rules as multiple weak supervision sources.
SeqMix: Augmenting Active Sequence Labeling via Sequence Mixup
Our method, SeqMix, simply augments the queried samples by generating extra labeled sequences in each iteration.
Transformer-Based Neural Text Generation with Syntactic Guidance
We study the problem of using (partial) constituency parse trees as syntactic guidance for controlled text generation.
A Spherical Hidden Markov Model for Semantics-Rich Human Mobility Modeling
We propose SHMM, a multi-modal spherical hidden Markov model for semantics-rich human mobility modeling.
SumGNN: Multi-typed Drug Interaction Prediction via Efficient Knowledge Graph Summarization
Furthermore, most previous works focus on binary DDI prediction whereas the multi-typed DDI pharmacological effect prediction is a more meaningful but harder task.
Exploring the Hierarchy in Relation Labels for Scene Graph Generation
By assigning each relationship a single label, current approaches formulate the relationship detection as a classification problem.
Transfer Learning of Graph Neural Networks with Ego-graph Information Maximization
Graph neural networks (GNNs) have achieved superior performance in various applications, but training dedicated GNNs can be costly for large-scale graphs.
Example-based Color Transfer with Gaussian Mixture Modeling
In particular, we relate the transferred image with the example image under the Gaussian Mixture Model (GMM) and regard the transferred image color as the GMM centroids.
SDE-Net: Equipping Deep Neural Networks with Uncertainty Estimates
We propose a new method for quantifying uncertainties of DNNs from a dynamical system perspective.
A variational quantum algorithm for Hamiltonian diagonalization
To obtain the full spectrum of the Hamiltonian, we use a quantum imaginary time evolution algorithm with high temperature, which prepares a thermal state with a small correlation length.
Quantum Physics
Neural Kalman Filtering for Speech Enhancement
Statistical signal processing based speech enhancement methods adopt expert knowledge to design the statistical models and linear filters, which is complementary to the deep neural network (DNN) based methods which are data-driven.
Hierarchical Topic Mining via Joint Spherical Tree and Text Embedding
Mining a set of meaningful topics organized into a hierarchy is intuitively appealing since topic correlations are ubiquitous in massive text corpora.
Ranked #1 on
Topic Models
on NYT
Deep Patch-based Human Segmentation
3D human segmentation has seen noticeable progress in re-cent years.
BOND: BERT-Assisted Open-Domain Named Entity Recognition with Distant Supervision
We study the open-domain named entity recognition (NER) problem under distant supervision.
STEAM: Self-Supervised Taxonomy Expansion with Mini-Paths
We propose a self-supervised taxonomy expansion model named STEAM, which leverages natural supervision in the existing taxonomy for expansion.
Curating a COVID-19 data repository and forecasting county-level death counts in the United States
We use this data to develop predictions and corresponding prediction intervals for the short-term trajectory of COVID-19 cumulative death counts at the county-level in the United States up to two weeks ahead.
Partially-Typed NER Datasets Integration: Connecting Practice to Theory
While typical named entity recognition (NER) models require the training set to be annotated with all target types, each available datasets may only cover a part of them.
paper2repo: GitHub Repository Recommendation for Academic Papers
Motivated by this trend, we describe a novel item-item cross-platform recommender system, $\textit{paper2repo}$, that recommends relevant repositories on GitHub that match a given paper in an academic search system such as Microsoft Academic.
Spherically symmetric static black holes in Einstein-aether theory
In particular, we find that, out of the five non-trivial field equations, only three are independent, so the problem is well-posed, as now generically there are only three unknown functions, {$F(r), B(r), A(r)$, where $F$ and $B$ are metric coefficients, and $A$ describes the aether field.}
General Relativity and Quantum Cosmology Astrophysics of Galaxies High Energy Physics - Phenomenology High Energy Physics - Theory
SHX: Search History Driven Crossover for Real-Coded Genetic Algorithm
In evolutionary algorithms, genetic operators iteratively generate new offspring which constitute a potentially valuable set of search history.
Hit-Detector: Hierarchical Trinity Architecture Search for Object Detection
To this end, we propose a hierarchical trinity search framework to simultaneously discover efficient architectures for all components (i. e. backbone, neck, and head) of object detector in an end-to-end manner.
Self-Adaptive Training: beyond Empirical Risk Minimization
We propose self-adaptive training---a new training algorithm that dynamically corrects problematic training labels by model predictions without incurring extra computational cost---to improve generalization of deep learning for potentially corrupted training data.
G2MF-WA: Geometric Multi-Model Fitting with Weakly Annotated Data
The WA data can be naturally obtained in an interactive way for specific tasks, for example, in the case of homography estimation, one can easily annotate points on the same plane/object with a single label by observing the image.
Improved Large-margin Softmax Loss for Speaker Diarisation
Speaker diarisation systems nowadays use embeddings generated from speech segments in a bottleneck layer, which are needed to be discriminative for unseen speakers.
Multimodal Intelligence: Representation Learning, Information Fusion, and Applications
This review provides a comprehensive analysis of recent works on multimodal deep learning from three perspectives: learning multimodal representations, fusing multimodal signals at various levels, and multimodal applications.
Spherical Text Embedding
While text embeddings are typically learned in the Euclidean space, directional similarity is often more effective in tasks such as word similarity and document clustering, which creates a gap between the training stage and usage stage of text embedding.
Discriminative Neural Clustering for Speaker Diarisation
In this paper, we propose Discriminative Neural Clustering (DNC) that formulates data clustering with a maximum number of clusters as a supervised sequence-to-sequence learning problem.
Beyond Human Parts: Dual Part-Aligned Representations for Person Re-Identification
On the other hand, there still exist many useful contextual cues that do not fall into the scope of predefined human parts or attributes.
Ranked #57 on
Person Re-Identification
on DukeMTMC-reID
Efficient Projection-Free Online Methods with Stochastic Recursive Gradient
This paper focuses on projection-free methods for solving smooth Online Convex Optimization (OCO) problems.
Aggregated Gradient Langevin Dynamics
In this paper, we explore a general Aggregated Gradient Langevin Dynamics framework (AGLD) for the Markov Chain Monte Carlo (MCMC) sampling.
HiExpan: Task-Guided Taxonomy Construction by Hierarchical Tree Expansion
Taxonomies are of great value to many knowledge-rich applications.
FUSE: Multi-Faceted Set Expansion by Coherent Clustering of Skip-grams
In this paper, we study the task of multi-faceted set expansion, which aims to capture all semantic facets in the seed set and return multiple sets of entities, one for each semantic facet.
On Dimension-free Tail Inequalities for Sums of Random Matrices and Applications
We also develop the tail inequalities for matrix random series and matrix martingale difference sequence.
PiNN: A Python Library for Building Atomic Neural Networks of Molecules and Materials
Atomic neural networks (ANNs) constitute a class of machine learning methods for predicting potential energy surfaces and physico-chemical properties of molecules and materials.
Computational Physics Disordered Systems and Neural Networks Chemical Physics
Device-independent verification of Einstein-Podolsky-Rosen steering
If entanglement could be verified without any trust in the devices of observers, i. e., in a device-independent (DI) way, then unconditional security can be guaranteed for various quantum information tasks.
Quantum Physics
Decision Set Optimization and Energy-Efficient MIMO Communications
We propose a framework to find a good (finite) decision set which induces a minimal performance loss w. r. t.
Integrating Source-channel and Attention-based Sequence-to-sequence Models for Speech Recognition
This paper proposes a novel automatic speech recognition (ASR) framework called Integrated Source-Channel and Attention (ISCA) that combines the advantages of traditional systems based on the noisy source-channel model (SC) and end-to-end style systems using attention-based sequence-to-sequence models.
Discriminative Topic Mining via Category-Name Guided Text Embedding
We propose a new task, discriminative topic mining, which leverages a set of user-provided category names to mine discriminative topics from text corpora.
Orientation-aware Semantic Segmentation on Icosahedron Spheres
For the spherical domain, several methods recently adopt an icosahedron mesh, but systems are typically rotation invariant or require significant memory and parameters, thus enabling execution only at very low resolutions.
Ranked #14 on
Semantic Segmentation
on Stanford2D3D Panoramic
Interlaced Sparse Self-Attention for Semantic Segmentation
There are two successive attention modules each estimating a sparse affinity matrix.
Multi-scale Template Matching with Scalable Diversity Similarity in an Unconstrained Environment
We propose a novel multi-scale template matching method which is robust against both scaling and rotation in unconstrained environments.
Accelerating Primal Solution Findings for Mixed Integer Programs Based on Solution Prediction
In many applications, a similar MIP model is solved on a regular basis, maintaining remarkable similarities in model structures and solution appearances but differing in formulation coefficients.
Multi-Span Acoustic Modelling using Raw Waveform Signals
This paper proposes a novel multi-span structure for acoustic modelling based on the raw waveform with multiple streams of CNN input layers, each processing a different span of the raw waveform signal.
ADA-Tucker: Compressing Deep Neural Networks via Adaptive Dimension Adjustment Tucker Decomposition
Furthermore, we propose that weight tensors in networks with proper order and balanced dimension are easier to be compressed.
A gradual, semi-discrete approach to generative network training via explicit Wasserstein minimization
This paper provides a simple procedure to fit generative networks to target distributions, with the goal of a small Wasserstein distance (or other optimal transport costs).
Fragmentation of shells: An analogy with the crack formation in tree bark
We recognize that the fragmentation problem in shells is analogous to the cracking behavior of tree bark, and closed form solutions is obtained to describe the relationship between the expansion velocity and the number of necks with consideration of the strain rate dependent strength of the shell material.
Soft Condensed Matter Applied Physics
Decision-Oriented Communications: Application to Energy-Efficient Resource Allocation
In this paper, we introduce the problem of decision-oriented communications, that is, the goal of the source is to send the right amount of information in order for the intended destination to execute a task.
FrameRank: A Text Processing Approach to Video Summarization
In constructing the dataset, because of the subjectivity of user-generated video summarization, we manually annotate 25 summaries for each video, which are in total 1300 summaries.