Search Results for author:
Found 82 papers, 29 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.
TermMind: Alibaba’s WMT21 Machine Translation Using Terminologies Task Submission
We used tags to mark and add the term translations into the matched sentences.
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.
Tele-FLM Technical Report
Large language models (LLMs) have showcased profound capabilities in language understanding and generation, facilitating a wide array of applications.
The Hallucinations Leaderboard -- An Open Effort to Measure Hallucinations in Large Language Models
Large Language Models (LLMs) have transformed the Natural Language Processing (NLP) landscape with their remarkable ability to understand and generate human-like text.
Tensor-based Graph Learning with Consistency and Specificity for Multi-view Clustering
In the context of multi-view clustering, graph learning is recognized as a crucial technique, which generally involves constructing an adaptive neighbor graph based on probabilistic neighbors, and then learning a consensus graph to for clustering.
Multi-Scale Subgraph Contrastive Learning
By an experimental analysis, we discover the semantic information of an augmented graph structure may be not consistent as original graph structure, and whether two augmented graphs are positive or negative pairs is highly related with the multi-scale structures.
Towards Optimal Customized Architecture for Heterogeneous Federated Learning with Contrastive Cloud-Edge Model Decoupling
To address these issues, we propose a novel federated learning framework called FedCMD, a model decoupling tailored to the Cloud-edge supported federated learning that separates deep neural networks into a body for capturing shared representations in Cloud and a personalized head for migrating data heterogeneity.
Analysing The Impact of Sequence Composition on Language Model Pre-Training
In this work, we find that applying causal masking can lead to the inclusion of distracting information from previous documents during pre-training, which negatively impacts the performance of the models on language modelling and downstream tasks.
StableMask: Refining Causal Masking in Decoder-only Transformer
The decoder-only Transformer architecture with causal masking and relative position encoding (RPE) has become the de facto choice in language modeling.
Nonlinear subspace clustering by functional link neural networks
Additionally, we introduce a convex combination subspace clustering scheme, which combining a linear subspace clustering method with the functional link neural network subspace clustering approach.
Sophisticated Behavioral Simulation: A Possible Solution to Problems of Organized Complexity
As a matter of facts, they act as the best tool to handle problems in complex systems where closed-form expressions are unavailable and the target distribution in the representation space is too complex to be fully represented by data-driven learning models, such as deep learning (DL) models.
TeleChat Technical Report
Subsequently, the model undergoes fine-tuning to align with human preferences, following a detailed methodology that we describe.
Structured Packing in LLM Training Improves Long Context Utilization
Recent developments in long-context large language models have attracted considerable attention.
Improving Neural Machine Translation by Multi-Knowledge Integration with Prompting
In this work, we focus on how to integrate multi-knowledge, multiple types of knowledge, into NMT models to enhance the performance with prompting.
Generating Progressive Images from Pathological Transitions via Diffusion Model
Deep learning is widely applied in computer-aided pathological diagnosis, which alleviates the pathologist workload and provide timely clinical analysis.
WATUNet: A Deep Neural Network for Segmentation of Volumetric Sweep Imaging Ultrasound
Volume sweep imaging (VSI) is an innovative approach that enables untrained operators to capture high-quality ultrasound images.
PuzzleTuning: Explicitly Bridge Pathological and Natural Image with Puzzles
Pathological image analysis is a crucial field in computer vision.
CPIA Dataset: A Comprehensive Pathological Image Analysis Dataset for Self-supervised Learning Pre-training
This paper presents the comprehensive pathological image analysis (CPIA) dataset, a large-scale SSL pre-training dataset combining 103 open-source datasets with extensive standardization.
Taming Gradient Variance in Federated Learning with Networked Control Variates
To address this, we introduce a novel Networked Control Variates (FedNCV) framework for Federated Learning.
Synslator: An Interactive Machine Translation Tool with Online Learning
Interactive machine translation (IMT) has emerged as a progression of the computer-aided translation paradigm, where the machine translation system and the human translator collaborate to produce high-quality translations.
Constructing Holistic Spatio-Temporal Scene Graph for Video Semantic Role Labeling
A scene-event mapping mechanism is first designed to bridge the gap between the underlying scene structure and the high-level event semantic structure, resulting in an overall hierarchical scene-event (termed ICE) graph structure.
Revisiting Disentanglement and Fusion on Modality and Context in Conversational Multimodal Emotion Recognition
On the other hand, during the feature fusion stage, we propose a Contribution-aware Fusion Mechanism (CFM) and a Context Refusion Mechanism (CRM) for multimodal and context integration, respectively.
Ranked #5 on
Emotion Recognition in Conversation
on IEMOCAP
A Noisy-Label-Learning Formulation for Immune Repertoire Classification and Disease-Associated Immune Receptor Sequence Identification
Immune repertoire classification, a typical multiple instance learning (MIL) problem, is a frontier research topic in computational biology that makes transformative contributions to new vaccines and immune therapies.
DNAGPT: A Generalized Pre-trained Tool for Versatile DNA Sequence Analysis Tasks
Pre-trained large language models demonstrate potential in extracting information from DNA sequences, yet adapting to a variety of tasks and data modalities remains a challenge.
Mining Interest Trends and Adaptively Assigning SampleWeight for Session-based Recommendation
Session-based Recommendation (SR) aims to predict users' next click based on their behavior within a short period, which is crucial for online platforms.
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.
From Alignment to Entailment: A Unified Textual Entailment Framework for Entity Alignment
Our approach captures the unified correlation pattern of two kinds of information between entities, and explicitly models the fine-grained interaction between original entity information.
Generating Visual Spatial Description via Holistic 3D Scene Understanding
With an external 3D scene extractor, we obtain the 3D objects and scene features for input images, based on which we construct a target object-centered 3D spatial scene graph (Go3D-S2G), such that we model the spatial semantics of target objects within the holistic 3D scenes.
Diffusion Models in NLP: A Survey
Diffusion models have become a powerful family of deep generative models, with record-breaking performance in many applications.
Optimizing Audio Recommendations for the Long-Term: A Reinforcement Learning Perspective
We study the problem of optimizing a recommender system for outcomes that occur over several weeks or months.
CellMix: A General Instance Relationship based Method for Data Augmentation Towards Pathology Image Classification
In pathology image analysis, obtaining and maintaining high-quality annotated samples is an extremely labor-intensive task.
Causal conditional hidden Markov model for multimodal traffic prediction
Recent works overemphasize spatio-temporal correlations of traffic flow, ignoring the physical concepts that lead to the generation of observations and their causal relationship.
Spatio-temporal neural structural causal models for bike flow prediction
In addition, due to the disturbance of incomplete observations in the data, random contextual conditions lead to spurious correlations between data and features, making the prediction of the model ineffective in special scenarios.
Graph Learning and Its Advancements on Large Language Models: A Holistic Survey
Different from previous surveys on graph learning, we provide a holistic review that analyzes current works from the perspective of graph structure, and discusses the latest applications, trends, and challenges in graph learning.
A Comprehensive Survey on Enterprise Financial Risk Analysis from Big Data Perspective
In contrast, this paper attempts to provide a systematic literature survey of enterprise risk analysis approaches from Big Data perspective, which reviews more than 250 representative articles in the past almost 50 years (from 1968 to 2023).
ESIE-BERT: Enriching Sub-words Information Explicitly with BERT for Joint Intent Classification and SlotFilling
We address the problem by introducing a novel joint method on top of BERT which explicitly models the multiple sub-tokens features after wordpiece tokenization, thereby contributing to the two tasks.
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.
Learning with Noisy Labels over Imbalanced Subpopulations
Then, we refurbish the noisy labels using the estimated clean probabilities and the pseudo-labels from the model's predictions.
Easy Guided Decoding in Providing Suggestions for Interactive Machine Translation
Human translators perform post editing on machine translations to correct errors in the scene of computer aided translation.
An Efficient Memory-Augmented Transformer for Knowledge-Intensive NLP Tasks
Experiments on various knowledge-intensive tasks such as question answering and dialogue datasets show that, simply augmenting parametric models (T5-base) using our method produces more accurate results (e. g., 25. 8 -> 44. 3 EM on NQ) while retaining a high throughput (e. g., 1000 queries/s on NQ).
Ranked #4 on
Question Answering
on KILT: ELI5
Visual Spatial Description: Controlled Spatial-Oriented Image-to-Text Generation
Accordingly, we manually annotate a dataset to facilitate the investigation of the newly-introduced task and build several benchmark encoder-decoder models by using VL-BART and VL-T5 as backbones.
MoSE: Modality Split and Ensemble for Multimodal Knowledge Graph Completion
Based on these embeddings, in the inference phase, we first make modality-split predictions and then exploit various ensemble methods to combine the predictions with different weights, which models the modality importance dynamically.
Overcoming Language Priors in Visual Question Answering via Distinguishing Superficially Similar Instances
In this work, we define the training instances with the same question type but different answers as \textit{superficially similar instances}, and attribute the language priors to the confusion of VQA model on such instances.
Shuffle Instances-based Vision Transformer for Pancreatic Cancer ROSE Image Classification
The rapid on-site evaluation (ROSE) technique can signifi-cantly accelerate the diagnosis of pancreatic cancer by im-mediately analyzing the fast-stained cytopathological images.
Mobility-Aware Cooperative Caching in Vehicular Edge Computing Based on Asynchronous Federated and Deep Reinforcement Learning
In addition, we consider the mobility of vehicles and propose a deep reinforcement learning algorithm to obtain the optimal cooperative caching location for the predicted popular contents in order to optimize the content transmission delay.
Time-Dependent Performance Modeling for Platooning Communications at Intersection
In this paper, we construct the time-dependent model to evaluate the platooning communication performance at the intersection based on the initial movement characteristics.
ReMix: A General and Efficient Framework for Multiple Instance Learning based Whole Slide Image Classification
We evaluate ReMix on two public datasets with two state-of-the-art MIL methods.
MSDF: A General Open-Domain Multi-Skill Dialog Framework
In this paper, we propose a general Multi-Skill Dialog Framework, namely MSDF, which can be applied in different dialog tasks (e. g. knowledge grounded dialog and persona based dialog).
Medical Dialogue Response Generation with Pivotal Information Recalling
To mitigate this problem, we propose a medical response generation model with Pivotal Information Recalling (MedPIR), which is built on two components, i. e., knowledge-aware dialogue graph encoder and recall-enhanced generator.
Combining Intra-Risk and Contagion Risk for Enterprise Bankruptcy Prediction Using Graph Neural Networks
This study for the first time considers both types of risk and their joint effects in bankruptcy prediction.
Stock Movement Prediction Based on Bi-typed Hybrid-relational Market Knowledge Graph via Dual Attention Networks
Stock Movement Prediction (SMP) aims at predicting listed companies' stock future price trend, which is a challenging task due to the volatile nature of financial markets.
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.
MSHT: Multi-stage Hybrid Transformer for the ROSE Image Analysis of Pancreatic Cancer
Pancreatic cancer is one of the most malignant cancers in the world, which deteriorates rapidly with very high mortality.
Learning Bi-typed Multi-relational Heterogeneous Graph via Dual Hierarchical Attention Networks
To address this issue, we propose a novel Dual Hierarchical Attention Networks (DHAN) based on the bi-typed multi-relational heterogeneous graphs to learn comprehensive node representations with the intra-class and inter-class attention-based encoder under a hierarchical mechanism.
Improving Human-Object Interaction Detection via Phrase Learning and Label Composition
Human-Object Interaction (HOI) detection is a fundamental task in high-level human-centric scene understanding.
Fast Electromagnetic Validations of Large-Scale Digital Coding Metasurfaces Accelerated by Recurrence Rebuild and Retrieval Method
The recurrence rebuild and retrieval method (R3M) is proposed in this paper to accelerate the electromagnetic (EM) validations of large-scale digital coding metasurfaces (DCMs).
Deep Keyphrase Completion
Keyphrase provides accurate information of document content that is highly compact, concise, full of meanings, and widely used for discourse comprehension, organization, and text retrieval.
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).
GlyphCRM: Bidirectional Encoder Representation for Chinese Character with its Glyph
Previous works indicate that the glyph of Chinese characters contains rich semantic information and has the potential to enhance the representation of Chinese characters.
End-to-End Human Object Interaction Detection with HOI Transformer
We propose HOI Transformer to tackle human object interaction (HOI) detection in an end-to-end manner.
Ranked #30 on
Human-Object Interaction Detection
on HICO-DET
(using extra training data)
Differentiable Channel Sparsity Search via Weight Sharing within Filters
Experimental results of semantic segmentation and image super resolution indicate that task-specific search achieves better performance than transferring slim models, demonstrating the wide applicability and high efficiency of DCSS.
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.
Connecting Embeddings for Knowledge Graph Entity Typing
In this paper, we propose a novel approach for KG entity typing which is trained by jointly utilizing local typing knowledge from existing entity type assertions and global triple knowledge from KGs.
Feedback Graph Attention Convolutional Network for Medical Image Enhancement
To well exploit global structural information and texture details, we propose a novel biomedical image enhancement network, named Feedback Graph Attention Convolutional Network (FB-GACN).
Predicting Lymph Node Metastasis Using Histopathological Images Based on Multiple Instance Learning With Deep Graph Convolution
In this paper, we propose a multiple instance learning method based on deep graph convolutional network and feature selection (FS-GCN-MIL) for histopathological image classification.
Graph-augmented Convolutional Networks on Drug-Drug Interactions Prediction
We propose an end-to-end model to predict drug-drug interactions (DDIs) by employing graph-augmented convolutional networks.
Nonconvex Nonsmooth Low-Rank Minimization for Generalized Image Compressed Sensing via Group Sparse Representation
The popular L_2-norm and M-estimator are employed for standard image CS and robust CS problem to fit the data respectively.
SmartBullets: A Cloud-Assisted Bullet Screen Filter based on Deep Learning
Although the bullet-screen video websites have provided filter functions based on regular expression, bad bullets can still easily pass the filter through making a small modification.
ADMM-IDNN: Iteratively Double-reweighted Nuclear Norm Algorithm for Group-prior based Nonconvex Compressed Sensing via ADMM
Group-prior based regularization method has led to great successes in various image processing tasks, which can usually be considered as a low-rank matrix minimization problem.
Image and Video Processing
SCEF: A Support-Confidence-aware Embedding Framework for Knowledge Graph Refinement
Knowledge graph (KG) refinement mainly aims at KG completion and correction (i. e., error detection).
Identifying the Best Machine Learning Algorithms for Brain Tumor Segmentation, Progression Assessment, and Overall Survival Prediction in the BRATS Challenge
This study assesses the state-of-the-art machine learning (ML) methods used for brain tumor image analysis in mpMRI scans, during the last seven instances of the International Brain Tumor Segmentation (BraTS) challenge, i. e., 2012-2018.
Hierarchical multi-class segmentation of glioma images using networks with multi-level activation function
Based on the same start-of-the-art network architecture, the accuracy of nested-class (enhancing tumor) is reasonably improved from 69% to 72% compared with the traditional Softmax-based method which blind to topological prior.
A novel active learning framework for classification: using weighted rank aggregation to achieve multiple query criteria
The proposed method serves as a heuristic means to select high-value samples of high scalability and generality and is implemented through a three-step process: (1) the transformation of the sample selection to sample ranking and scoring, (2) the computation of the self-adaptive weights of each criterion, and (3) the weighted aggregation of each sample rank list.
Modeling 4D fMRI Data via Spatio-Temporal Convolutional Neural Networks (ST-CNN)
Simultaneous modeling of the spatio-temporal variation patterns of brain functional network from 4D fMRI data has been an important yet challenging problem for the field of cognitive neuroscience and medical image analysis.
A Robust AUC Maximization Framework with Simultaneous Outlier Detection and Feature Selection for Positive-Unlabeled Classification
The positive-unlabeled (PU) classification is a common scenario in real-world applications such as healthcare, text classification, and bioinformatics, in which we only observe a few samples labeled as "positive" together with a large volume of "unlabeled" samples that may contain both positive and negative samples.
Fast and Scalable Distributed Deep Convolutional Autoencoder for fMRI Big Data Analytics
In recent years, analyzing task-based fMRI (tfMRI) data has become an essential tool for understanding brain function and networks.
Deep Residual Bidir-LSTM for Human Activity Recognition Using Wearable Sensors
Human activity recognition (HAR) has become a popular topic in research because of its wide application.
Applying Deep Bidirectional LSTM and Mixture Density Network for Basketball Trajectory Prediction
In the hit-or-miss classification experiment, the proposed model outperformed other models in terms of the convergence speed and accuracy.
Neural Headline Generation with Sentence-wise Optimization
Recently, neural models have been proposed for headline generation by learning to map documents to headlines with recurrent neural networks.
Intrinsically Motivated Learning of Visual Motion Perception and Smooth Pursuit
We extend the framework of efficient coding, which has been used to model the development of sensory processing in isolation, to model the development of the perception/action cycle.
