Search Results for author:
Found 99 papers, 28 papers with code
QEMind: Alibaba’s Submission to the WMT21 Quality Estimation Shared Task
Quality Estimation, as a crucial step of quality control for machine translation, has been explored for years.
Alibaba’s Submission for the WMT 2020 APE Shared Task: Improving Automatic Post-Editing with Pre-trained Conditional Cross-Lingual BERT
We also apply an imitation learning strategy to augment a reasonable amount of pseudo APE training data, potentially preventing the model to overfit on the limited real training data and boosting the performance on held-out data.
DelibGAN: Coarse-to-Fine Text Generation via Adversarial Network
In this paper, we propose a novel adversarial learning framework, namely DelibGAN, for generating high-quality sentences without supervision.
TermMind: Alibaba’s WMT21 Machine Translation Using Terminologies Task Submission
We used tags to mark and add the term translations into the matched sentences.
Disambiguated Lexically Constrained Neural Machine Translation
Lexically constrained neural machine translation (LCNMT), which controls the translation generation with pre-specified constraints, is important in many practical applications.
Non-parametric, Nearest-neighbor-assisted Fine-tuning for Neural Machine Translation
We explore whether such non-parametric models can improve machine translation models at the fine-tuning stage by incorporating statistics from the kNN predictions to inform the gradient updates for a baseline translation model.
Curricular Object Manipulation in LiDAR-based Object Detection
For the loss design, we propose the COMLoss to dynamically predict object-level difficulties and emphasize objects of different difficulties based on training stages.
Gated Mechanism Enhanced Multi-Task Learning for Dialog Routing
Although most existing methods can fulfil this requirement, they can only model single-source dialog data and cannot effectively capture the underlying knowledge of relations among data and subtasks.
Augment and Criticize: Exploring Informative Samples for Semi-Supervised Monocular 3D Object Detection
In this paper, we improve the challenging monocular 3D object detection problem with a general semi-supervised framework.
Contrastive Self-supervised Learning in Recommender Systems: A Survey
We then introduce a taxonomy based on the key components of the framework, including view generation strategy, contrastive task, and contrastive objective.
Demystifying What Code Summarization Models Learned
Based on these findings, we present two example uses of the formal definition of patterns: a new method for evaluating the robustness and a new technique for improving the accuracy of code summarization models.
Grid-Centric Traffic Scenario Perception for Autonomous Driving: A Comprehensive Review
Grid-centric perception is a crucial field for mobile robot perception and navigation.
Semi-supervised Parametric Real-world Image Harmonization
Learning-based image harmonization techniques are usually trained to undo synthetic random global transformations applied to a masked foreground in a single ground truth photo.
Disentangled Representation for Causal Mediation Analysis
Causal mediation analysis is a method that is often used to reveal direct and indirect effects.
FusionMotion: Multi-Sensor Asynchronous Fusion for Continuous Occupancy Prediction via Neural-ODE
This paper investigates multi-sensor spatio-temporal fusion strategies for continuous occupancy prediction in a systematic manner.
OAMatcher: An Overlapping Areas-based Network for Accurate Local Feature Matching
Local feature matching is an essential component in many visual applications.
DeepMatcher: A Deep Transformer-based Network for Robust and Accurate Local Feature Matching
In this work, we propose DeepMatcher, a deep Transformer-based network built upon our investigation of local feature matching in detector-free methods.
Poly-PC: A Polyhedral Network for Multiple Point Cloud Tasks at Once
In this work, we show that it is feasible to perform multiple tasks concurrently on point cloud with a straightforward yet effective multi-task network.
ResGrad: Residual Denoising Diffusion Probabilistic Models for Text to Speech
Denoising Diffusion Probabilistic Models (DDPMs) are emerging in text-to-speech (TTS) synthesis because of their strong capability of generating high-fidelity samples.
High-fidelity Direct Contrast Synthesis from Magnetic Resonance Fingerprinting
Here we propose a supervised learning-based method that directly synthesizes contrast-weighted images from the MRF data without going through the quantitative mapping and spin-dynamics simulation.
Magnetic Resonance Fingerprinting
Vocal Bursts Intensity Prediction
TSMind: Alibaba and Soochow University's Submission to the WMT22 Translation Suggestion Task
The leader board finally shows that our submissions are ranked first in three of four language directions in the Naive TS task of the WMT22 Translation Suggestion task.
Easy Guided Decoding in Providing Suggestions for Interactive Machine Translation
Fully machine translation scarcely guarantees error-free results.
Structured Knowledge Distillation Towards Efficient and Compact Multi-View 3D Detection
Detecting 3D objects from multi-view images is a fundamental problem in 3D computer vision.
Spatiotemporal Classification with limited labels using Constrained Clustering for large datasets
Using this large unlabelled dataset, we first show how a spatiotemporal representation is better compared to just spatial or temporal representation.
CLAD: A Contrastive Learning based Approach for Background Debiasing
Convolutional neural networks (CNNs) have achieved superhuman performance in multiple vision tasks, especially image classification.
Monolith: Real Time Recommendation System With Collisionless Embedding Table
In this paper, we present Monolith, a system tailored for online training.
Disentangled Representation with Causal Constraints for Counterfactual Fairness
Much research has been devoted to the problem of learning fair representations; however, they do not explicitly the relationship between latent representations.
On how to avoid exacerbating spurious correlations when models are overparameterized
Overparameterized models fail to generalize well in the presence of data imbalance even when combined with traditional techniques for mitigating imbalances.
Artificial Intelligence Techniques for Next-Generation Mega Satellite Networks
This article introduces the application of AI techniques for integrated terrestrial satellite networks, particularly mega satellite network communications.
Analyzing the Adoption Challenges of the Internet of Things (IoT) and Artificial Intelligence (AI) for Smart Cities in China
However, the adoption of AI and the IoT in developing countries has some challenges.
Experimental quantum adversarial learning with programmable superconducting qubits
Our results reveal experimentally a crucial vulnerability aspect of quantum learning systems under adversarial scenarios and demonstrate an effective defense strategy against adversarial attacks, which provide a valuable guide for quantum artificial intelligence applications with both near-term and future quantum devices.
i-Razor: A Neural Input Razor for Feature Selection and Dimension Search in Large-Scale Recommender Systems
Typically, feature selection and embedding dimension search are optimized sequentially, i. e., feature selection is performed first, followed by embedding dimension search to determine the optimal dimension size for each selected feature.
XYLayoutLM: Towards Layout-Aware Multimodal Networks For Visually-Rich Document Understanding
Recently, various multimodal networks for Visually-Rich Document Understanding(VRDU) have been proposed, showing the promotion of transformers by integrating visual and layout information with the text embeddings.
InferGrad: Improving Diffusion Models for Vocoder by Considering Inference in Training
In this paper, we propose InferGrad, a diffusion model for vocoder that incorporates inference process into training, to reduce the inference iterations while maintaining high generation quality.
Systematic analysis reveals key microRNAs as diagnostic and prognostic factors in progressive stages of lung cancer
MicroRNAs play an indispensable role in numerous biological processes ranging from organismic development to tumor progression. In oncology, these microRNAs constitute a fundamental regulation role in the pathology of cancer that provides the basis for probing into the influences on clinical features through transcriptome data.
QEMind: Alibaba's Submission to the WMT21 Quality Estimation Shared Task
Quality Estimation, as a crucial step of quality control for machine translation, has been explored for years.
Differentially Private Ensemble Classifiers for Data Streams
Learning from continuous data streams via classification/regression is prevalent in many domains.
Subtle Data Crimes: Naively training machine learning algorithms could lead to overly-optimistic results
We demonstrate this phenomenon for inverse problem solvers and show how their biased performance stems from hidden data preprocessing pipelines.
Beyond Glass-Box Features: Uncertainty Quantification Enhanced Quality Estimation for Neural Machine Translation
Quality Estimation (QE) plays an essential role in applications of Machine Translation (MT).
High Fidelity Deep Learning-based MRI Reconstruction with Instance-wise Discriminative Feature Matching Loss
By adding an additional loss function on the low-dimensional feature space during training, the reconstruction frameworks from under-sampled or corrupted data can reproduce more realistic images that are closer to the original with finer textures, sharper edges, and improved overall image quality.
Benign Overfitting in Multiclass Classification: All Roads Lead to Interpolation
The literature on "benign overfitting" in overparameterized models has been mostly restricted to regression or binary classification; however, modern machine learning operates in the multiclass setting.
Bridging the Domain Gap: Improve Informal Language Translation via Counterfactual Domain Adaptation
Despite the near-human performances already achieved on formal texts such as news articles, neural machine transla- tion still has difficulty in dealing with ”user-generated” texts that have diverse linguistic phenomena but lack large-scale high-quality parallel corpora.
Learning Gaussian Graphical Models with Latent Confounders
In this paper, we compare and contrast two strategies for inference in graphical models with latent confounders: Gaussian graphical models with latent variables (LVGGM) and PCA-based removal of confounding (PCA+GGM).
Mapping the phase diagram of the quantum anomalous Hall and topological Hall effects in a dual-gated magnetic topological insulator heterostructure
We use magnetotransport in dual-gated magnetic topological insulator heterostructures to map out a phase diagram of the topological Hall and quantum anomalous Hall effects as a function of the chemical potential (primarily determined by the back gate voltage) and the asymmetric potential (primarily determined by the top gate voltage).
Mesoscale and Nanoscale Physics
OUTCOMES: Rapid Under-sampling Optimization achieves up to 50% improvements in reconstruction accuracy for multi-contrast MRI sequences
Multi-contrast Magnetic Resonance Imaging (MRI) acquisitions from a single scan have tremendous potential to streamline exams and reduce imaging time.
Memory-efficient Learning for High-Dimensional MRI Reconstruction
Deep learning (DL) based unrolled reconstructions have shown state-of-the-art performance for under-sampled magnetic resonance imaging (MRI).
WheaCha: A Method for Explaining the Predictions of Models of Code
Attribution methods have emerged as a popular approach to interpreting model predictions based on the relevance of input features.
Echelon: Two-Tier Malware Detection for Raw Executables to Reduce False Alarms
Existing malware detection approaches suffer from a simplistic trade-off between false positive rate (FPR) and true positive rate (TPR) due to a single tier classification approach, where the two measures adversely affect one another.
Salient Bundle Adjustment for Visual SLAM
Recently, the philosophy of visual saliency and attention has started to gain popularity in the robotics community.
Saliency Prediction
Robotics
Sample-Efficient Reinforcement Learning via Counterfactual-Based Data Augmentation
We propose counterfactual RL algorithms to learn both population-level and individual-level policies.
Binary Classification of Gaussian Mixtures: Abundance of Support Vectors, Benign Overfitting and Regularization
Combining the two, we present novel sufficient conditions on the covariance spectrum and on the signal-to-noise ratio (SNR) under which interpolating estimators achieve asymptotically optimal performance as overparameterization increases.
Adversarial Text Generation via Sequence Contrast Discrimination
In this paper, we propose a sequence contrast loss driven text generation framework, which learns the difference between real texts and generated texts and uses that difference.
Assessing Classifier Fairness with Collider Bias
The increasing application of machine learning techniques in everyday decision-making processes has brought concerns about the fairness of algorithmic decision-making.
Computer Assisted Translation with Neural Quality Estimation and Automatic Post-Editing
With the advent of neural machine translation, there has been a marked shift towards leveraging and consuming the machine translation results.
Approaches, Challenges, and Applications for Deep Visual Odometry: Toward to Complicated and Emerging Areas
Visual odometry (VO) is a prevalent way to deal with the relative localization problem, which is becoming increasingly mature and accurate, but it tends to be fragile under challenging environments.
Revisiting Adversarially Learned Injection Attacks Against Recommender Systems
Recommender systems play an important role in modern information and e-commerce applications.
A Design of Cooperative Overtaking Based on Complex Lane Detection and Collision Risk Estimation
Cooperative overtaking is believed to have the capability of improving road safety and traffic efficiency by means of the real-time information exchange between traffic participants, including road infrastructures, nearby vehicles and others.
CG-SENSE revisited: Results from the first ISMRM reproducibility challenge
The reference implementations were in good agreement, both visually and in terms of image similarity metrics.
A feature-supervised generative adversarial network for environmental monitoring during hazy days
First, pairs of hazy and clean images are used as inputs to supervise the encoding process and obtain high-quality feature maps.
On the Generalizability of Neural Program Models with respect to Semantic-Preserving Program Transformations
With the prevalence of publicly available source code repositories to train deep neural network models, neural program models can do well in source code analysis tasks such as predicting method names in given programs that cannot be easily done by traditional program analysis techniques.
Time-aware Graph Embedding: A temporal smoothness and task-oriented approach
Knowledge graph embedding, which aims to learn the low-dimensional representations of entities and relationships, has attracted considerable research efforts recently.
Robust and Accurate Authorship Attribution via Program Normalization
To address these emerging issues, we formulate this security challenge into a general threat model, the $\textit{relational adversary}$, that allows an arbitrary number of the semantics-preserving transformations to be applied to an input in any problem space.
Relative Pose Estimation for Stereo Rolling Shutter Cameras
In this paper, we present a novel linear algorithm to estimate the 6 DoF relative pose from consecutive frames of stereo rolling shutter (RS) cameras.
Learning Semantic Program Embeddings with Graph Interval Neural Network
We have also created a neural bug detector based on GINN to catch null pointer deference bugs in Java code.
Robust Visual Object Tracking with Two-Stream Residual Convolutional Networks
Inspired by the human "visual tracking" capability which leverages motion cues to distinguish the target from the background, we propose a Two-Stream Residual Convolutional Network (TS-RCN) for visual tracking, which successfully exploits both appearance and motion features for model update.
HOPPITY: LEARNING GRAPH TRANSFORMATIONS TO DETECT AND FIX BUGS IN PROGRAMS
We present a learning-based approach to detect and fix a broad range of bugs in Javascript programs.
CF2-Net: Coarse-to-Fine Fusion Convolutional Network for Breast Ultrasound Image Segmentation
Breast ultrasound (BUS) image segmentation plays a crucial role in a computer-aided diagnosis system, which is regarded as a useful tool to help increase the accuracy of breast cancer diagnosis.
The Differentially Private Lottery Ticket Mechanism
We propose the differentially private lottery ticket mechanism (DPLTM).
IStego100K: Large-scale Image Steganalysis Dataset
We hope that this test set can help to evaluate the robustness of steganalysis algorithms.
SEED RL: Scalable and Efficient Deep-RL with Accelerated Central Inference
We present a modern scalable reinforcement learning agent called SEED (Scalable, Efficient Deep-RL).
AI Benchmark: All About Deep Learning on Smartphones in 2019
The performance of mobile AI accelerators has been evolving rapidly in the past two years, nearly doubling with each new generation of SoCs.
Differentially Private Survival Function Estimation
Survival function estimation is used in many disciplines, but it is most common in medical analytics in the form of the Kaplan-Meier estimator.
Winning Privately: The Differentially Private Lottery Ticket Mechanism
We propose the differentially private lottery ticket mechanism (DPLTM).
Testing Neural Program Analyzers
Deep neural networks have been increasingly used in software engineering and program analysis tasks.
Learning a Static Bug Finder from Data
In a cross-project prediction task, three neural bug detectors we instantiate from NeurSA are effective in catching null pointer dereference, array index out of bound and class cast bugs in unseen code.
Learning Blended, Precise Semantic Program Embeddings
Learning on the same set of functions (more than 170K in total), \liger significantly outperforms code2seq, the previous state-of-the-art for method name prediction.
Controllable Unsupervised Text Attribute Transfer via Editing Entangled Latent Representation
Unsupervised text attribute transfer automatically transforms a text to alter a specific attribute (e. g. sentiment) without using any parallel data, while simultaneously preserving its attribute-independent content.
COSET: A Benchmark for Evaluating Neural Program Embeddings
Neural program embedding can be helpful in analyzing large software, a task that is challenging for traditional logic-based program analyses due to their limited scalability.
Learning Scalable and Precise Representation of Program Semantics
Neural program embedding has shown potential in aiding the analysis of large-scale, complicated software.
Machine Learning for Classification of Protein Helix Capping Motifs
The biological function of a protein stems from its 3-dimensional structure, which is thermodynamically determined by the energetics of interatomic forces between its amino acid building blocks (the order of amino acids, known as the sequence, defines a protein).
How Training Data Affect the Accuracy and Robustness of Neural Networks for Image Classification
In light of a recent study on the mutual influence between robustness and accuracy over 18 different ImageNet models, this paper investigates how training data affect the accuracy and robustness of deep neural networks.
Enhanced Expressive Power and Fast Training of Neural Networks by Random Projections
The key in our proof is that random projections embed stably the set of sparse vectors or a low-dimensional smooth manifold into a low-dimensional subspace.
AI Benchmark: Running Deep Neural Networks on Android Smartphones
Over the last years, the computational power of mobile devices such as smartphones and tablets has grown dramatically, reaching the level of desktop computers available not long ago.
Ranking Distillation: Learning Compact Ranking Models With High Performance for Recommender System
We propose a KD technique for learning to rank problems, called \emph{ranking distillation (RD)}.
Personalized Top-N Sequential Recommendation via Convolutional Sequence Embedding
Top-$N$ sequential recommendation models each user as a sequence of items interacted in the past and aims to predict top-$N$ ranked items that a user will likely interact in a `near future'.
Reconstruction and Registration of Large-Scale Medical Scene Using Point Clouds Data from Different Modalities
In this paper, we proposed a method which can fuse different modalities 3D data to get a large-scale and dense point cloud.
Empirical Evaluation of Speaker Adaptation on DNN based Acoustic Model
Speaker adaptation aims to estimate a speaker specific acoustic model from a speaker independent one to minimize the mismatch between the training and testing conditions arisen from speaker variabilities.
Investigating Generative Adversarial Networks based Speech Dereverberation for Robust Speech Recognition
First, we study the effectiveness of different dereverberation networks (the generator in GAN) and find that LSTM leads a significant improvement as compared with feed-forward DNN and CNN in our dataset.
Matrices with Gaussian noise: optimal estimates for singular subspace perturbation
In this paper, we prove a stochastic version of the Davis--Kahan--Wedin $\sin \Theta$ theorem when the perturbation is a Gaussian random matrix.
Recovering Loss to Followup Information Using Denoising Autoencoders
Loss to followup is a significant issue in healthcare and has serious consequences for a study's validity and cost.
Dynamic Neural Program Embeddings for Program Repair
Our evaluation results show that the semantic program embeddings significantly outperform the syntactic program embeddings based on token sequences and abstract syntax trees.
Dynamic Neural Program Embedding for Program Repair
Evaluation results show that our new semantic program embedding significantly outperforms the syntactic program embeddings based on token sequences and abstract syntax trees.
Interactive, Intelligent Tutoring for Auxiliary Constructions in Geometry Proofs
Although there exist many intelligent tutoring systems proposed for geometry proofs, few teach students how to find auxiliary constructions.
MIDA: Multiple Imputation using Denoising Autoencoders
Missing data is a significant problem impacting all domains.
Detailed Garment Recovery from a Single-View Image
Most recent garment capturing techniques rely on acquiring multiple views of clothing, which may not always be readily available, especially in the case of pre-existing photographs from the web.
Domain Transfer Multi-Instance Dictionary Learning
We assume we already have a well-trained multi-instance dictionary and its corresponding classifier from the source domain, which can be used to represent and classify the bags.
Minimal Solvers for 3D Geometry From Satellite Imagery
We propose two novel minimal solvers which advance the state of the art in satellite imagery processing.
Stereo under Sequential Optimal Sampling: A Statistical Analysis Framework for Search Space Reduction
We develop a sequential optimal sampling framework for stereo disparity estimation by adapting the Sequential Probability Ratio Test (SPRT) model.
