Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation

Abstract

In this paper, we propose a novel neural network model called RNN Encoder-Decoder that consists of two recurrent neural networks (RNN). One RNN encodes a sequence of symbols into a fixed-length vector representation, and the other decodes the representation into another sequence of symbols. The encoder and decoder of the proposed model are jointly trained to maximize the conditional probability of a target sequence given a source sequence. The performance of a statistical machine translation system is empirically found to improve by using the conditional probabilities of phrase pairs computed by the RNN Encoder-Decoder as an additional feature in the existing log-linear model. Qualitatively, we show that the proposed model learns a semantically and syntactically meaningful representation of linguistic phrases.

EMNLP 2014

References in corpus (3)

• Distributed Representations of Words and Phrases and their Compositionality
• ADADELTA: An Adaptive Learning Rate Method
• Exact solutions to the nonlinear dynamics of learning in deep linear neural networks

Cited by in corpus (966)

• A Survey on Deep Learning in Medical Image Analysis
• Neural Machine Translation by Jointly Learning to Align and Translate
• Sequence to Sequence Learning with Neural Networks
• Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting
• Convolutional Sequence to Sequence Learning
• Deep Learning for Anomaly Detection: A Survey
• xDeepFM: Combining Explicit and Implicit Feature Interactions for Recommender Systems
• MAGNN: Metapath Aggregated Graph Neural Network for Heterogeneous Graph Embedding
• Character-Aware Neural Language Models
• Mixed Precision Training
• Deep Audio-Visual Speech Recognition
• A Theoretically Grounded Application of Dropout in Recurrent Neural Networks
• Deep Learning in Medical Image Registration: A Review
• A C-LSTM Neural Network for Text Classification
• Convolutional Recurrent Neural Networks for Polyphonic Sound Event Detection
• Dual Learning for Machine Translation
• Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges
• Deep Reinforcement Learning: An Overview
• On Using Monolingual Corpora in Neural Machine Translation
• From Softmax to Sparsemax: A Sparse Model of Attention and Multi-Label Classification
• Gated Graph Sequence Neural Networks
• Deep Speaker: an End-to-End Neural Speaker Embedding System
• End-to-end Continuous Speech Recognition using Attention-based Recurrent NN: First Results
• Deep Learning and its Application to LHC Physics
• Artificial neural networks for neuroscientists: A primer
• A Dual-Stage Attention-Based Recurrent Neural Network for Time Series Prediction
• Hello Edge: Keyword Spotting on Microcontrollers
• GAN-Leaks: A Taxonomy of Membership Inference Attacks against Generative Models
• Modulating early visual processing by language
• Fine-grained Analysis of Sentence Embeddings Using Auxiliary Prediction Tasks
• ChemTS: An Efficient Python Library for de novo Molecular Generation
• Graph-Based Deep Learning for Medical Diagnosis and Analysis: Past, Present and Future
• A Neural Network Architecture Combining Gated Recurrent Unit (GRU) and Support Vector Machine (SVM) for Intrusion Detection in Network Traffic Data
• Incorporating Copying Mechanism in Sequence-to-Sequence Learning
• Neural Relational Inference for Interacting Systems
• Exploration by Random Network Distillation
• Image Captioning with Semantic Attention
• Fi-GNN: Modeling Feature Interactions via Graph Neural Networks for CTR Prediction
• A Simple, Fast Diverse Decoding Algorithm for Neural Generation
• One-Shot Imitation Learning
• Online and Linear-Time Attention by Enforcing Monotonic Alignments
• An Actor-Critic Algorithm for Sequence Prediction
• RETAIN: An Interpretable Predictive Model for Healthcare using Reverse Time Attention Mechanism
• Towards End-to-End Prosody Transfer for Expressive Speech Synthesis with Tacotron
• Learning a Multi-View Stereo Machine
• Deep Voice 2: Multi-Speaker Neural Text-to-Speech
• Demystifying Parallel and Distributed Deep Learning: An In-Depth Concurrency Analysis
• Learning Stochastic Recurrent Networks
• Understanding and mitigating gradient pathologies in physics-informed neural networks
• Abnormal respiratory patterns classifier may contribute to large-scale screening of people infected with COVID-19 in an accurate and unobtrusive manner
• FiLM: Visual Reasoning with a General Conditioning Layer
• Describing Videos by Exploiting Temporal Structure
• Contextual LSTM (CLSTM) models for Large scale NLP tasks
• Long Short-Term Memory-Networks for Machine Reading
• Evaluating the State-of-the-Art of End-to-End Natural Language Generation: The E2E NLG Challenge
• On Extended Long Short-term Memory and Dependent Bidirectional Recurrent Neural Network
• Order Matters: Sequence to sequence for sets
• Data Noising as Smoothing in Neural Network Language Models
• SMILES Transformer: Pre-trained Molecular Fingerprint for Low Data Drug Discovery
• Reinforcement Learning for Solving the Vehicle Routing Problem
• GRU-ODE-Bayes: Continuous modeling of sporadically-observed time series
• The NLP Cookbook: Modern Recipes for Transformer based Deep Learning Architectures
• Variational Recurrent Auto-Encoders
• Machine Learning for Intelligent Optical Networks: A Comprehensive Survey
• Modeling Coverage for Neural Machine Translation
• A Label Attention Model for ICD Coding from Clinical Text
• What-and-Where to Match: Deep Spatially Multiplicative Integration Networks for Person Re-identification
• Time series forecasting of new cases and new deaths rate for COVID-19 using deep learning methods
• dna2vec: Consistent vector representations of variable-length k-mers
• Delving Deeper into Convolutional Networks for Learning Video Representations
• Training recurrent neural networks robust to incomplete data: application to Alzheimer's disease progression modeling
• Unified Quality Assessment of In-the-Wild Videos with Mixed Datasets Training
• Real-Time Fruit Recognition and Grasping Estimation for Autonomous Apple Harvesting
• Exploring Sparsity in Recurrent Neural Networks
• Weighted Transformer Network for Machine Translation
• Scalable Gradients for Stochastic Differential Equations
• Sharp Minima Can Generalize For Deep Nets
• Meta-modeling game for deriving theoretical-consistent, micro-structural-based traction-separation laws via deep reinforcement learning
• Stabilizing Transformers for Reinforcement Learning
• Image-Grounded Conversations: Multimodal Context for Natural Question and Response Generation
• Can neural machine translation do simultaneous translation?
• Supervised and Semi-Supervised Text Categorization using LSTM for Region Embeddings
• Lifelong Sequential Modeling with Personalized Memorization for User Response Prediction
• Deep Reinforcement Learning with Shallow Controllers: An Experimental Application to PID Tuning
• Adversarial Feature Matching for Text Generation
• Multilogue-Net: A Context Aware RNN for Multi-modal Emotion Detection and Sentiment Analysis in Conversation
• Neural Language Correction with Character-Based Attention
• Boosting Continuous Sign Language Recognition via Cross Modality Augmentation
• Learning Intrinsic Sparse Structures within Long Short-Term Memory
• Streaming keyword spotting on mobile devices
• Emotional Chatting Machine: Emotional Conversation Generation with Internal and External Memory
• Style Transfer as Unsupervised Machine Translation
• TimeNet: Pre-trained deep recurrent neural network for time series classification
• Sequence-based Dynamic Handwriting Analysis for Parkinson's Disease Detection with One-dimensional Convolutions and BiGRUs
• Imagination improves Multimodal Translation
• Hardware Acceleration of Sparse and Irregular Tensor Computations of ML Models: A Survey and Insights
• Going in circles is the way forward: the role of recurrence in visual inference
• Sequence Learning with RNNs for Medical Concept Normalization in User-Generated Texts
• Adversarial Generation of Natural Language
• Investigating Capsule Networks with Dynamic Routing for Text Classification
• Learning General Purpose Distributed Sentence Representations via Large Scale Multi-task Learning
• Actor-Critic Sequence Training for Image Captioning
• Mutual Information and Diverse Decoding Improve Neural Machine Translation
• Block-Sparse Recurrent Neural Networks
• Artificial Neural Networks-Based Machine Learning for Wireless Networks: A Tutorial
• Black-Box Attacks against RNN based Malware Detection Algorithms
• Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering
• A Comparison of Transformer and Recurrent Neural Networks on Multilingual Neural Machine Translation
• R-Transformer: Recurrent Neural Network Enhanced Transformer
• LSTM-Based System-Call Language Modeling and Robust Ensemble Method for Designing Host-Based Intrusion Detection Systems
• CharBERT: Character-aware Pre-trained Language Model
• On the Bottleneck of Graph Neural Networks and its Practical Implications
• On the Origin of Deep Learning
• Forward Attention in Sequence-to-sequence Acoustic Modelling for Speech Synthesis
• Learning Longer-term Dependencies in RNNs with Auxiliary Losses
• D-VAE: A Variational Autoencoder for Directed Acyclic Graphs
• Video Paragraph Captioning Using Hierarchical Recurrent Neural Networks
• The Pitfalls of Simplicity Bias in Neural Networks
• Artificial Neural Networks for Photonic Applications: From Algorithms to Implementation
• OpenNMT: Neural Machine Translation Toolkit
• Efficient Summarization with Read-Again and Copy Mechanism
• Unsupervised Cross-Modal Alignment of Speech and Text Embedding Spaces
• Story Generation from Sequence of Independent Short Descriptions
• Not all bytes are equal: Neural byte sieve for fuzzing
• Deep Learning Inference in Facebook Data Centers: Characterization, Performance Optimizations and Hardware Implications
• Neural Reverse Engineering of Stripped Binaries using Augmented Control Flow Graphs
• On-line Active Reward Learning for Policy Optimisation in Spoken Dialogue Systems
• Collaborative Recurrent Autoencoder: Recommend while Learning to Fill in the Blanks
• Deeply learning molecular structure-property relationships using attention- and gate-augmented graph convolutional network
• Toward Subgraph-Guided Knowledge Graph Question Generation with Graph Neural Networks
• Ultralow complexity long short-term memory network for fiber nonlinearity mitigation in coherent optical communication systems
• Temporal processing and context dependency in C. elegans mechanosensation
• Chinese Song Iambics Generation with Neural Attention-based Model
• Towards Building an Intelligent Anti-Malware System: A Deep Learning Approach using Support Vector Machine (SVM) for Malware Classification
• Combating Fake News: A Survey on Identification and Mitigation Techniques
• A Tutorial on Deep Learning for Music Information Retrieval
• ProtTrans: Towards Cracking the Language of Life's Code Through Self-Supervised Deep Learning and High Performance Computing
• The unreasonable effectiveness of the forget gate
• Feedforward Sequential Memory Networks: A New Structure to Learn Long-term Dependency
• Data-driven prognostics based on time-frequency analysis and symbolic recurrent neural network for fuel cells under dynamic load
• Modeling Global and Local Node Contexts for Text Generation from Knowledge Graphs
• KERMIT: Generative Insertion-Based Modeling for Sequences
• Iterative Refinement Graph Neural Network for Antibody Sequence-Structure Co-design
• Improving performance of recurrent neural network with relu nonlinearity
• Stochastic Latent Actor-Critic: Deep Reinforcement Learning with a Latent Variable Model
• Bridging the Gap between Stochastic Gradient MCMC and Stochastic Optimization
• An Evaluation of Trajectory Prediction Approaches and Notes on the TrajNet Benchmark
• Revisiting the poverty of the stimulus: hierarchical generalization without a hierarchical bias in recurrent neural networks
• EdgeDRNN: Recurrent Neural Network Accelerator for Edge Inference
• Graph Neural Ordinary Differential Equations
• Distraction-Based Neural Networks for Document Summarization
• Neural Machine Translation with Reconstruction
• A Deep Learning Approach for Forecasting Air Pollution in South Korea Using LSTM
• Optimizing Speech Recognition For The Edge
• On Multiplicative Integration with Recurrent Neural Networks
• Topic-Guided Variational Autoencoders for Text Generation
• Robust Multimodal Learning with Missing Modalities via Parameter-Efficient Adaptation
• Gram-CTC: Automatic Unit Selection and Target Decomposition for Sequence Labelling
• TDAM: a Topic-Dependent Attention Model for Sentiment Analysis
• Neural Text Generation: Past, Present and Beyond
• Forecast Network-Wide Traffic States for Multiple Steps Ahead: A Deep Learning Approach Considering Dynamic Non-Local Spatial Correlation and Non-Stationary Temporal Dependency
• Imposing higher-level Structure in Polyphonic Music Generation using Convolutional Restricted Boltzmann Machines and Constraints
• Time2Vec: Learning a Vector Representation of Time
• Encoding Source Language with Convolutional Neural Network for Machine Translation
• Learning to Decode for Future Success
• Local Monotonic Attention Mechanism for End-to-End Speech and Language Processing
• WAF-A-MoLE: Evading Web Application Firewalls through Adversarial Machine Learning
• Ithemal: Accurate, Portable and Fast Basic Block Throughput Estimation using Deep Neural Networks
• Zero-Resource Knowledge-Grounded Dialogue Generation
• Structured Sequence Modeling with Graph Convolutional Recurrent Networks
• A Deep Learning Approach for Active Anomaly Detection of Extragalactic Transients
• Text Recognition in the Wild: A Survey
• End-to-End Tracking and Semantic Segmentation Using Recurrent Neural Networks
• Looking at Outfit to Parse Clothing
• Advances in Quantum Deep Learning: An Overview
• Ask Me Anything: Free-form Visual Question Answering Based on Knowledge from External Sources
• Exploiting BERT for End-to-End Aspect-based Sentiment Analysis
• EEG-Based Emotion Recognition Using Regularized Graph Neural Networks
• YouTube-BoundingBoxes: A Large High-Precision Human-Annotated Data Set for Object Detection in Video
• Learning Video Object Segmentation with Visual Memory
• Neural Based Statement Classification for Biased Language
• DNA-Level Splice Junction Prediction using Deep Recurrent Neural Networks
• Revisiting Activation Regularization for Language RNNs
• Hierarchical Recurrent Neural Encoder for Video Representation with Application to Captioning
• Tensor Programs I: Wide Feedforward or Recurrent Neural Networks of Any Architecture are Gaussian Processes
• Generating Text with Deep Reinforcement Learning
• Speech Prediction using an Adaptive Recurrent Neural Network with Application to Packet Loss Concealment
• Mixed-Precision Training for NLP and Speech Recognition with OpenSeq2Seq
• Tree-structured multi-stage principal component analysis (TMPCA): theory and applications
• Long-Term Human Motion Prediction by Modeling Motion Context and Enhancing Motion Dynamic
• Embedding Word Similarity with Neural Machine Translation
• Anomalous Jet Identification via Sequence Modeling
• Implicit Distortion and Fertility Models for Attention-based Encoder-Decoder NMT Model
• Evaluating prose style transfer with the Bible
• Recent advances in conversational NLP : Towards the standardization of Chatbot building
• When, Where, and What? A New Dataset for Anomaly Detection in Driving Videos
• Mental Task Classification Using Electroencephalogram Signal
• Factorized Multimodal Transformer for Multimodal Sequential Learning
• SketchyGAN: Towards Diverse and Realistic Sketch to Image Synthesis
• NavFormer: A Transformer Architecture for Robot Target-Driven Navigation in Unknown and Dynamic Environments
• Learning to Play Guess Who? and Inventing a Grounded Language as a Consequence
• Skip RNN: Learning to Skip State Updates in Recurrent Neural Networks
• Multimodal Attention for Neural Machine Translation
• Comparative evaluation of CNN architectures for Image Caption Generation
• Combining Visible Light and Infrared Imaging for Efficient Detection of Respiratory Infections such as COVID-19 on Portable Device
• Trivializations for Gradient-Based Optimization on Manifolds
• CLOSURE: Assessing Systematic Generalization of CLEVR Models
• Point2Sequence: Learning the Shape Representation of 3D Point Clouds with an Attention-based Sequence to Sequence Network
• Combining Discrete and Neural Features for Sequence Labeling
• Text Data Augmentation Made Simple By Leveraging NLP Cloud APIs
• Attribute Recognition by Joint Recurrent Learning of Context and Correlation
• Dynamic Neural Turing Machine with Soft and Hard Addressing Schemes
• Towards High Performance Video Object Detection for Mobiles
• A Survey of Natural Language Generation Techniques with a Focus on Dialogue Systems - Past, Present and Future Directions
• Abstractive and Extractive Text Summarization using Document Context Vector and Recurrent Neural Networks
• Towards a Visual Turing Challenge
• MINN: Learning the dynamics of differential-algebraic equations and application to battery modeling
• Zero-Resource Translation with Multi-Lingual Neural Machine Translation
• LSTM vs. GRU vs. Bidirectional RNN for script generation
• What value do explicit high level concepts have in vision to language problems?
• Neural Text Generation: A Practical Guide
• Character-Based Handwritten Text Transcription with Attention Networks
• Deep learning for dynamic graphs: models and benchmarks
• Efficient inverse design and spectrum prediction for nanophotonic devices based on deep recurrent neural networks
• A Review of Machine Learning Applications in Fuzzing
• Data-driven Summarization of Scientific Articles
• Predicting Citywide Crowd Flows Using Deep Spatio-Temporal Residual Networks
• Edge-based sequential graph generation with recurrent neural networks
• SOS: Selective Objective Switch for Rapid Immunofluorescence Whole Slide Image Classification
• Rice Classification Using Spatio-Spectral Deep Convolutional Neural Network
• PyDEns: a Python Framework for Solving Differential Equations with Neural Networks
• Compressing RNNs for IoT devices by 15-38x using Kronecker Products
• Joint Training for Neural Machine Translation Models with Monolingual Data
• ROMA: Multi-Agent Reinforcement Learning with Emergent Roles
• A Comparative Study of Word Embeddings for Reading Comprehension
• A Conditional Variational Framework for Dialog Generation
• Heterogeneous Multi-task Learning with Expert Diversity
• Glance and Focus: a Dynamic Approach to Reducing Spatial Redundancy in Image Classification
• Neural Machine Reading Comprehension: Methods and Trends
• SemEval-2021 Task 11: NLPContributionGraph -- Structuring Scholarly NLP Contributions for a Research Knowledge Graph
• A non-cooperative meta-modeling game for automated third-party calibrating, validating, and falsifying constitutive laws with parallelized adversarial attacks
• Well Googled is Half Done: Multimodal Forecasting of New Fashion Product Sales with Image-based Google Trends
• The Impact of Preprocessing on Arabic-English Statistical and Neural Machine Translation
• Context-Aware Self-Attention Networks
• Unifying Cardiovascular Modelling with Deep Reinforcement Learning for Uncertainty Aware Control of Sepsis Treatment
• Regularizing RNNs for Caption Generation by Reconstructing The Past with The Present
• Decoding Imagined Speech and Computer Control using Brain Waves
• Deep Learning with a Rethinking Structure for Multi-label Classification
• Real-Time Referring Expression Comprehension by Single-Stage Grounding Network
• Uncertainty-Aware Reliable Text Classification
• A Deep Memory-based Architecture for Sequence-to-Sequence Learning
• Relational recurrent neural networks
• A Reinforced Topic-Aware Convolutional Sequence-to-Sequence Model for Abstractive Text Summarization
• An Overview of Voice Conversion and its Challenges: From Statistical Modeling to Deep Learning
• Machine Learning in High Energy Physics: A review of heavy-flavor jet tagging at the LHC
• Less Is More: Picking Informative Frames for Video Captioning
• V2CNet: A Deep Learning Framework to Translate Videos to Commands for Robotic Manipulation
• e-SNLI-VE: Corrected Visual-Textual Entailment with Natural Language Explanations
• Abstractive Summarization of Spoken and Written Instructions with BERT
• Memory-enhanced Decoder for Neural Machine Translation
• TarMAC: Targeted Multi-Agent Communication
• DeepTriage: Exploring the Effectiveness of Deep Learning for Bug Triaging
• Seq2Seq AI Chatbot with Attention Mechanism
• How To Train Your Deep Multi-Object Tracker
• Model-based Reinforcement Learning for Semi-Markov Decision Processes with Neural ODEs
• Learning to Select Knowledge for Response Generation in Dialog Systems
• 3D Gated Recurrent Fusion for Semantic Scene Completion
• Neural Language Generation: Formulation, Methods, and Evaluation
• BlockCNN: A Deep Network for Artifact Removal and Image Compression
• A recurrent neural network without chaos
• Attention-Based Multimodal Fusion for Video Description
• Predictive Mutation Analysis via Natural Language Channel in Source Code
• PIP-Net: Pedestrian Intention Prediction in the Wild
• Survey of Visual Question Answering: Datasets and Techniques
• Rethinking Action Spaces for Reinforcement Learning in End-to-end Dialog Agents with Latent Variable Models
• On the Learnability of Concepts: With Applications to Comparing Word Embedding Algorithms
• Situation Recognition with Graph Neural Networks
• Unsupervised Discrete Sentence Representation Learning for Interpretable Neural Dialog Generation
• Guided Feature Transformation (GFT): A Neural Language Grounding Module for Embodied Agents
• Ranking for Relevance and Display Preferences in Complex Presentation Layouts
• One Sentence One Model for Neural Machine Translation
• Sales forecasting using WaveNet within the framework of the Kaggle competition
• Hierarchically Structured Reinforcement Learning for Topically Coherent Visual Story Generation
• Algorithmic Composition of Melodies with Deep Recurrent Neural Networks
• Learning Chinese Word Representations From Glyphs Of Characters
• SEE: Syntax-aware Entity Embedding for Neural Relation Extraction
• Learning Word Embeddings from Speech
• A Bi-LSTM-RNN Model for Relation Classification Using Low-Cost Sequence Features
• Unsupervised pre-training for sequence to sequence speech recognition
• DeepHealth: Review and challenges of artificial intelligence in health informatics
• Low Resource Neural Machine Translation: A Benchmark for Five African Languages
• Sequence Model Design for Code Completion in the Modern IDE
• Confidence through Attention
• ACDC: A Structured Efficient Linear Layer
• A Multi-task Learning Approach for Improving Product Title Compression with User Search Log Data
• SemStyle: Learning to Generate Stylised Image Captions using Unaligned Text
• Machine Translation of Low-Resource Spoken Dialects: Strategies for Normalizing Swiss German
• Read, Watch, and Move: Reinforcement Learning for Temporally Grounding Natural Language Descriptions in Videos
• Action Sequence Augmentation for Early Graph-based Anomaly Detection
• A Unified Framework of Online Learning Algorithms for Training Recurrent Neural Networks
• Joint Learning of Correlated Sequence Labelling Tasks Using Bidirectional Recurrent Neural Networks
• Exploration on Generating Traditional Chinese Medicine Prescription from Symptoms with an End-to-End method
• Comparison of Deep learning models on time series forecasting : a case study of Dissolved Oxygen Prediction
• GuessWhat?! Visual object discovery through multi-modal dialogue
• Grounded Recurrent Neural Networks
• Building a Neural Machine Translation System Using Only Synthetic Parallel Data
• Watch What You Just Said: Image Captioning with Text-Conditional Attention
• Reasoning with Sarcasm by Reading In-between
• Leveraging the Video-level Semantic Consistency of Event for Audio-visual Event Localization
• I Am Not What I Write: Privacy Preserving Text Representation Learning
• Convolutional RNN: an Enhanced Model for Extracting Features from Sequential Data
• Transfer Learning for Clinical Time Series Analysis using Recurrent Neural Networks
• Semantic Compositional Networks for Visual Captioning
• Non-Autoregressive Machine Translation with Auxiliary Regularization
• From FiLM to Video: Multi-turn Question Answering with Multi-modal Context
• Multichannel CNN with Attention for Text Classification
• Image Captioning and Visual Question Answering Based on Attributes and External Knowledge
• Investigating gated recurrent neural networks for speech synthesis
• On the Benefit of Combining Neural, Statistical and External Features for Fake News Identification
• Modality Fusion Network and Personalized Attention in Momentary Stress Detection in the Wild
• Co-attending Free-form Regions and Detections with Multi-modal Multiplicative Feature Embedding for Visual Question Answering
• GateNet: Gating-Enhanced Deep Network for Click-Through Rate Prediction
• Gated Recurrent Neural Network Approach for Multilabel Emotion Detection in Microblogs
• Learning Blended, Precise Semantic Program Embeddings
• Temporal Recurrent Networks for Online Action Detection
• Doubly Attentive Transformer Machine Translation
• Zero-Shot Dialog Generation with Cross-Domain Latent Actions
• Deep Learning Model on Gravitational Waveforms in Merging and Ringdown Phases of Binary Black Hole Coalescences
• End-to-End User Behavior Retrieval in Click-Through RatePrediction Model
• A Natural Language-Inspired Multi-label Video Streaming Traffic Classification Method Based on Deep Neural Networks
• Meta-Learning for Stochastic Gradient MCMC
• Low-resource Deep Entity Resolution with Transfer and Active Learning
• Ancient-Modern Chinese Translation with a Large Training Dataset
• Recurrent Attention Unit
• BERT Based Multilingual Machine Comprehension in English and Hindi
• Learning Generic Sentence Representations Using Convolutional Neural Networks
• Ghost translation
• Heterogeneous Interaction Modeling With Reduced Accumulated Error for Multi-Agent Trajectory Prediction
• BEHRT: Transformer for Electronic Health Records
• On the model-based stochastic value gradient for continuous reinforcement learning
• A Hierarchical Latent Structure for Variational Conversation Modeling
• TeMP: Temporal Message Passing for Temporal Knowledge Graph Completion
• DeepVecFont: Synthesizing High-quality Vector Fonts via Dual-modality Learning
• Robust offset-free constrained Model Predictive Control with Long Short-Term Memory Networks -- Extended version
• Deep Context-Aware Recommender System Utilizing Sequential Latent Context
• Skeleton Key: Image Captioning by Skeleton-Attribute Decomposition
• Augmenting Neural Machine Translation with Knowledge Graphs
• Human Motion Prediction via Spatio-Temporal Inpainting
• RST-MODNet: Real-time Spatio-temporal Moving Object Detection for Autonomous Driving
• A Note on Learning Rare Events in Molecular Dynamics using LSTM and Transformer
• Skeleton-to-Response: Dialogue Generation Guided by Retrieval Memory
• Deep Learning Methods for Efficient Large Scale Video Labeling
• Referenceless Quality Estimation for Natural Language Generation
• PyHealth: A Python Library for Health Predictive Models
• A Read-Write Memory Network for Movie Story Understanding
• ProLanGO: Protein Function Prediction Using Neural~Machine Translation Based on a Recurrent Neural Network
• Robustness Analysis of Visual QA Models by Basic Questions
• Neural Sign Language Translation based on Human Keypoint Estimation
• Visual Question Answering with Memory-Augmented Networks
• Heavy Ball Neural Ordinary Differential Equations
• "Mask and Infill" : Applying Masked Language Model to Sentiment Transfer
• Towards Sub-Word Level Compositions for Sentiment Analysis of Hindi-English Code Mixed Text
• Differentiable Top-k Operator with Optimal Transport
• Fact-based Text Editing
• Double Neural Counterfactual Regret Minimization
• Recurrent MVSNet for High-resolution Multi-view Stereo Depth Inference
• Neural Personalized Response Generation as Domain Adaptation
• Unsupervised Neural Machine Translation with Weight Sharing
• Memory Warps for Learning Long-Term Online Video Representations
• PSIque: Next Sequence Prediction of Satellite Images using a Convolutional Sequence-to-Sequence Network
• Zero-Shot Recommender Systems
• Semantic Parsing Natural Language into SPARQL: Improving Target Language Representation with Neural Attention
• Trainable Greedy Decoding for Neural Machine Translation
• Singing Style Transfer Using Cycle-Consistent Boundary Equilibrium Generative Adversarial Networks
• Tensor2Tensor for Neural Machine Translation
• Real-Time Emotion Recognition via Attention Gated Hierarchical Memory Network
• The Relative Performance of Ensemble Methods with Deep Convolutional Neural Networks for Image Classification
• Explicit Feature Interaction-aware Graph Neural Networks
• Joint Modeling of Local and Global Temporal Dynamics for Multivariate Time Series Forecasting with Missing Values
• CSVideoNet: A Real-time End-to-end Learning Framework for High-frame-rate Video Compressive Sensing
• ViT LoS V2X: Vision Transformers for Environment-aware LoS Blockage Prediction for 6G Vehicular Networks
• Physics-informed attention-based neural network for solving non-linear partial differential equations
• Learning to Understand Phrases by Embedding the Dictionary
• Can RNNs learn Recursive Nested Subject-Verb Agreements?
• Unifying Data, Model and Hybrid Parallelism in Deep Learning via Tensor Tiling
• An Empirical Comparison on Imitation Learning and Reinforcement Learning for Paraphrase Generation
• Generative Encoder-Decoder Models for Task-Oriented Spoken Dialog Systems with Chatting Capability
• NODE-SELECT: A Graph Neural Network Based On A Selective Propagation Technique
• Deconvolutional Feature Stacking for Weakly-Supervised Semantic Segmentation
• A Survey on Biomedical Image Captioning
• Deep Reinforced Query Reformulation for Information Retrieval
• Lie Access Neural Turing Machine
• Adversarial Resilience Learning - Towards Systemic Vulnerability Analysis for Large and Complex Systems
• Predictive-State Decoders: Encoding the Future into Recurrent Networks
• Enabling My Robot To Play Pictionary : Recurrent Neural Networks For Sketch Recognition
• Incorporating Discriminator in Sentence Generation: a Gibbs Sampling Method
• Deep Learning Approach for Singer Voice Classification of Vietnamese Popular Music
• Joint Image Captioning and Question Answering
• Deep Multimodal Representation Learning from Temporal Data
• Sequence to Sequence Learning for Optical Character Recognition
• A Time-Temperature Dataset for the Strawberry Cold Chain Across Multiple Shipments and Locations
• No Need to Pay Attention: Simple Recurrent Neural Networks Work! (for Answering "Simple" Questions)
• Recurrent Neural Network Control of a Hybrid Dynamic Transfemoral Prosthesis with EdgeDRNN Accelerator
• Dialogue history integration into end-to-end signal-to-concept spoken language understanding systems
• Cross-domain Semantic Parsing via Paraphrasing
• Code Attention: Translating Code to Comments by Exploiting Domain Features
• Transfer Learning for Neural Semantic Parsing
• Improving Neural Machine Translation with Conditional Sequence Generative Adversarial Nets
• How recurrent networks implement contextual processing in sentiment analysis
• Simultaneously Recovering Multi-Person Meshes and Multi-View Cameras with Human Semantics
• RawNet: Advanced end-to-end deep neural network using raw waveforms for text-independent speaker verification
• One-Class Adversarial Nets for Fraud Detection
• Potential Field: Interpretable and Unified Representation for Trajectory Prediction
• Automatic Generation of Grounded Visual Questions
• IterGANs: Iterative GANs to Learn and Control 3D Object Transformation
• New Era of Deeplearning-Based Malware Intrusion Detection: The Malware Detection and Prediction Based On Deep Learning
• Hyperbolic Deep Neural Networks: A Survey
• An Effective Automatic Image Annotation Model Via Attention Model and Data Equilibrium
• A Hierarchical Contextual Attention-based GRU Network for Sequential Recommendation
• ConcealNet: An End-to-end Neural Network for Packet Loss Concealment in Deep Speech Emotion Recognition
• Analyzing the Forgetting Problem in the Pretrain-Finetuning of Dialogue Response Models
• Retrieving Sequential Information for Non-Autoregressive Neural Machine Translation
• Minimal Gated Unit for Recurrent Neural Networks
• Acquiring Knowledge from Pre-trained Model to Neural Machine Translation
• Semi-Autoregressive Neural Machine Translation
• Indic-Transformers: An Analysis of Transformer Language Models for Indian Languages
• Neural Lattice-to-Sequence Models for Uncertain Inputs
• Personalized Re-ranking for Recommendation
• An Encoder-Decoder Framework Translating Natural Language to Database Queries
• Effective Representations of Clinical Notes
• LAVA NAT: A Non-Autoregressive Translation Model with Look-Around Decoding and Vocabulary Attention
• In-Ear-Voice: Towards Milli-Watt Audio Enhancement With Bone-Conduction Microphones for In-Ear Sensing Platforms
• Recurrent Neural Network Encoder with Attention for Community Question Answering
• Cortex: A Compiler for Recursive Deep Learning Models
• TRIG: Transformer-Based Text Recognizer with Initial Embedding Guidance
• IconQA: A New Benchmark for Abstract Diagram Understanding and Visual Language Reasoning
• Language Modeling on a SpiNNaker 2 Neuromorphic Chip
• OctoPath: An OcTree Based Self-Supervised Learning Approach to Local Trajectory Planning for Mobile Robots
• Modeling Dynamic Heterogeneous Network for Link Prediction using Hierarchical Attention with Temporal RNN
• Sample-efficient Deep Reinforcement Learning for Dialog Control
• VideoNavQA: Bridging the Gap between Visual and Embodied Question Answering
• Capturing social media expressions during the COVID-19 pandemic in Argentina and forecasting mental health and emotions
• An end-to-end Generative Retrieval Method for Sponsored Search Engine --Decoding Efficiently into a Closed Target Domain
• Neural Machine Translation Advised by Statistical Machine Translation
• CoCoSum: Contextual Code Summarization with Multi-Relational Graph Neural Network
• Still not there? Comparing Traditional Sequence-to-Sequence Models to Encoder-Decoder Neural Networks on Monotone String Translation Tasks
• Classification-based RNN machine translation using GRUs
• Extracting Symptoms and their Status from Clinical Conversations
• Lattice-Based Transformer Encoder for Neural Machine Translation
• First Experiments with Neural Translation of Informal to Formal Mathematics
• Learning Graph-Level Representations with Recurrent Neural Networks
• Personalized Embedding-based e-Commerce Recommendations at eBay
• Context-Dependent Translation Selection Using Convolutional Neural Network
• GPS-Aided Deep Learning for Beam Prediction and Tracking in UAV mmWave Communication
• Growing Efficient Deep Networks by Structured Continuous Sparsification
• Recurrent Predictive State Policy Networks
• Foreign English Accent Adjustment by Learning Phonetic Patterns
• Automatically Labeling Low Quality Content on Wikipedia by Leveraging Patterns in Editing Behaviors
• Generating Commit Messages from Git Diffs
• Pragmatically Informative Text Generation
• Deep Joint Source Channel Coding for WirelessImage Transmission with OFDM
• Audio-based automatic mating success prediction of giant pandas
• S3VAE: Self-Supervised Sequential VAE for Representation Disentanglement and Data Generation
• Feature Boosting Network For 3D Pose Estimation
• MathNet: A Data-Centric Approach for Printed Mathematical Expression Recognition
• Faithful Multimodal Explanation for Visual Question Answering
• The Tensor Memory Hypothesis
• HANet: Hierarchical Alignment Networks for Video-Text Retrieval
• Regularizing Neural Machine Translation by Target-bidirectional Agreement
• English-Bhojpuri SMT System: Insights from the Karaka Model
• Breaking the Activation Function Bottleneck through Adaptive Parameterization
• Training Language Models Using Target-Propagation
• Fully Supervised Speaker Diarization
• A Simple LSTM model for Transition-based Dependency Parsing
• Multimodal Memory Modelling for Video Captioning
• Tango: A Deep Neural Network Benchmark Suite for Various Accelerators
• Detecting Cyberattacks in Industrial Control Systems Using Convolutional Neural Networks
• SEED: Semantic Graph based Deep detection for type-4 clone
• TiKick: Towards Playing Multi-agent Football Full Games from Single-agent Demonstrations
• ACtuAL: Actor-Critic Under Adversarial Learning
• EEV: A Large-Scale Dataset for Studying Evoked Expressions from Video
• Question Answering on Linked Data: Challenges and Future Directions
• Improving Domain Adaptation Translation with Domain Invariant and Specific Information
• QuickEdit: Editing Text & Translations by Crossing Words Out
• WikiReading: A Novel Large-scale Language Understanding Task over Wikipedia
• On the Effective Use of Pretraining for Natural Language Inference
• Towards Proof Synthesis Guided by Neural Machine Translation for Intuitionistic Propositional Logic
• Semi-Supervised Phoneme Recognition with Recurrent Ladder Networks
• Figure Captioning with Reasoning and Sequence-Level Training
• Learning meters of Arabic and English poems with Recurrent Neural Networks: a step forward for language understanding and synthesis
• Relational Action Forecasting
• Machine Translation : From Statistical to modern Deep-learning practices
• Guiding attention in Sequence-to-sequence models for Dialogue Act prediction
• CAUSE: Learning Granger Causality from Event Sequences using Attribution Methods
• Fully-Convolutional Intensive Feature Flow Neural Network for Text Recognition
• I Know You'll Be Back: Interpretable New User Clustering and Churn Prediction on a Mobile Social Application
• Jointly Modeling Aspect and Sentiment with Dynamic Heterogeneous Graph Neural Networks
• Learning Interpretable Deep State Space Model for Probabilistic Time Series Forecasting
• Artificial Intelligence Decision Support for Medical Triage
• RNNAccel: A Fusion Recurrent Neural Network Accelerator for Edge Intelligence
• DropAttack: A Masked Weight Adversarial Training Method to Improve Generalization of Neural Networks
• Multiple Object Tracking with Mixture Density Networks for Trajectory Estimation
• Physics-Informed Real NVP for Satellite Power System Fault Detection
• Spatio-temporal Features for Generalized Detection of Deepfake Videos
• Reconfigurable Cyber-Physical System for Lifestyle Video-Monitoring via Deep Learning
• Gated Recurrent Context: Softmax-free Attention for Online Encoder-Decoder Speech Recognition
• MeshWalker: Deep Mesh Understanding by Random Walks
• RefNet: A Reference-aware Network for Background Based Conversation
• Thinking Globally, Acting Locally: Distantly Supervised Global-to-Local Knowledge Selection for Background Based Conversation
• An Encoder-Decoder Based Approach for Anomaly Detection with Application in Additive Manufacturing
• Identify Susceptible Locations in Medical Records via Adversarial Attacks on Deep Predictive Models
• Deep Keyphrase Generation
• Link Prediction using Embedded Knowledge Graphs
• Learning Index Selection with Structured Action Spaces
• When FastText Pays Attention: Efficient Estimation of Word Representations using Constrained Positional Weighting
• PoseScript: Linking 3D Human Poses and Natural Language
• PFML: Self-Supervised Learning of Time-Series Data Without Representation Collapse
• Fatigue-PINN: Physics-Informed Fatigue-Driven Motion Modulation and Synthesis
• HiMo: High-Speed Objects Motion Compensation in Point Clouds
• Visual Reasoning: from State to Transformation
• Rethinking Lifelong Sequential Recommendation with Incremental Multi-Interest Attention
• Generate, Prune, Select: A Pipeline for Counterspeech Generation against Online Hate Speech
• Reflective Decoding Network for Image Captioning
• Improving Neural Text Simplification Model with Simplified Corpora
• Greedy Search with Probabilistic N-gram Matching for Neural Machine Translation
• Merging datasets through deep learning
• Sequential Copying Networks
• TI-Capsule: Capsule Network for Stock Exchange Prediction
• Echo: Compiler-based GPU Memory Footprint Reduction for LSTM RNN Training
• A Novel Fusion of Attention and Sequence to Sequence Autoencoders to Predict Sleepiness From Speech
• CAPS: Context Aware Personalized POI Sequence Recommender System
• Improving Retrieval Modeling Using Cross Convolution Networks And Multi Frequency Word Embedding
• Dual Recurrent Attention Units for Visual Question Answering
• Event-Driven Visual-Tactile Sensing and Learning for Robots
• The NLP Engine: A Universal Turing Machine for NLP
• Temporal Probability Calibration
• Exploring Neural Models for Parsing Natural Language into First-Order Logic
• HAS-QA: Hierarchical Answer Spans Model for Open-domain Question Answering
• soc2seq: Social Embedding meets Conversation Model
• What and How Well You Performed? A Multitask Learning Approach to Action Quality Assessment
• Top-down Visual Saliency Guided by Captions
• Scalable Bayesian Learning of Recurrent Neural Networks for Language Modeling
• Generating Multiple Diverse Responses with Multi-Mapping and Posterior Mapping Selection
• Automatically Generating Commit Messages from Diffs using Neural Machine Translation
• Learning Phrase Embeddings from Paraphrases with GRUs
• Delineation of Skin Strata in Reflectance Confocal Microscopy Images using Recurrent Convolutional Networks with Toeplitz Attention
• Chunked Autoregressive GAN for Conditional Waveform Synthesis
• Phonology Recognition in American Sign Language
• Deep Insights of Deepfake Technology : A Review
• Neural Spatio-Temporal Point Processes
• Sound Event Detection Utilizing Graph Laplacian Regularization with Event Co-occurrence
• Attentional Multilabel Learning over Graphs: A Message Passing Approach
• An Efficient Character-Level Neural Machine Translation
• Teaching Machines to Converse
• Can Machine Generate Traditional Chinese Poetry? A Feigenbaum Test
• Language Models with Pre-Trained (GloVe) Word Embeddings
• Outline Generation: Understanding the Inherent Content Structure of Documents
• Multilingual sequence-to-sequence speech recognition: architecture, transfer learning, and language modeling
• Assessing Language Models with Scaling Properties
• Improved Audio Embeddings by Adjacency-Based Clustering with Applications in Spoken Term Detection
• TrafficStream: A Streaming Traffic Flow Forecasting Framework Based on Graph Neural Networks and Continual Learning
• The Tensor Brain: Semantic Decoding for Perception and Memory
• End-to-End Spoken Language Translation
• Spatial and Temporal Networks for Facial Expression Recognition in the Wild Videos
• Topic-Aware Neural Keyphrase Generation for Social Media Language
• WSLLN: Weakly Supervised Natural Language Localization Networks
• 3D Quasi-Recurrent Neural Network for Hyperspectral Image Denoising
• Learning from Fact-checkers: Analysis and Generation of Fact-checking Language
• Unpaired Cross-lingual Image Caption Generation with Self-Supervised Rewards
• Satirical News Detection and Analysis using Attention Mechanism and Linguistic Features
• Stock price prediction using BERT and GAN
• Interpretation of Natural Language Rules in Conversational Machine Reading
• Learning to Read by Spelling: Towards Unsupervised Text Recognition
• Fusion Recurrent Neural Network
• Learning Oculomotor Behaviors from Scanpath
• Structured Variational Inference in Unstable Gaussian Process State Space Models
• An Empirical Evaluation of various Deep Learning Architectures for Bi-Sequence Classification Tasks
• Rissanen Data Analysis: Examining Dataset Characteristics via Description Length
• Towards Multi-Scale Style Control for Expressive Speech Synthesis
• DiaNet: BERT and Hierarchical Attention Multi-Task Learning of Fine-Grained Dialect
• Multi Task Deep Morphological Analyzer: Context Aware Joint Morphological Tagging and Lemma Prediction
• Exoplanet Transit Candidate Identification in TESS Full-Frame Images via a Transformer-Based Algorithm
• Dense Residual Network: Enhancing Global Dense Feature Flow for Character Recognition
• ReLiCADA -- Reservoir Computing using Linear Cellular Automata Design Algorithm
• The Style-Content Duality of Attractiveness: Learning to Write Eye-Catching Headlines via Disentanglement
• Neural Melody Composition from Lyrics
• Simplified Gating in Long Short-term Memory (LSTM) Recurrent Neural Networks
• Multi-stream RNN for Merchant Transaction Prediction
• Melodic Phrase Segmentation By Deep Neural Networks
• HAConvGNN: Hierarchical Attention Based Convolutional Graph Neural Network for Code Documentation Generation in Jupyter Notebooks
• Investigating Linguistic Pattern Ordering in Hierarchical Natural Language Generation
• Deepening Hidden Representations from Pre-trained Language Models
• A Deep Sequential Model for Discourse Parsing on Multi-Party Dialogues
• Neural network approach to classifying alarming student responses to online assessment
• Mandarin tone modeling using recurrent neural networks
• Network of Evolvable Neural Units: Evolving to Learn at a Synaptic Level
• A Hierarchical Recurrent Encoder-Decoder For Generative Context-Aware Query Suggestion
• Teaching Machines to Code: Neural Markup Generation with Visual Attention
• Robust Neural Machine Translation with Joint Textual and Phonetic Embedding
• Fashion-IQ 2020 Challenge 2nd Place Team's Solution
• Multilingual Neural Machine Translation for Zero-Resource Languages
• ST${}^2$: Small-data Text Style Transfer via Multi-task Meta-Learning
• Syntax-driven Iterative Expansion Language Models for Controllable Text Generation
• Online Multi-horizon Transaction Metric Estimation with Multi-modal Learning in Payment Networks
• Language Modelling for Source Code with Transformer-XL
• A Deep Learning Based Decoder for Concatenated Coding over Deletion Channels
• APo-VAE: Text Generation in Hyperbolic Space
• Frame-To-Frame Consistent Semantic Segmentation
• SpatialSense: An Adversarially Crowdsourced Benchmark for Spatial Relation Recognition
• Modeling Spatio-Temporal Human Track Structure for Action Localization
• Learning Latent Local Conversation Modes for Predicting Community Endorsement in Online Discussions
• ContextNet: A Click-Through Rate Prediction Framework Using Contextual information to Refine Feature Embedding
• A Dynamic Model for Traffic Flow Prediction Using Improved DRN
• Applications of Machine Learning in Document Digitisation
• Towards Trainable Media: Using Waves for Neural Network-Style Training
• ParaSCI: A Large Scientific Paraphrase Dataset for Longer Paraphrase Generation
• An End-to-End Deep RL Framework for Task Arrangement in Crowdsourcing Platforms
• MoNet: Motion-based Point Cloud Prediction Network
• Interactive Recommender System via Knowledge Graph-enhanced Reinforcement Learning
• Multi-Horizon Forecasting for Limit Order Books: Novel Deep Learning Approaches and Hardware Acceleration using Intelligent Processing Units
• Title-Guided Encoding for Keyphrase Generation
• Graph-augmented Learning to Rank for Querying Large-scale Knowledge Graph
• Neural ODEs for Informative Missingness in Multivariate Time Series
• Discriminative Multi-modality Speech Recognition
• Boosting Naturalness of Language in Task-oriented Dialogues via Adversarial Training
• Adversarial Contrastive Pre-training for Protein Sequences
• Forecasting in multivariate irregularly sampled time series with missing values
• A Review of Formal Methods applied to Machine Learning
• Refined Gate: A Simple and Effective Gating Mechanism for Recurrent Units
• CARL: Content-Aware Representation Learning for Heterogeneous Networks
• Continuous-Depth Neural Models for Dynamic Graph Prediction
• TCN-DPD: Parameter-Efficient Temporal Convolutional Networks for Wideband Digital Predistortion
• Implementing a Reverse Dictionary, based on word definitions, using a Node-Graph Architecture
• Deep Structural Point Process for Learning Temporal Interaction Networks
• Empirical Evaluation of RNN Architectures on Sentence Classification Task
• A Correlational Encoder Decoder Architecture for Pivot Based Sequence Generation
• Complex Transformer: A Framework for Modeling Complex-Valued Sequence
• Context-free Self-Conditioned GAN for Trajectory Forecasting
• Memory-Augmented Neural Networks for Machine Translation
• WeNet: Weighted Networks for Recurrent Network Architecture Search
• Learned Indexes for Dynamic Workloads
• Variational Recurrent Neural Networks for Graph Classification
• Trouble on the Horizon: Forecasting the Derailment of Online Conversations as they Develop
• Telling Human and Machine Handwriting Apart
• Classification of Radiology Reports Using Neural Attention Models
• Discovering Dynamic Salient Regions for Spatio-Temporal Graph Neural Networks
• Recurrent Neural Networks with Pre-trained Language Model Embedding for Slot Filling Task
• INFLECT-DGNN: Influencer Prediction with Dynamic Graph Neural Networks
• UniPoll: A Unified Social Media Poll Generation Framework via Multi-Objective Optimization
• Context-Sensitive Generation Network for Handing Unknown Slot Values in Dialogue State Tracking
• Hyperbolic Deep Learning for Chinese Natural Language Understanding
• Towards Learning How to Properly Play UNO with the iCub Robot
• Getting Started with Neural Models for Semantic Matching in Web Search
• MC-LSTM: Mass-Conserving LSTM
• Benchmark Performance of Machine And Deep Learning Based Methodologies for Urdu Text Document Classification
• Performance of a Geometric Deep Learning Pipeline for HL-LHC Particle Tracking
• LightMove: A Lightweight Next-POI Recommendation for Taxicab Rooftop Advertising
• Black-Box Attacks on Sequential Recommenders via Data-Free Model Extraction
• Variational Hyper RNN for Sequence Modeling
• Trajectory Prediction for Autonomous Driving using Agent-Interaction Graph Embedding
• Tha3aroon at NSURL-2019 Task 8: Semantic Question Similarity in Arabic
• Predicting Inpatient Discharge Prioritization With Electronic Health Records
• Parameter Prediction for Unseen Deep Architectures
• Improving Bidirectional Decoding with Dynamic Target Semantics in Neural Machine Translation
• Cross-Lingual Cross-Platform Rumor Verification Pivoting on Multimedia Content
• Learning Contextual Hierarchical Structure of Medical Concepts with Poincairé Embeddings to Clarify Phenotypes
• Complex Unitary Recurrent Neural Networks using Scaled Cayley Transform
• Scalable and Accurate Dialogue State Tracking via Hierarchical Sequence Generation
• Recurrent Neural Network-based Model for Accelerated Trajectory Analysis in AIMD Simulations
• Target Guided Emotion Aware Chat Machine
• Less is More: Sparse Sampling for Dense Reaction Predictions
• Rethinking Supervised Learning and Reinforcement Learning in Task-Oriented Dialogue Systems
• Unified recurrent neural network for many feature types
• Calendar Graph Neural Networks for Modeling Time Structures in Spatiotemporal User Behaviors
• PI-Net: Pose Interacting Network for Multi-Person Monocular 3D Pose Estimation
• A Comparative Study on Basic Elements of Deep Learning Models for Spatial-Temporal Traffic Forecasting
• Recurrent Attention Walk for Semi-supervised Classification
• Relevance-Promoting Language Model for Short-Text Conversation
• SCR-Graph: Spatial-Causal Relationships based Graph Reasoning Network for Human Action Prediction
• Go From the General to the Particular: Multi-Domain Translation with Domain Transformation Networks
• Tree-Structured Neural Machine for Linguistics-Aware Sentence Generation
• Reverse engineering learned optimizers reveals known and novel mechanisms
• Seeing in the dark with recurrent convolutional neural networks
• Multi-Zone Unit for Recurrent Neural Networks
• Attention-Based End-to-End Speech Recognition on Voice Search
• Learning to refer informatively by amortizing pragmatic reasoning
• Learning-Accelerated ADMM for Distributed Optimal Power Flow
• Learning Attribute-Structure Co-Evolutions in Dynamic Graphs
• Object-oriented Neural Programming (OONP) for Document Understanding
• Consumer Image Quality Prediction using Recurrent Neural Networks for Spatial Pooling
• Android Security using NLP Techniques: A Review
• Completely Unsupervised Phoneme Recognition by Adversarially Learning Mapping Relationships from Audio Embeddings
• Energy balancing using charge/discharge storages control and load forecasts in a renewable-energy-based grids
• Automatic Romanization of Arabic Bibliographic Records
• Optical Flow Dataset Synthesis from Unpaired Images
• Detecting and Explaining Crisis
• Path Imputation Strategies for Signature Models of Irregular Time Series
• RPC Considered Harmful: Fast Distributed Deep Learning on RDMA
• Investigation of Sentiment Controllable Chatbot
• Partially-Aligned Data-to-Text Generation with Distant Supervision
• Enhanced Neural Machine Translation by Learning from Draft
• UTS submission to Google YouTube-8M Challenge 2017
• On the approximation of functions by tanh neural networks
• A low latency ASR-free end to end spoken language understanding system
• Match${}^2$: A Matching over Matching Model for Similar Question Identification
• Deep Sequence Learning with Auxiliary Information for Traffic Prediction
• An Encoder-Decoder Model for ICD-10 Coding of Death Certificates
• A Memory Network Approach for Story-based Temporal Summarization of 360° Videos
• Query-based Interactive Recommendation by Meta-Path and Adapted Attention-GRU
• Deep Architectures and Ensembles for Semantic Video Classification
• Cross-Media Keyphrase Prediction: A Unified Framework with Multi-Modality Multi-Head Attention and Image Wordings
• LAGOS-AND: A Large Gold Standard Dataset for Scholarly Author Name Disambiguation
• An Empirical Comparison of Neural Architectures for Reinforcement Learning in Partially Observable Environments
• A Framework for Hierarchical Multilingual Machine Translation
• Exploiting Unlabeled Data for Neural Grammatical Error Detection
• Sentence Bag Graph Formulation for Biomedical Distant Supervision Relation Extraction
• Learning a Distributed Control Scheme for Demand Flexibility in Thermostatically Controlled Loads
• Second-Order Neural ODE Optimizer
• Video Time: Properties, Encoders and Evaluation
• MCEN: Bridging Cross-Modal Gap between Cooking Recipes and Dish Images with Latent Variable Model
• A Database for Research on Detection and Enhancement of Speech Transmitted over HF links
• Causal World Models by Unsupervised Deconfounding of Physical Dynamics
• Large Scale Question Answering using Tourism Data
• ast2vec: Utilizing Recursive Neural Encodings of Python Programs
• Towards Music Captioning: Generating Music Playlist Descriptions
• Towards Interpreting Recurrent Neural Networks through Probabilistic Abstraction
• Estimating Granger Causality with Unobserved Confounders via Deep Latent-Variable Recurrent Neural Network
• Stochastic Weight Matrix-based Regularization Methods for Deep Neural Networks
• Neural Machine Translation Model with a Large Vocabulary Selected by Branching Entropy
• Analysis of Bag-of-n-grams Representation's Properties Based on Textual Reconstruction
• KWT-Tiny: RISC-V Accelerated, Embedded Keyword Spotting Transformer
• Inductive Visual Localisation: Factorised Training for Superior Generalisation
• Deep Diabetologist: Learning to Prescribe Hyperglycemia Medications with Hierarchical Recurrent Neural Networks
• Options Discovery with Budgeted Reinforcement Learning
• Headline-Guided Extractive Summarization for Thai News Articles
• ForecastQA: A Question Answering Challenge for Event Forecasting with Temporal Text Data
• On the Exploitation of Neuroevolutionary Information: Analyzing the Past for a More Efficient Future
• Towards Relevance and Sequence Modeling in Language Recognition
• Quotation Recommendation and Interpretation Based on Transformation from Queries to Quotations
• Variational inference formulation for a model-free simulation of a dynamical system with unknown parameters by a recurrent neural network
• PURS: Personalized Unexpected Recommender System for Improving User Satisfaction
• OadTR: Online Action Detection with Transformers
• Learned Interpretable Residual Extragradient ISTA for Sparse Coding
• Application of Seq2Seq Models on Code Correction
• Neural Subgraph Isomorphism Counting
• Semi-supervised Learning for Marked Temporal Point Processes
• Tea: Program Repair Using Neural Network Based on Program Information Attention Matrix
• Learning Calibratable Policies using Programmatic Style-Consistency
• Neural Fixed-Point Acceleration for Convex Optimization
• A Joint and Domain-Adaptive Approach to Spoken Language Understanding
• Analysis of Big Data Technology for Health Care Services
• A Review of Bangla Natural Language Processing Tasks and the Utility of Transformer Models
• Seq-SG2SL: Inferring Semantic Layout from Scene Graph Through Sequence to Sequence Learning
• PKSpell: Data-Driven Pitch Spelling and Key Signature Estimation
• Learning Representations and Agents for Information Retrieval
• Generative Models for Security: Attacks, Defenses, and Opportunities
• Empirical Evaluation of A New Approach to Simplifying Long Short-term Memory (LSTM)
• BPPSA: Scaling Back-propagation by Parallel Scan Algorithm
• Look Who's Talking: Active Speaker Detection in the Wild
• Multi-Turn Beam Search for Neural Dialogue Modeling
• Task-Guided Pair Embedding in Heterogeneous Network
• Learning Dual Dynamic Representations on Time-Sliced User-Item Interaction Graphs for Sequential Recommendation
• Light Field Saliency Detection with Dual Local Graph Learning andReciprocative Guidance
• FPETS : Fully Parallel End-to-End Text-to-Speech System
• A Hierarchical Neural Network for Sequence-to-Sequences Learning
• Implicit Argument Prediction as Reading Comprehension
• Sequence-to-Sequence Networks Learn the Meaning of Reflexive Anaphora
• Goal recognition via model-based and model-free techniques
• Policy Design for Active Sequential Hypothesis Testing using Deep Learning
• Unsupervised Neural Text Simplification
• Sentylic at IEST 2018: Gated Recurrent Neural Network and Capsule Network Based Approach for Implicit Emotion Detection
• Temporal Pattern Attention for Multivariate Time Series Forecasting
• Keyword-Guided Neural Conversational Model
• Syntactic representation learning for neural network based TTS with syntactic parse tree traversal
• Recurrent Neural Networks with Flexible Gates using Kernel Activation Functions
• Roughly Collected Dataset for Contact Force Sensing Catheter
• Stay On-Topic: Generating Context-specific Fake Restaurant Reviews
• Hierarchical Gated Recurrent Neural Tensor Network for Answer Triggering
• Hierarchical Similarity Learning for Language-based Product Image Retrieval
• Real-time low-resource phoneme recognition on edge devices
• A Sketch-Based Neural Model for Generating Commit Messages from Diffs
• News Meets Microblog: Hashtag Annotation via Retriever-Generator
• Unsupervised Facial Action Unit Intensity Estimation via Differentiable Optimization
• Multitask Models for Supervised Protests Detection in Texts
• Sensor Data for Human Activity Recognition: Feature Representation and Benchmarking
• Building robust prediction models for defective sensor data using Artificial Neural Networks
• MTSS: Learn from Multiple Domain Teachers and Become a Multi-domain Dialogue Expert
• Generative network complex for the automated generation of druglike molecules
• Sampling-free Uncertainty Estimation in Gated Recurrent Units with Exponential Families
• Multi-Head Decoder for End-to-End Speech Recognition
• Astronomical Classification of Light Curves with an Ensemble of Gated Recurrent Units
• Dynamic Oracle for Neural Machine Translation in Decoding Phase
• PR-NN: RNN-based Detection for Coded Partial-Response Channels
• Bringing Semantic Structures to User Intent Detection in Online Medical Queries
• Long-tail Session-based Recommendation
• Which Kind Is Better in Open-domain Multi-turn Dialog,Hierarchical or Non-hierarchical Models? An Empirical Study
• Boundary Uncertainty in a Single-Stage Temporal Action Localization Network
• Multi-Scale One-Class Recurrent Neural Networks for Discrete Event Sequence Anomaly Detection
• Asking Complex Questions with Multi-hop Answer-focused Reasoning
• Cubic Spline Smoothing Compensation for Irregularly Sampled Sequences
• Tell Me How to Ask Again: Question Data Augmentation with Controllable Rewriting in Continuous Space
• Towards Controllable and Personalized Review Generation
• Semantic Graph Convolutional Network for Implicit Discourse Relation Classification
• Language Transfer of Audio Word2Vec: Learning Audio Segment Representations without Target Language Data
• Deep learning bank distress from news and numerical financial data
• Multi-task Sentence Encoding Model for Semantic Retrieval in Question Answering Systems
• Learning Multi-level Dependencies for Robust Word Recognition
• An Optimized and Energy-Efficient Parallel Implementation of Non-Iteratively Trained Recurrent Neural Networks
• Seeds Cleansing CNMF for Spatiotemporal Neural Signals Extraction of Miniscope Imaging Data
• Memory Augmented Graph Neural Networks for Sequential Recommendation
• Action Recognition and State Change Prediction in a Recipe Understanding Task Using a Lightweight Neural Network Model
• On Attribution of Recurrent Neural Network Predictions via Additive Decomposition
• Controllable Dialogue Generation with Disentangled Multi-grained Style Specification and Attribute Consistency Reward
• Seq2Biseq: Bidirectional Output-wise Recurrent Neural Networks for Sequence Modelling
• Dynamic Compositionality in Recursive Neural Networks with Structure-aware Tag Representations
• Latent Variable Algorithms for Multimodal Learning and Sensor Fusion
• Multi-Task Learning for Argumentation Mining
• A Case Study: Exploiting Neural Machine Translation to Translate CUDA to OpenCL
• Spatio-Temporal Image Boundary Extrapolation
• Longitudinal patient stratification of electronic health records with flexible adjustment for clinical outcomes
• Mini-Batch Consistent Slot Set Encoder for Scalable Set Encoding
• A Deep Learning Approach for Macroscopic Energy Consumption Prediction with Microscopic Quality for Electric Vehicles
• A Graph Convolutional Network with Signal Phasing Information for Arterial Traffic Prediction
• Asset Price Forecasting using Recurrent Neural Networks
• Sobolev training of thermodynamic-informed neural networks for smoothed elasto-plasticity models with level set hardening
• Logographic Subword Model for Neural Machine Translation
• ScopeIt: Scoping Task Relevant Sentences in Documents
• Continuous representations of intents for dialogue systems
• When to Fold'em: How to answer Unanswerable questions
• Are You Sure You Want To Do That? Classification with Verification
• An Investigation of the Impact of COVID-19 Non-Pharmaceutical Interventions and Economic Support Policies on Foreign Exchange Markets with Explainable AI Techniques
• Learning and Evaluating Sparse Interpretable Sentence Embeddings
• Discovering Latent Representations of Relations for Interacting Systems
• CooGAN: A Memory-Efficient Framework for High-Resolution Facial Attribute Editing
• Graph Convolutional Networks Reveal Neural Connections Encoding Prosthetic Sensation
• Longitudinal Pooling & Consistency Regularization to Model Disease Progression from MRIs
• Query Understanding via Intent Description Generation
• Adaptive Recurrent Neural Network Based on Mixture Layer
• End-to-end Learning for Short Text Expansion
• Content Word-based Sentence Decoding and Evaluating for Open-domain Neural Response Generation
• Comparative Study of Language Models on Cross-Domain Data with Model Agnostic Explainability
• HeunNet: Extending ResNet using Heun's Methods
• Functionally Modular and Interpretable Temporal Filtering for Robust Segmentation
• Generate Novel Molecules With Target Properties Using Conditional Generative Models
• Discourse Embellishment Using a Deep Encoder-Decoder Network
• Quantum Statistics-Inspired Neural Attention
• Artificial Intelligence in Surgery: Neural Networks and Deep Learning
• Enriching Transformers with Structured Tensor-Product Representations for Abstractive Summarization
• A New Hybrid-parameter Recurrent Neural Networks for Online Handwritten Chinese Character Recognition
• Modeling Melodic Feature Dependency with Modularized Variational Auto-Encoder
• Parameter-Efficient Neural Question Answering Models via Graph-Enriched Document Representations
• Strategies for Language Identification in Code-Mixed Low Resource Languages
• Using Deep Learning Sequence Models to Identify SARS-CoV-2 Divergence
• Recurrent Deep Divergence-based Clustering for simultaneous feature learning and clustering of variable length time series
• Deep Learning for Predicting Dynamic Uncertain Opinions in Network Data
• Workload-aware Automatic Parallelization for Multi-GPU DNN Training
• Neural Sequence Model Training via $\alpha$-divergence Minimization
• ProDyn0: Inferring calponin homology domain stretching behavior using graph neural networks
• Autoregressive Knowledge Distillation through Imitation Learning
• The RLLChatbot: a solution to the ConvAI challenge
• Threshold-Based Portfolio: The Role of the Threshold and Its Applications
• Machine Translation in Pronunciation Space
• Real-time People Tracking and Identification from Sparse mm-Wave Radar Point-clouds
• UPB at SemEval-2020 Task 12: Multilingual Offensive Language Detection on Social Media by Fine-tuning a Variety of BERT-based Models
• Seq2Seq Mimic Games: A Signaling Perspective
• Contextual Unsupervised Outlier Detection in Sequences
• Tailored Architectures for Time Series Forecasting: Evaluating Deep Learning Models on Gaussian Process-Generated Data
• How Do Neural Sequence Models Generalize? Local and Global Context Cues for Out-of-Distribution Prediction
• Context-Aware Dialog Re-Ranking for Task-Oriented Dialog Systems
• FeatureNorm: L2 Feature Normalization for Dynamic Graph Embedding
• Thick-Net: Parallel Network Structure for Sequential Modeling
• Sequential Embedding Induced Text Clustering, a Non-parametric Bayesian Approach
• On Multilingual Training of Neural Dependency Parsers
• Reducing the impact of out of vocabulary words in the translation of natural language questions into SPARQL queries
• Empirical Analysis of Korean Public AI Hub Parallel Corpora and in-depth Analysis using LIWC
• Probabilistic Trust Intervals for Out of Distribution Detection
• Jejueo Datasets for Machine Translation and Speech Synthesis
• Don't Judge Me by My Face : An Indirect Adversarial Approach to Remove Sensitive Information From Multimodal Neural Representation in Asynchronous Job Video Interviews
• Re-Evaluating GermEval17 Using German Pre-Trained Language Models
• Dialog Context Language Modeling with Recurrent Neural Networks
• Convolutional Quantum-Like Language Model with Mutual-Attention for Product Rating Prediction
• FastTrees: Parallel Latent Tree-Induction for Faster Sequence Encoding
• Generation of Synthetic Electronic Medical Record Text
• Disarranged Zone Learning (DZL): An unsupervised and dynamic automatic stenosis recognition methodology based on coronary angiography
• Speaker-aware speech-transformer
• ARMIN: Towards a More Efficient and Light-weight Recurrent Memory Network
• Differentiable Grammars for Videos
• Stock Index Prediction using Cointegration test and Quantile Loss
• Contributions to Large Scale Bayesian Inference and Adversarial Machine Learning
• Non-Negative PARATUCK2 Tensor Decomposition Combined to LSTM Network For Smart Contracts Profiling
• GRET: Global Representation Enhanced Transformer
• Neuro-Symbolic AI: An Emerging Class of AI Workloads and their Characterization
• Guider l'attention dans les modeles de sequence a sequence pour la prediction des actes de dialogue
• #StayHome or #Marathon? Social Media Enhanced Pandemic Surveillance on Spatial-temporal Dynamic Graphs
• Dialogue Summarization with Supporting Utterance Flow Modeling and Fact Regularization
• Personalizing Search Results Using Hierarchical RNN with Query-aware Attention
• Reference Network for Neural Machine Translation
• Learn to Focus: Hierarchical Dynamic Copy Network for Dialogue State Tracking
• RotLSTM: Rotating Memories in Recurrent Neural Networks
• Gated Recurrent Units Learning for Optimal Deployment of Visible Light Communications Enabled UAVs
• A Sequential Set Generation Method for Predicting Set-Valued Outputs
• Learning Image Attacks toward Vision Guided Autonomous Vehicles
• Target Propagation via Regularized Inversion
• Latent Event-Predictive Encodings through Counterfactual Regularization
• Generative Dialog Policy for Task-oriented Dialog Systems
• Learning Representations by Stochastic Meta-Gradient Descent in Neural Networks
• CASA-NLU: Context-Aware Self-Attentive Natural Language Understanding for Task-Oriented Chatbots
• GaDei: On Scale-up Training As A Service For Deep Learning
• Neural Cross-Domain Collaborative Filtering with Shared Entities
• Effective Spoken Language Labeling with Deep Recurrent Neural Networks
• Residual Tree Aggregation of Layers for Neural Machine Translation
• Modeling of Rakugo Speech and Its Limitations: Toward Speech Synthesis That Entertains Audiences
• Cubic LSTMs for Video Prediction
• STR-GODEs: Spatial-Temporal-Ridership Graph ODEs for Metro Ridership Prediction
• Proposing Plausible Answers for Open-ended Visual Question Answering
• CycleGAN-Driven Transfer Learning for Electronics Response Emulation in High-Purity Germanium Detectors
• Asynchronous "Events" are Better For Motion Estimation
• Modelling Neuronal Behaviour with Time Series Regression: Recurrent Neural Networks on C. Elegans Data
• Neighbourhood Distillation: On the benefits of non end-to-end distillation
• Spatio-Temporal Deep Learning Models for Tip Force Estimation During Needle Insertion
• Modeling Multivariate Cyber Risks: Deep Learning Dating Extreme Value Theory
• LTN: Long-Term Network for Long-Term Motion Prediction
• Self-Learning for Zero Shot Neural Machine Translation
• Modeling Web Browsing Behavior across Tabs and Websites with Tracking and Prediction on the Client Side
• GWU NLP Lab at SemEval-2019 Task 3: EmoContext: Effective Contextual Information in Models for Emotion Detection in Sentence-level in a Multigenre Corpus
• LiDAR-based Recurrent 3D Semantic Segmentation with Temporal Memory Alignment
• Learning to Reweight Imaginary Transitions for Model-Based Reinforcement Learning
• Power Law Graph Transformer for Machine Translation and Representation Learning
• Freudian and Newtonian Recurrent Cell for Sequential Recommendation
• Combining Word Feature Vector Method with the Convolutional Neural Network for Slot Filling in Spoken Language Understanding
• Semi-supervised Learning with Contrastive Predicative Coding
• Lookup subnet based Spatial Graph Convolutional neural Network
• Phonetic-and-Semantic Embedding of Spoken Words with Applications in Spoken Content Retrieval
• Learning by stochastic serializations
• Medical Segment Coloring of Clinical Notes
• Probability Trajectory: One New Movement Description for Trajectory Prediction
• Question-Aware Sentence Gating Networks for Question and Answering
• Inductive Representation Learning in Temporal Networks via Mining Neighborhood and Community Influences
• Recurrent Neural Network-based Model Predictive Control for Continuous Pharmaceutical Manufacturing
• EmotionGIF-IITP-AINLPML: Ensemble-based Automated Deep Neural System for predicting category(ies) of a GIF response
• Continuity of Topic, Interaction, and Query: Learning to Quote in Online Conversations
• AV Taris: Online Audio-Visual Speech Recognition
• Labeled Data Generation with Inexact Supervision
• Reciprocal Supervised Learning Improves Neural Machine Translation
• Speaker and Posture Classification using Instantaneous Intraspeech Breathing Features
• Predicting Drug Responses by Propagating Interactions through Text-Enhanced Drug-Gene Networks
• Learning to Represent Bilingual Dictionaries
• Challenges and Thrills of Legal Arguments
• Dual Attentive Sequential Learning for Cross-Domain Click-Through Rate Prediction
• Latent Multi-Criteria Ratings for Recommendations
• Deep Learning Based Natural Language Processing for End to End Speech Translation
• Dropout during inference as a model for neurological degeneration in an image captioning network
• Addressee and Response Selection for Multilingual Conversation
• Channel Relationship Prediction with Forget-Update Module for Few-shot Classification
• Live Video Comment Generation Based on Surrounding Frames and Live Comments
• Linked Recurrent Neural Networks
• On the Ability of a CNN to Realize Image-to-Image Language Conversion
• A Multi-Modal Approach to Infer Image Affect
• Generative Adversarial Network for Probabilistic Forecast of Random Dynamical System
• A simple model for detection of rare sound events
• Contextual Encoding for Translation Quality Estimation
• Discovering long term dependencies in noisy time series data using deep learning
• Automatic Construction of Sememe Knowledge Bases via Dictionaries
• Hybrid Supervised Reinforced Model for Dialogue Systems
• Handling Variable-Dimensional Time Series with Graph Neural Networks
• A recurrent multi-scale approach to RBG-D Object Recognition