Search Results for author:
Found 52 papers, 19 papers with code
Coding Textual Inputs Boosts the Accuracy of Neural Networks
Natural Language Processing (NLP) tasks are usually performed word by word on textual inputs.
Can Data Diversity Enhance Learning Generalization?
This paper introduces our Diversity Advanced Actor-Critic reinforcement learning (A2C) framework (DAAC) to improve the generalization and accuracy of Natural Language Processing (NLP).
Byte-based Multilingual NMT for Endangered Languages
We propose a byte-based multilingual neural machine translation system (BMNMT) to alleviate the representation bottleneck and improve translation performance in endangered languages.
Measuring Robustness for NLP
The quality of Natural Language Processing (NLP) models is typically measured by the accuracy or error rate of a predefined test set.
A Note on Bias to Complete
Minimizing social bias strengthens societal bonds, promoting shared understanding and better decision-making.
Changes by Butterflies: Farsighted Forecasting with Group Reservoir Transformer
In Chaos, a minor divergence between two initial conditions exhibits exponential amplification over time, leading to far-away outcomes, known as the butterfly effect.
Investigating Training Strategies and Model Robustness of Low-Rank Adaptation for Language Modeling in Speech Recognition
The use of low-rank adaptation (LoRA) with frozen pretrained language models (PLMs) has become increasing popular as a mainstream, resource-efficient modeling approach for memory-constrained hardware.
Dual-Modal Attention-Enhanced Text-Video Retrieval with Triplet Partial Margin Contrastive Learning
We thereby present a new Triplet Partial Margin Contrastive Learning (TPM-CL) module to construct partial order triplet samples by automatically generating fine-grained hard negatives for matched text-video pairs.
Ranked #4 on
Video Retrieval
on MSR-VTT-1kA
Beyond Semantics: Learning a Behavior Augmented Relevance Model with Self-supervised Learning
Drawing inspiration from this, we devise a novel Behavior Augmented Relevance Learning model for Alipay Search (BARL-ASe) that leverages neighbor queries of target item and neighbor items of target query to complement target query-item semantic matching.
Towards Integrated Traffic Control with Operating Decentralized Autonomous Organization
Furthermore, an operation algorithm is proposed regarding the issue of structural rigidity in DAO.
Copula Variational LSTM for High-dimensional Cross-market Multivariate Dependence Modeling
Our variational neural network WPVC-VLSTM models variational sequential dependence degrees and structures across multivariate time series by variational long short-term memory networks and regular vine copula.
PAD: Towards Principled Adversarial Malware Detection Against Evasion Attacks
To promote defense effectiveness, we propose a new mixture of attacks to instantiate PAD to enhance deep neural network-based measurements and malware detectors.
Human MotionFormer: Transferring Human Motions with Vision Transformers
In this paper, we propose Human MotionFormer, a hierarchical ViT framework that leverages global and local perceptions to capture large and subtle motion matching, respectively.
Extraction of cropland field parcels with high resolution remote sensing using multi-task learning
Parcel-level farmland information contains rich spatial distribution and boundary details, which is crucial for digital agriculture and agricultural resource surveys.
ConceptX: A Framework for Latent Concept Analysis
We use an unsupervised method to discover concepts learned in these models and enable a graphical interface for humans to generate explanations for the concepts.
SIT at MixMT 2022: Fluent Translation Built on Giant Pre-trained Models
This paper describes the Stevens Institute of Technology's submission for the WMT 2022 Shared Task: Code-mixed Machine Translation (MixMT).
Transferable Multi-Agent Reinforcement Learning with Dynamic Participating Agents
To tackle this problem, we propose a special network architecture with a few-shot learning algorithm that allows the number of agents to vary during centralized training.
Analyzing Encoded Concepts in Transformer Language Models
We propose a novel framework ConceptX, to analyze how latent concepts are encoded in representations learned within pre-trained language models.
Discovering Latent Concepts Learned in BERT
We address this limitation by discovering and analyzing latent concepts learned in neural network models in an unsupervised fashion and provide interpretations from the model's perspective.
Reinforcement Learning in the Wild: Scalable RL Dispatching Algorithm Deployed in Ridehailing Marketplace
In this study, a real-time dispatching algorithm based on reinforcement learning is proposed and for the first time, is deployed in large scale.
Action-guided 3D Human Motion Prediction
The ability of forecasting future human motion is important for human-machine interaction systems to understand human behaviors and make interaction.
Itinerary-aware Personalized Deep Matching at Fliggy
All orders in a user itinerary are learned as a whole, based on which the implicit travel intention of each user can be more accurately inferred.
Interpreting Criminal Charge Prediction and Its Algorithmic Bias via Quantum-Inspired Complex Valued Networks
Our analysis of the importance of each input feature shows the critical causal impact on decision-making, suggesting that criminal histories are statistically significant factors, while identifiers, such as race and age, are not.
Learning by Distillation: A Self-Supervised Learning Framework for Optical Flow Estimation
Then, a self-supervised learning framework is constructed: confident predictions from teacher models are served as annotations to guide the student model to learn optical flow for those less confident predictions.
Grouping Words with Semantic Diversity
Deep Learning-based NLP systems can be sensitive to unseen tokens and hard to learn with high-dimensional inputs, which critically hinder learning generalization.
Few-Shot Human Motion Transfer by Personalized Geometry and Texture Modeling
We present a new method for few-shot human motion transfer that achieves realistic human image generation with only a small number of appearance inputs.
A Novel Graph-based Computation Offloading Strategy for Workflow Applications in Mobile Edge Computing
To achieve better Quality of Service (QoS), for instance, faster response time and lower energy consumption, computation offloading is widely used in the MEC environment.
Edge-computing
Distributed, Parallel, and Cluster Computing
C.2.4
Learning 3D Face Reconstruction with a Pose Guidance Network
We present a self-supervised learning approach to learning monocular 3D face reconstruction with a pose guidance network (PGN).
Flow2Stereo: Effective Self-Supervised Learning of Optical Flow and Stereo Matching
In this paper, we propose a unified method to jointly learn optical flow and stereo matching.
A Clustering Framework for Lexical Normalization of Roman Urdu
Roman Urdu is an informal form of the Urdu language written in Roman script, which is widely used in South Asia for online textual content.
Diversity by Phonetics and its Application in Neural Machine Translation
We achieve significant and consistent improvements overall language pairs and datasets: French-English, German-English, and Chinese-English in medium task IWSLT'17 and French-English in large task WMT'18 Bio, with up to 4 BLEU points over the state-of-the-art.
Adversarial Defense via Local Flatness Regularization
In this paper, we define the local flatness of the loss surface as the maximum value of the chosen norm of the gradient regarding to the input within a neighborhood centered on the benign sample, and discuss the relationship between the local flatness and adversarial vulnerability.
Learning to Solve a Rubik's Cube with a Dexterous Hand
We present a learning-based approach to solving a Rubik's cube with a multi-fingered dexterous hand.
Robotics
CUNY-PKU Parser at SemEval-2019 Task 1: Cross-Lingual Semantic Parsing with UCCA
This paper describes the systems of the CUNY-PKU team in SemEval 2019 Task 1: Cross-lingual Semantic Parsing with UCCA.
DHER: Hindsight Experience Replay for Dynamic Goals
Dealing with sparse rewards is one of the most important challenges in reinforcement learning (RL), especially when a goal is dynamic (e. g., to grasp a moving object).
SelFlow: Self-Supervised Learning of Optical Flow
We present a self-supervised learning approach for optical flow.
Ranked #7 on
Optical Flow Estimation
on KITTI 2012
DDFlow: Learning Optical Flow with Unlabeled Data Distillation
We present DDFlow, a data distillation approach to learning optical flow estimation from unlabeled data.
Hunter NMT System for WMT18 Biomedical Translation Task: Transfer Learning in Neural Machine Translation
Furthermore, we applied ensemble learning on training models of intermediate epochs and achieved an improvement of 4. 02 BLEU points over the baseline.
Assessing Quality Estimation Models for Sentence-Level Prediction
This paper provides an evaluation of a wide range of advanced sentence-level Quality Estimation models, including Support Vector Regression, Ride Regression, Neural Networks, Gaussian Processes, Bayesian Neural Networks, Deep Kernel Learning and Deep Gaussian Processes.
Learning to See in the Dark
Imaging in low light is challenging due to low photon count and low SNR.
Ranked #4 on
Image Denoising
on SID x300
Fast Image Processing with Fully-Convolutional Networks
Our approach uses a fully-convolutional network that is trained on input-output pairs that demonstrate the operator's action.
Accurate Optical Flow via Direct Cost Volume Processing
We present an optical flow estimation approach that operates on the full four-dimensional cost volume.
Radial Velocity Retrieval for Multichannel SAR Moving Targets with Time-Space Doppler De-ambiguity
Accordingly, the multichannel SAR systems with different parameters are investigated in three different cases with diverse Doppler ambiguity properties, and a multi-frequency SAR is then proposed to obtain the RV estimation by solving the ambiguity problem based on Chinese remainder theorem (CRT).
Learning to Segment Under Various Forms of Weak Supervision
Despite the promising performance of conventional fully supervised algorithms, semantic segmentation has remained an important, yet challenging task.
Gaze-Enabled Egocentric Video Summarization via Constrained Submodular Maximization
Motivated by these applications, this paper focuses on the problem of egocentric video summarization.
Phrase Based Language Model For Statistical Machine Translation
We consider phrase based Language Models (LM), which generalize the commonly used word level models.
Converting Instance Checking to Subsumption: A Rethink for Object Queries over Practical Ontologies
Efficiently querying Description Logic (DL) ontologies is becoming a vital task in various data-intensive DL applications.
Tell Me What You See and I will Show You Where It Is
We tackle the problem of weakly labeled semantic segmentation, where the only source of annotation are image tags encoding which classes are present in the scene.
Incorporating User Interaction and Topological Constraints within Contour Completion via Discrete Calculus
We study the problem of interactive segmentation and contour completion for multiple objects.
Extract ABox Modules for Efficient Ontology Querying
The extraction of logically-independent fragments out of an ontology ABox can be useful for solving the tractability problem of querying ontologies with large ABoxes.
