Neural Machine Translation by Jointly Learning to Align and Translate

Abstract

Neural machine translation is a recently proposed approach to machine translation. Unlike the traditional statistical machine translation, the neural machine translation aims at building a single neural network that can be jointly tuned to maximize the translation performance. The models proposed recently for neural machine translation often belong to a family of encoder-decoders and consists of an encoder that encodes a source sentence into a fixed-length vector from which a decoder generates a translation. In this paper, we conjecture that the use of a fixed-length vector is a bottleneck in improving the performance of this basic encoder-decoder architecture, and propose to extend this by allowing a model to automatically (soft-)search for parts of a source sentence that are relevant to predicting a target word, without having to form these parts as a hard segment explicitly. With this new approach, we achieve a translation performance comparable to the existing state-of-the-art phrase-based system on the task of English-to-French translation. Furthermore, qualitative analysis reveals that the (soft-)alignments found by the model agree well with our intuition.

Accepted at ICLR 2015 as oral presentation

References in corpus (5)

• Sequence to Sequence Learning with Neural Networks
• ADADELTA: An Adaptive Learning Rate Method
• Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation
• Sequence Transduction with Recurrent Neural Networks
• On the Properties of Neural Machine Translation: Encoder-Decoder Approaches

Cited by in corpus (1163)

• Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
• Deep learning for time series classification: a review
• Axiomatic Attribution for Deep Networks
• A Survey on Explainable Artificial Intelligence (XAI): Towards Medical XAI
• Time Series Forecasting With Deep Learning: A Survey
• Deep Learning Enabled Semantic Communication Systems
• LSTM Fully Convolutional Networks for Time Series Classification
• A Neural Conversational Model
• Explaining Deep Neural Networks and Beyond: A Review of Methods and Applications
• Recurrent Neural Networks for Time Series Forecasting: Current Status and Future Directions
• Enhanced LSTM for Natural Language Inference
• Multivariate LSTM-FCNs for Time Series Classification
• Graph Convolutional Matrix Completion
• Recent advances and clinical applications of deep learning in medical image analysis
• A Survey on the Explainability of Supervised Machine Learning
• BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain
• Show and Tell: Lessons learned from the 2015 MSCOCO Image Captioning Challenge
• A Survey of Model Compression and Acceleration for Deep Neural Networks
• Deep Learning for Audio Signal Processing
• Deep Audio-Visual Speech Recognition
• A Comparative Study on Transformer vs RNN in Speech Applications
• ConViT: Improving Vision Transformers with Soft Convolutional Inductive Biases
• Applications of deep learning in stock market prediction: recent progress
• A General Survey on Attention Mechanisms in Deep Learning
• DailyDialog: A Manually Labelled Multi-turn Dialogue Dataset
• Attention in Natural Language Processing
• SeqSleepNet: End-to-End Hierarchical Recurrent Neural Network for Sequence-to-Sequence Automatic Sleep Staging
• NAIS: Neural Attentive Item Similarity Model for Recommendation
• A Survey on Dialogue Systems: Recent Advances and New Frontiers
• Deep Learning on Traffic Prediction: Methods, Analysis and Future Directions
• Focusing Attention: Towards Accurate Text Recognition in Natural Images
• Wireless Image Transmission Using Deep Source Channel Coding With Attention Modules
• Multimodal Intelligence: Representation Learning, Information Fusion, and Applications
• An End-to-End Spatio-Temporal Attention Model for Human Action Recognition from Skeleton Data
• Session-based Social Recommendation via Dynamic Graph Attention Networks
• Understanding Neural Networks through Representation Erasure
• A Literature Survey of Recent Advances in Chatbots
• Deep attractor network for single-microphone speaker separation
• Deep Reinforcement Learning for Multi-objective Optimization
• Deep Reinforcement Learning for Page-wise Recommendations
• Light Gated Recurrent Units for Speech Recognition
• Fast Adaptive Task Offloading in Edge Computing based on Meta Reinforcement Learning
• A Survey on Accuracy-oriented Neural Recommendation: From Collaborative Filtering to Information-rich Recommendation
• End-to-end Continuous Speech Recognition using Attention-based Recurrent NN: First Results
• Improving Generalization Performance by Switching from Adam to SGD
• Artificial neural networks for neuroscientists: A primer
• SequenceR: Sequence-to-Sequence Learning for End-to-End Program Repair
• Neural Network Detection of Data Sequences in Communication Systems
• Deep Learning for Time Series Forecasting: Tutorial and Literature Survey
• Adaptive Computation Time for Recurrent Neural Networks
• A Survey of Sound Source Localization with Deep Learning Methods
• The Natural Language Decathlon: Multitask Learning as Question Answering
• Evaluating Word Embedding Models: Methods and Experimental Results
• A Generalization of Transformer Networks to Graphs
• Fast Parallel Hypertree Decompositions in Logarithmic Recursion Depth
• RetainVis: Visual Analytics with Interpretable and Interactive Recurrent Neural Networks on Electronic Medical Records
• Neural Rating Regression with Abstractive Tips Generation for Recommendation
• Collaborative Memory Network for Recommendation Systems
• MST-GAT: A Multimodal Spatial-Temporal Graph Attention Network for Time Series Anomaly Detection
• Multi-stage Attention ResU-Net for Semantic Segmentation of Fine-Resolution Remote Sensing Images
• SeqGAN: Sequence Generative Adversarial Nets with Policy Gradient
• Selective Encoding for Abstractive Sentence Summarization
• Efficiently Trainable Text-to-Speech System Based on Deep Convolutional Networks with Guided Attention
• ReasoNet: Learning to Stop Reading in Machine Comprehension
• Point Transformer
• Working Memory Connections for LSTM
• Improved training of end-to-end attention models for speech recognition
• What do Neural Machine Translation Models Learn about Morphology?
• Transfer learning for time series classification
• Training Tips for the Transformer Model
• Dual Aspect Self-Attention based on Transformer for Remaining Useful Life Prediction
• TSMixer: Lightweight MLP-Mixer Model for Multivariate Time Series Forecasting
• Visual Question Answering: Datasets, Algorithms, and Future Challenges
• Traffic Prediction using Artificial Intelligence: Review of Recent Advances and Emerging Opportunities
• Deep-learning Architecture for Short-term Passenger Flow Forecasting in Urban Rail Transit
• A Survey of Knowledge-Enhanced Text Generation
• AUTSL: A Large Scale Multi-modal Turkish Sign Language Dataset and Baseline Methods
• Temporal Attention augmented Bilinear Network for Financial Time-Series Data Analysis
• SCINet: Time Series Modeling and Forecasting with Sample Convolution and Interaction
• Image Captioning with Semantic Attention
• Attentional Encoder Network for Targeted Sentiment Classification
• A Comprehensive Study on Deep Learning-based Methods for Sign Language Recognition
• Improving Text-to-SQL Evaluation Methodology
• Crop Yield Prediction Integrating Genotype and Weather Variables Using Deep Learning
• A Survey of Information Cascade Analysis: Models, Predictions, and Recent Advances
• Neural GPUs Learn Algorithms
• Motion-Attentive Transition for Zero-Shot Video Object Segmentation
• Rendezvous: Attention Mechanisms for the Recognition of Surgical Action Triplets in Endoscopic Videos
• Quantum Entanglement in Deep Learning Architectures
• Adversarial Text-to-Image Synthesis: A Review
• Attention-based Convolutional Neural Network for Weakly Labeled Human Activities Recognition with Wearable Sensors
• Spatio-Temporal Wind Speed Forecasting using Graph Networks and Novel Transformer Architectures
• Controllable Protein Design with Language Models
• Self-Training for End-to-End Speech Recognition
• MHSA-Net: Multi-Head Self-Attention Network for Occluded Person Re-Identification
• Deep Reinforcement Learning for Electric Vehicle Routing Problem with Time Windows
• Arabic natural language processing: An overview
• Transformers for Modeling Physical Systems
• CodeBLEU: a Method for Automatic Evaluation of Code Synthesis
• SuperNNova: an open-source framework for Bayesian, Neural Network based supernova classification
• Applying Neural Networks in Optical Communication Systems: Possible Pitfalls
• Evaluating the State-of-the-Art of End-to-End Natural Language Generation: The E2E NLG Challenge
• Weakly-Supervised Neural Text Classification
• On Extended Long Short-term Memory and Dependent Bidirectional Recurrent Neural Network
• Tensor Methods in Computer Vision and Deep Learning
• Fathom: Reference Workloads for Modern Deep Learning Methods
• Adversarial Example Detection for DNN Models: A Review and Experimental Comparison
• Towards Natural Language Interfaces for Data Visualization: A Survey
• Order Matters: Sequence to sequence for sets
• wav2letter++: The Fastest Open-source Speech Recognition System
• Exploring Chemical Space using Natural Language Processing Methodologies for Drug Discovery
• Span-based Joint Entity and Relation Extraction with Transformer Pre-training
• Fast Decoding in Sequence Models using Discrete Latent Variables
• Learning Combinatorial Optimization on Graphs: A Survey with Applications to Networking
• Zoneout: Regularizing RNNs by Randomly Preserving Hidden Activations
• Getting Gender Right in Neural Machine Translation
• The NLP Cookbook: Modern Recipes for Transformer based Deep Learning Architectures
• Towards Explainable Anticancer Compound Sensitivity Prediction via Multimodal Attention-based Convolutional Encoders
• 3HAN: A Deep Neural Network for Fake News Detection
• A Survey on Aspect-Based Sentiment Classification
• Asynchronous Stochastic Gradient Descent with Delay Compensation
• AttnGAN: Fine-Grained Text to Image Generation with Attentional Generative Adversarial Networks
• Adversarial Ranking for Language Generation
• Context-Aware Visual Policy Network for Fine-Grained Image Captioning
• Neural Program Repair with Execution-based Backpropagation
• OpenTag: Open Attribute Value Extraction from Product Profiles [Deep Learning, Active Learning, Named Entity Recognition]
• Assessing The Factual Accuracy of Generated Text
• DeepMood: Modeling Mobile Phone Typing Dynamics for Mood Detection
• Script Identification in Natural Scene Image and Video Frame using Attention based Convolutional-LSTM Network
• Modeling Human Motion with Quaternion-based Neural Networks
• Is Neural Machine Translation Ready for Deployment? A Case Study on 30 Translation Directions
• A Comprehensive Overview and Comparative Analysis on Deep Learning Models: CNN, RNN, LSTM, GRU
• A3CLNN: Spatial, Spectral and Multiscale Attention ConvLSTM Neural Network for Multisource Remote Sensing Data Classification
• Robust Attentional Aggregation of Deep Feature Sets for Multi-view 3D Reconstruction
• dna2vec: Consistent vector representations of variable-length k-mers
• Ensemble learning of diffractive optical networks
• Scale- and Context-Aware Convolutional Non-intrusive Load Monitoring
• Neural Entity Linking: A Survey of Models Based on Deep Learning
• Beyond Data and Model Parallelism for Deep Neural Networks
• Rolling-Unrolling LSTMs for Action Anticipation from First-Person Video
• Unsupervised Predictive Memory in a Goal-Directed Agent
• Improvement in Land Cover and Crop Classification based on Temporal Features Learning from Sentinel-2 Data Using Recurrent-Convolutional Neural Network (R-CNN)
• Enable Deep Learning on Mobile Devices: Methods, Systems, and Applications
• A survey on efficient vision transformers: algorithms, techniques, and performance benchmarking
• Self-Attention Networks for Connectionist Temporal Classification in Speech Recognition
• A Hierarchical Structured Self-Attentive Model for Extractive Document Summarization (HSSAS)
• The Modern Mathematics of Deep Learning
• The value of text for small business default prediction: A deep learning approach
• Emotion Intensity and its Control for Emotional Voice Conversion
• Relational Neural Expectation Maximization: Unsupervised Discovery of Objects and their Interactions
• Explainable Outfit Recommendation with Joint Outfit Matching and Comment Generation
• Bangla hate speech detection on social media using attention-based recurrent neural network
• Learning a bidirectional mapping between human whole-body motion and natural language using deep recurrent neural networks
• Lifelong Sequential Modeling with Personalized Memorization for User Response Prediction
• Continual Learning for Recurrent Neural Networks: an Empirical Evaluation
• Linking the Neural Machine Translation and the Prediction of Organic Chemistry Reactions
• Curriculum Learning and Minibatch Bucketing in Neural Machine Translation
• Towards Automated ICD Coding Using Deep Learning
• Neural Networks for Entity Matching: A Survey
• A neural attention model for speech command recognition
• Context-Aware Visual Policy Network for Sequence-Level Image Captioning
• On the Explainability of Natural Language Processing Deep Models
• On the Dimensionality of Word Embedding
• Streaming keyword spotting on mobile devices
• Grammatical Error Correction: A Survey of the State of the Art
• Biomedical Question Answering: A Survey of Approaches and Challenges
• CODIT: Code Editing with Tree-Based Neural Models
• Supervised and Unsupervised Neural Approaches to Text Readability
• Style Transfer as Unsupervised Machine Translation
• DTAAD: Dual Tcn-Attention Networks for Anomaly Detection in Multivariate Time Series Data
• GA2MIF: Graph and Attention Based Two-Stage Multi-Source Information Fusion for Conversational Emotion Detection
• Compressing Recurrent Neural Network with Tensor Train
• A Syntactic Neural Model for General-Purpose Code Generation
• A Survey on Data-driven Software Vulnerability Assessment and Prioritization
• Lifelong Generative Modeling
• Contextual Hybrid Session-based News Recommendation with Recurrent Neural Networks
• Neural Turing Machines
• Learning to Reason: End-to-End Module Networks for Visual Question Answering
• Molecule Attention Transformer
• Review: Deep Learning in Electron Microscopy
• Listen, Attend, and Walk: Neural Mapping of Navigational Instructions to Action Sequences
• Aligning where to see and what to tell: image caption with region-based attention and scene factorization
• RobustFill: Neural Program Learning under Noisy I/O
• Going in circles is the way forward: the role of recurrence in visual inference
• Local-Global Context Aware Transformer for Language-Guided Video Segmentation
• Compositional Sequence Labeling Models for Error Detection in Learner Writing
• Hierarchical Text Classification with Reinforced Label Assignment
• DeepSense: A Unified Deep Learning Framework for Time-Series Mobile Sensing Data Processing
• Solving a New 3D Bin Packing Problem with Deep Reinforcement Learning Method
• Obesity Prediction with EHR Data: A deep learning approach with interpretable elements
• Inf-VAE: A Variational Autoencoder Framework to Integrate Homophily and Influence in Diffusion Prediction
• Hierarchically-Refined Label Attention Network for Sequence Labeling
• GRAM: Graph-based Attention Model for Healthcare Representation Learning
• A Deep Neural Network for Unsupervised Anomaly Detection and Diagnosis in Multivariate Time Series Data
• Physics and Equality Constrained Artificial Neural Networks: Application to Forward and Inverse Problems with Multi-fidelity Data Fusion
• Frame-Semantic Parsing with Softmax-Margin Segmental RNNs and a Syntactic Scaffold
• Advances in All-Neural Speech Recognition
• Excited state, non-adiabatic dynamics of large photoswitchable molecules using a chemically transferable machine learning potential
• End-to-End ASR-free Keyword Search from Speech
• Unsupervised Neural Machine Translation
• A Comparison of Transformer and Recurrent Neural Networks on Multilingual Neural Machine Translation
• Graph Neural Network and Spatiotemporal Transformer Attention for 3D Video Object Detection from Point Clouds
• Compositional Vector Space Models for Knowledge Base Completion
• Explainable AI for Robot Failures: Generating Explanations that Improve User Assistance in Fault Recovery
• A Survey of Malware Detection Using Deep Learning
• HUNTER: AI based Holistic Resource Management for Sustainable Cloud Computing
• Tunable Efficient Unitary Neural Networks (EUNN) and their application to RNNs
• Investigating Pose Representations and Motion Contexts Modeling for 3D Motion Prediction
• Forward Attention in Sequence-to-sequence Acoustic Modelling for Speech Synthesis
• Robust Scene Text Recognition with Automatic Rectification
• Paradigm Shift in Natural Language Processing
• Is attention all you need in medical image analysis? A review
• Sound Event Detection in Multichannel Audio Using Spatial and Harmonic Features
• Video Paragraph Captioning Using Hierarchical Recurrent Neural Networks
• Variational Deep Embedding: An Unsupervised and Generative Approach to Clustering
• Extraction of Salient Sentences from Labelled Documents
• Self-Attention Transducers for End-to-End Speech Recognition
• Modeling emotion in complex stories: the Stanford Emotional Narratives Dataset
• Every Moment Counts: Dense Detailed Labeling of Actions in Complex Videos
• A Joint Model for Question Answering and Question Generation
• OpenNMT: Neural Machine Translation Toolkit
• Automatic Text Summarization of COVID-19 Medical Research Articles using BERT and GPT-2
• Fonduer: Knowledge Base Construction from Richly Formatted Data
• Attention-Aware Compositional Network for Person Re-identification
• Weakly Labelled AudioSet Tagging with Attention Neural Networks
• Efficiently Embedding Dynamic Knowledge Graphs
• Jointly Learning Sentence Embeddings and Syntax with Unsupervised Tree-LSTMs
• MobiSR: Efficient On-Device Super-Resolution through Heterogeneous Mobile Processors
• Memory-augmented Dense Predictive Coding for Video Representation Learning
• Deep Polynomial Neural Networks
• Neural Reverse Engineering of Stripped Binaries using Augmented Control Flow Graphs
• Representation Learning for Natural Language Processing
• Toward Subgraph-Guided Knowledge Graph Question Generation with Graph Neural Networks
• Adaptive Fusion of Multi-view Remote Sensing data for Optimal Sub-field Crop Yield Prediction
• Dynamic Dense Graph Convolutional Network for Skeleton-based Human Motion Prediction
• Hopfield Networks is All You Need
• Multi-Head Attention: Collaborate Instead of Concatenate
• StaQC: A Systematically Mined Question-Code Dataset from Stack Overflow
• Lip-reading with Densely Connected Temporal Convolutional Networks
• RETURNN as a Generic Flexible Neural Toolkit with Application to Translation and Speech Recognition
• Generative Chemical Transformer: Neural Machine Learning of Molecular Geometric Structures from Chemical Language via Attention
• Neural Networks and Quantum Field Theory
• Does Multimodality Help Human and Machine for Translation and Image Captioning?
• Freezing Subnetworks to Analyze Domain Adaptation in Neural Machine Translation
• Attention-based Audio-Visual Fusion for Robust Automatic Speech Recognition
• Learning Multi-Attention Context Graph for Group-Based Re-Identification
• An Empirical Analysis of NMT-Derived Interlingual Embeddings and their Use in Parallel Sentence Identification
• Syntactically Guided Neural Machine Translation
• Augmenting Librispeech with French Translations: A Multimodal Corpus for Direct Speech Translation Evaluation
• Multilingual Neural Machine Translation with Task-Specific Attention
• A Survey of Automatic Generation of Source Code Comments: Algorithms and Techniques
• Pose-conditioned Spatio-Temporal Attention for Human Action Recognition
• Abstractive Text Summarization: State of the Art, Challenges, and Improvements
• Attention-Based Deep Learning Framework for Human Activity Recognition with User Adaptation
• SleePyCo: Automatic Sleep Scoring with Feature Pyramid and Contrastive Learning
• DeepTrack: Lightweight Deep Learning for Vehicle Path Prediction in Highways
• A newcomer's guide to deep learning for inverse design in nano-photonics
• Distance-based Self-Attention Network for Natural Language Inference
• Email Spam Detection Using Hierarchical Attention Hybrid Deep Learning Method
• Context-aware Natural Language Generation with Recurrent Neural Networks
• Short-term forecasting of solar irradiance without local telemetry: a generalized model using satellite data
• A Set of Recommendations for Assessing Human-Machine Parity in Language Translation
• Feedforward Sequential Memory Networks: A New Structure to Learn Long-term Dependency
• CLVSA: A Convolutional LSTM Based Variational Sequence-to-Sequence Model with Attention for Predicting Trends of Financial Markets
• One Chatbot Per Person: Creating Personalized Chatbots based on Implicit User Profiles
• Aspect Based Sentiment Analysis with Gated Convolutional Networks
• Pre-Translation for Neural Machine Translation
• Cloud Removal for Remote Sensing Imagery via Spatial Attention Generative Adversarial Network
• Pyramid Stereo Matching Network
• Deep learning as a tool for neural data analysis: speech classification and cross-frequency coupling in human sensorimotor cortex
• Well-calibrated Confidence Measures for Multi-label Text Classification with a Large Number of Labels
• Online Hybrid CTC/Attention End-to-End Automatic Speech Recognition Architecture
• Recursive Recurrent Nets with Attention Modeling for OCR in the Wild
• Hurricane Forecasting: A Novel Multimodal Machine Learning Framework
• Attention-Enhanced Neural Network Models for Turbulence Simulation
• Unsupervised Translation of Programming Languages
• Neural Natural Language Processing for Long Texts: A Survey on Classification and Summarization
• Action-Attending Graphic Neural Network
• MGP-AttTCN: An Interpretable Machine Learning Model for the Prediction of Sepsis
• AutoMLP: Automated MLP for Sequential Recommendations
• Fine-Grained Sports, Yoga, and Dance Postures Recognition: A Benchmark Analysis
• Psychlab: A Psychology Laboratory for Deep Reinforcement Learning Agents
• Transformation Networks for Target-Oriented Sentiment Classification
• Deep Neural Generative Model of Functional MRI Images for Psychiatric Disorder Diagnosis
• DP-GAN: Diversity-Promoting Generative Adversarial Network for Generating Informative and Diversified Text
• Syntactically Supervised Transformers for Faster Neural Machine Translation
• Deep Choice Model Using Pointer Networks for Airline Itinerary Prediction
• Energy-based Graph Convolutional Networks for Scoring Protein Docking Models
• Code Search based on Context-aware Code Translation
• Real-time Neural Network Inference on Extremely Weak Devices: Agile Offloading with Explainable AI
• Generative power of a protein language model trained on multiple sequence alignments
• Predicting Temporal Sets with Deep Neural Networks
• A Spatio-Temporal Spot-Forecasting Framework for Urban Traffic Prediction
• Deep Learning-based Sentiment Classification: A Comparative Survey
• Deep Learning for Plasma Tomography and Disruption Prediction from Bolometer Data
• Temporal Attention Model for Neural Machine Translation
• Newton-Type Methods for Non-Convex Optimization Under Inexact Hessian Information
• SGM: Sequence Generation Model for Multi-label Classification
• A Context-aware Natural Language Generator for Dialogue Systems
• SODFormer: Streaming Object Detection with Transformer Using Events and Frames
• Sequential Weakly Labeled Multi-Activity Localization and Recognition on Wearable Sensors using Recurrent Attention Networks
• Forecast Network-Wide Traffic States for Multiple Steps Ahead: A Deep Learning Approach Considering Dynamic Non-Local Spatial Correlation and Non-Stationary Temporal Dependency
• RobustART: Benchmarking Robustness on Architecture Design and Training Techniques
• Scalable End-to-end Recurrent Neural Network for Variable star classification
• Deep Learning for Sentiment Analysis : A Survey
• Deep reinforcement learning for machine scheduling: Methodology, the state-of-the-art, and future directions
• Trends in Integration of Vision and Language Research: A Survey of Tasks, Datasets, and Methods
• A Unified Query-based Generative Model for Question Generation and Question Answering
• Adversarial Robustness of Deep Code Comment Generation
• Talking-Heads Attention
• Uncertainty-Aware Deep Ensembles for Reliable and Explainable Predictions of Clinical Time Series
• Identifying Clickbait: A Multi-Strategy Approach Using Neural Networks
• Attention-based Convolutional Autoencoders for 3D-Variational Data Assimilation
• Image Captioning at Will: A Versatile Scheme for Effectively Injecting Sentiments into Image Descriptions
• A Survey on State-of-the-art Deep Learning Applications and Challenges
• Application of belief functions to medical image segmentation: A review
• Hyperbolic Attention Networks
• Quantitative Fine-Grained Human Evaluation of Machine Translation Systems: a Case Study on English to Croatian
• Transformer Encoder with Multiscale Deep Learning for Pain Classification Using Physiological Signals
• Neural Based Statement Classification for Biased Language
• I-MAD: Interpretable Malware Detector Using Galaxy Transformer
• Dual Attention Networks for Multimodal Reasoning and Matching
• Transformer-based Map Matching Model with Limited Ground-Truth Data using Transfer-Learning Approach
• Res3ATN -- Deep 3D Residual Attention Network for Hand Gesture Recognition in Videos
• A Hybrid Convolutional Variational Autoencoder for Text Generation
• Denoising Multi-Source Weak Supervision for Neural Text Classification
• Object-driven Text-to-Image Synthesis via Adversarial Training
• Semi-Supervised Variational Reasoning for Medical Dialogue Generation
• A neural network walks into a lab: towards using deep nets as models for human behavior
• Self-Supervised Hyperboloid Representations from Logical Queries over Knowledge Graphs
• Fine-Grained Fashion Similarity Prediction by Attribute-Specific Embedding Learning
• TensorOpt: Exploring the Tradeoffs in Distributed DNN Training with Auto-Parallelism
• Real-time Attention Based Look-alike Model for Recommender System
• Accurate Single Stage Detector Using Recurrent Rolling Convolution
• Describing a Knowledge Base
• Deep Weakly-Supervised Learning Methods for Classification and Localization in Histology Images: A Survey
• PaperRobot: Incremental Draft Generation of Scientific Ideas
• Sequence Length is a Domain: Length-based Overfitting in Transformer Models
• Direction-Oriented Visual-semantic Embedding Model for Remote Sensing Image-text Retrieval
• Scalable Uncertainty Quantification for Deep Operator Networks using Randomized Priors
• ProjectionNet: Learning Efficient On-Device Deep Networks Using Neural Projections
• Recommender systems based on graph embedding techniques: A comprehensive review
• Conditional Variational Autoencoder for Neural Machine Translation
• Hierarchical Recurrent Neural Encoder for Video Representation with Application to Captioning
• Joint Admission Control and Resource Allocation of Virtual Network Embedding via Hierarchical Deep Reinforcement Learning
• Parallel Attention Network with Sequence Matching for Video Grounding
• On the Replicability and Reproducibility of Deep Learning in Software Engineering
• A Multi-task Selected Learning Approach for Solving 3D Flexible Bin Packing Problem
• Artificial Intelligence and Deep Learning Algorithms for Epigenetic Sequence Analysis: A Review for Epigeneticists and AI Experts
• Reinforced Mnemonic Reader for Machine Reading Comprehension
• Generating Text with Deep Reinforcement Learning
• Tensor Programs I: Wide Feedforward or Recurrent Neural Networks of Any Architecture are Gaussian Processes
• PAtt-Lite: Lightweight Patch and Attention MobileNet for Challenging Facial Expression Recognition
• Higher Order Recurrent Neural Networks
• Speaker Adaptation for Attention-Based End-to-End Speech Recognition
• Minimizing the Bag-of-Ngrams Difference for Non-Autoregressive Neural Machine Translation
• Chess AI: Competing Paradigms for Machine Intelligence
• Attentive Memory Networks: Efficient Machine Reading for Conversational Search
• Reconstruction Network for Video Captioning
• Speech Emotion Recognition via Contrastive Loss under Siamese Networks
• Online Model-based Anomaly Detection in Multivariate Time Series: Taxonomy, Survey, Research Challenges and Future Directions
• An Introductory Survey on Attention Mechanisms in NLP Problems
• Seeing voices and hearing voices: learning discriminative embeddings using cross-modal self-supervision
• Neural ranking models for document retrieval
• Fine-Grained Trajectory-based Travel Time Estimation for Multi-city Scenarios Based on Deep Meta-Learning
• Evaluating prose style transfer with the Bible
• Diet Code Is Healthy: Simplifying Programs for Pre-trained Models of Code
• How to Teach DNNs to Pay Attention to the Visual Modality in Speech Recognition
• SCA-CNN: Spatial and Channel-wise Attention in Convolutional Networks for Image Captioning
• A Neural Entity Coreference Resolution Review
• On the Choice of Modeling Unit for Sequence-to-Sequence Speech Recognition
• Attention-based Clinical Note Summarization
• Stealing Links from Graph Neural Networks
• Graph Transformer for Graph-to-Sequence Learning
• Local minima in training of neural networks
• Neural-based machine translation for medical text domain. Based on European Medicines Agency leaflet texts
• An empirical study on the effectiveness of images in Multimodal Neural Machine Translation
• Detecting Intentional AIS Shutdown in Open Sea Maritime Surveillance Using Self-Supervised Deep Learning
• Multimodal Attention for Neural Machine Translation
• Abstract Syntax Networks for Code Generation and Semantic Parsing
• Adversarially Robust Neural Architectures
• LDNet: End-to-End Lane Marking Detection Approach Using a Dynamic Vision Sensor
• Compositional Memory for Visual Question Answering
• MSED: a multi-modal sleep event detection model for clinical sleep analysis
• Modeling Time Series Similarity with Siamese Recurrent Networks
• Attribute Recognition by Joint Recurrent Learning of Context and Correlation
• RLAS-BIABC: A Reinforcement Learning-Based Answer Selection Using the BERT Model Boosted by an Improved ABC Algorithm
• Point2Sequence: Learning the Shape Representation of 3D Point Clouds with an Attention-based Sequence to Sequence Network
• Graph Constrained Reinforcement Learning for Natural Language Action Spaces
• Dual-Primal Graph Convolutional Networks
• Temporal Self-Attention Network for Medical Concept Embedding
• Comparative evaluation of CNN architectures for Image Caption Generation
• Avoiding Latent Variable Collapse With Generative Skip Models
• Universal Multimodal Representation for Language Understanding
• STING: Self-attention based Time-series Imputation Networks using GAN
• Fine-Pruning: Defending Against Backdooring Attacks on Deep Neural Networks
• Multilingual NMT with a language-independent attention bridge
• OpenViVQA: Task, Dataset, and Multimodal Fusion Models for Visual Question Answering in Vietnamese
• 3G structure for image caption generation
• Kronecker Attention Networks
• Learning to Select, Track, and Generate for Data-to-Text
• Spatial-temporal Conv-sequence Learning with Accident Encoding for Traffic Flow Prediction
• Speech2Vec: A Sequence-to-Sequence Framework for Learning Word Embeddings from Speech
• Keyphrase Generation for Scientific Document Retrieval
• Wasserstein Generative Adversarial Uncertainty Quantification in Physics-Informed Neural Networks
• Emergence of Compositional Language with Deep Generational Transmission
• A Spatial-Temporal Graph Neural Network Framework for Automated Software Bug Triaging
• Energy-Based Reranking: Improving Neural Machine Translation Using Energy-Based Models
• MetaMT,a MetaLearning Method Leveraging Multiple Domain Data for Low Resource Machine Translation
• Variational Context: Exploiting Visual and Textual Context for Grounding Referring Expressions
• Improving Sequence-to-Sequence Acoustic Modeling by Adding Text-Supervision
• Unifying Two-Stream Encoders with Transformers for Cross-Modal Retrieval
• Variational Neural Machine Translation
• Exploiting Multi-domain Visual Information for Fake News Detection
• What value do explicit high level concepts have in vision to language problems?
• Neural Text Generation: A Practical Guide
• Drug-Drug Interaction Extraction from Biomedical Text Using Long Short Term Memory Network
• Multi-View Self-Attention for Interpretable Drug-Target Interaction Prediction
• Technical Q&A Site Answer Recommendation via Question Boosting
• Automating the Correctness Assessment of AI-generated Code for Security Contexts
• Cerebro: Static Subsuming Mutant Selection
• Adaptive Dependency Learning Graph Neural Networks
• One model Packs Thousands of Items with Recurrent Conditional Query Learning
• Predicting Drivers' Route Trajectories in Last-Mile Delivery Using A Pair-wise Attention-based Pointer Neural Network
• Improving Neural Machine Translation Robustness via Data Augmentation: Beyond Back Translation
• Forecasting future action sequences with attention: a new approach to weakly supervised action forecasting
• Character-Based Handwritten Text Transcription with Attention Networks
• Clinical Insights: A Comprehensive Review of Language Models in Medicine
• Edge-based sequential graph generation with recurrent neural networks
• A cross-corpus study on speech emotion recognition
• A Multi-Modal Chinese Poetry Generation Model
• Granger-causal Attentive Mixtures of Experts: Learning Important Features with Neural Networks
• Towards Automated Customer Support
• Putting Question-Answering Systems into Practice: Transfer Learning for Efficient Domain Customization
• AGRNet: Adaptive Graph Representation Learning and Reasoning for Face Parsing
• Extracting Parallel Sentences with Bidirectional Recurrent Neural Networks to Improve Machine Translation
• Joint Training for Neural Machine Translation Models with Monolingual Data
• A social context-aware graph-based multimodal attentive learning framework for disaster content classification during emergencies: a benchmark dataset and method
• Amobee at SemEval-2018 Task 1: GRU Neural Network with a CNN Attention Mechanism for Sentiment Classification
• ElasticTrainer: Speeding Up On-Device Training with Runtime Elastic Tensor Selection
• Tropical Geometry of Deep Neural Networks
• Show, Attend and Interact: Perceivable Human-Robot Social Interaction through Neural Attention Q-Network
• Learning to Extract Coherent Summary via Deep Reinforcement Learning
• Capitalization and Punctuation Restoration: a Survey
• VD-BERT: A Unified Vision and Dialog Transformer with BERT
• TinySpeech: Attention Condensers for Deep Speech Recognition Neural Networks on Edge Devices
• Neural Machine Reading Comprehension: Methods and Trends
• End-to-End Self-Debiasing Framework for Robust NLU Training
• Text normalization using memory augmented neural networks
• Discrete and continuous representations and processing in deep learning: Looking forward
• Compositional Generalization by Learning Analytical Expressions
• Attention Meets Perturbations: Robust and Interpretable Attention with Adversarial Training
• DivGraphPointer: A Graph Pointer Network for Extracting Diverse Keyphrases
• ValueNet: A New Dataset for Human Value Driven Dialogue System
• Extracting Sentence Embeddings from Pretrained Transformer Models
• Constrained Deep Reinforcement Based Functional Split Optimization in Virtualized RANs
• Impedance-optical Dual-modal Cell Culture Imaging with Learning-based Information Fusion
• Inseq: An Interpretability Toolkit for Sequence Generation Models
• Synthesizing Speech from Intracranial Depth Electrodes using an Encoder-Decoder Framework
• Visual Intelligence through Human Interaction
• Context-Aware Self-Attention Networks
• Accelerating Transformer Inference for Translation via Parallel Decoding
• Deep Learning Based Simulators for the Phosphorus Removal Process Control in Wastewater Treatment via Deep Reinforcement Learning Algorithms
• Improving the Detection of Small Oriented Objects in Aerial Images
• Signed Distance-based Deep Memory Recommender
• Well Googled is Half Done: Multimodal Forecasting of New Fashion Product Sales with Image-based Google Trends
• Sketch-based Creativity Support Tools using Deep Learning
• DeepSignals: Predicting Intent of Drivers Through Visual Signals
• Toward a Better Monitoring Statistic for Profile Monitoring via Variational Autoencoders
• Pediatric Automatic Sleep Staging: A comparative study of state-of-the-art deep learning methods
• Unseen Target Stance Detection with Adversarial Domain Generalization
• Regularizing RNNs for Caption Generation by Reconstructing The Past with The Present
• COVID-19 Screening Using Residual Attention Network an Artificial Intelligence Approach
• Towards a Neural Network Approach to Abstractive Multi-Document Summarization
• Enhance the Motion Cues for Face Anti-Spoofing using CNN-LSTM Architecture
• A Robust Deep Ensemble Classifier for Figurative Language Detection
• scb-mt-en-th-2020: A Large English-Thai Parallel Corpus
• Understanding Hidden Memories of Recurrent Neural Networks
• An End-to-end Neural Natural Language Interface for Databases
• Transcribing Content from Structural Images with Spotlight Mechanism
• Evolving Modular Soft Robots without Explicit Inter-Module Communication using Local Self-Attention
• Low-Resource Text Classification using Domain-Adversarial Learning
• Keyphrase Generation: A Text Summarization Struggle
• Efficient Quantized Sparse Matrix Operations on Tensor Cores
• Explaining Software Bugs Leveraging Code Structures in Neural Machine Translation
• Mathematical Models of Overparameterized Neural Networks
• MeDAL: Medical Abbreviation Disambiguation Dataset for Natural Language Understanding Pretraining
• Operationally meaningful representations of physical systems in neural networks
• Out-of-Distribution Detection using Multiple Semantic Label Representations
• Assessing the Tolerance of Neural Machine Translation Systems Against Speech Recognition Errors
• Design Challenges in Named Entity Transliteration
• Self-Explaining Structures Improve NLP Models
• Deep Sequence Modeling: Development and Applications in Asset Pricing
• A Unified Model for Extractive and Abstractive Summarization using Inconsistency Loss
• Attention on Personalized Clinical Decision Support System: Federated Learning Approach
• Context-aware Captions from Context-agnostic Supervision
• A community-powered search of machine learning strategy space to find NMR property prediction models
• Style Mixer: Semantic-aware Multi-Style Transfer Network
• Generating synthetic mobility data for a realistic population with RNNs to improve utility and privacy
• Video Crowd Localization with Multi-focus Gaussian Neighborhood Attention and a Large-Scale Benchmark
• Boosting Neural Networks to Decompile Optimized Binaries
• On Extractive and Abstractive Neural Document Summarization with Transformer Language Models
• A Comprehensive Survey of Grammar Error Correction
• KOHTD: Kazakh Offline Handwritten Text Dataset
• An Expandable Machine Learning-Optimization Framework to Sequential Decision-Making
• Discriminative Neural Clustering for Speaker Diarisation
• Informative Visual Storytelling with Cross-modal Rules
• Binding via Reconstruction Clustering
• Attention-Based Multimodal Fusion for Video Description
• Attention-based Modeling for Emotion Detection and Classification in Textual Conversations
• Can We Generate Shellcodes via Natural Language? An Empirical Study
• LCSTS: A Large Scale Chinese Short Text Summarization Dataset
• LAVARNET: Neural Network Modeling of Causal Variable Relationships for Multivariate Time Series Forecasting
• Summarization, Simplification, and Generation: The Case of Patents
• Cross Modal Compression: Towards Human-comprehensible Semantic Compression
• Context in Neural Machine Translation: A Review of Models and Evaluations
• Experiment Segmentation in Scientific Discourse as Clause-level Structured Prediction using Recurrent Neural Networks
• Structure-Tags Improve Text Classification for Scholarly Document Quality Prediction
• Paper Abstract Writing through Editing Mechanism
• ORDNet: Capturing Omni-Range Dependencies for Scene Parsing
• Self-Supervised and Invariant Representations for Wireless Localization
• Encoders Help You Disambiguate Word Senses in Neural Machine Translation
• Analyzing analytical methods: The case of phonology in neural models of spoken language
• Global Encoding for Abstractive Summarization
• Cell Attention Networks
• Giving Commands to a Self-Driving Car: How to Deal with Uncertain Situations?
• Automated Question Answer medical model based on Deep Learning Technology
• Pile-Up Mitigation using Attention
• Exploiting Multiple Sequence Lengths in Fast End to End Training for Image Captioning
• Forecasting GICs and geoelectric fields from solar wind data using LSTMs: application in Austria
• An Exploration of Word Embedding Initialization in Deep-Learning Tasks
• Wind Park Power Prediction: Attention-Based Graph Networks and Deep Learning to Capture Wake Losses
• An Analysis of Abstractive Text Summarization Using Pre-trained Models
• CoT: Cooperative Training for Generative Modeling of Discrete Data
• Emotion-Aware Transformer Encoder for Empathetic Dialogue Generation
• Embedding API Dependency Graph for Neural Code Generation
• AEDNet: Adaptive Edge-Deleting Network For Subgraph Matching
• Homograph Disambiguation Through Selective Diacritic Restoration
• Confidence through Attention
• Sequential Recommendation with Graph Neural Networks
• KnowledgeVIS: Interpreting Language Models by Comparing Fill-in-the-Blank Prompts
• On the Importance of Delexicalization for Fact Verification
• Generation of Highlights from Research Papers Using Pointer-Generator Networks and SciBERT Embeddings
• Towards Complex Text-to-SQL in Cross-Domain Database with Intermediate Representation
• Exploration of Neural Machine Translation in Autoformalization of Mathematics in Mizar
• QCRI Machine Translation Systems for IWSLT 16
• Efficient Transformer-based Speech Enhancement Using Long Frames and STFT Magnitudes
• DeepTransport: Learning Spatial-Temporal Dependency for Traffic Condition Forecasting
• Metasql: A Generate-then-Rank Framework for Natural Language to SQL Translation
• Sequential Context Encoding for Duplicate Removal
• QA4IE: A Question Answering based Framework for Information Extraction
• Grounded Recurrent Neural Networks
• Multi-View Collaborative Network Embedding
• CS-MLGCN : Multiplex Graph Convolutional Networks for Community Search in Multiplex Networks
• SkipFlow: Incorporating Neural Coherence Features for End-to-End Automatic Text Scoring
• Robust Neural Abstractive Summarization Systems and Evaluation against Adversarial Information
• Non-uniform Motion Deblurring with Blurry Component Divided Guidance
• Guiding Neural Machine Translation with Retrieved Translation Pieces
• SPASS: Scientific Prominence Active Search System with Deep Image Captioning Network
• A Semantic Relevance Based Neural Network for Text Summarization and Text Simplification
• Covid-Transformer: Detecting COVID-19 Trending Topics on Twitter Using Universal Sentence Encoder
• Relevance Transformer: Generating Concise Code Snippets with Relevance Feedback
• Wat zei je? Detecting Out-of-Distribution Translations with Variational Transformers
• A Machine Learning Approach to Routing
• Relational Collaborative Filtering:Modeling Multiple Item Relations for Recommendation
• MatSciRE: Leveraging Pointer Networks to Automate Entity and Relation Extraction for Material Science Knowledge-base Construction
• On the Benefit of Combining Neural, Statistical and External Features for Fake News Identification
• Non-Autoregressive Machine Translation with Auxiliary Regularization
• A Dataset and Benchmark Towards Multi-Modal Face Anti-Spoofing Under Surveillance Scenarios
• Bengali Abstractive News Summarization(BANS): A Neural Attention Approach
• Modeling citation worthiness by using attention-based bidirectional long short-term memory networks and interpretable models
• SurgiTrack: Fine-Grained Multi-Class Multi-Tool Tracking in Surgical Videos
• Entropy-Enhanced Multimodal Attention Model for Scene-Aware Dialogue Generation
• Transfer Learning for Clinical Time Series Analysis using Recurrent Neural Networks
• Weakly-supervised Contextualization of Knowledge Graph Facts
• Self-Attentive Residual Decoder for Neural Machine Translation
• Neural Discourse Relation Recognition with Semantic Memory
• SANE-TTS: Stable And Natural End-to-End Multilingual Text-to-Speech
• Doubly Attentive Transformer Machine Translation
• Learning to Focus: Cascaded Feature Matching Network for Few-shot Image Recognition
• Pose2Trajectory: Using Transformers on Body Pose to Predict Tennis Player's Trajectory
• Recurrent Attention Unit
• Learning Convolutional Text Representations for Visual Question Answering
• Heterogeneous Target Speech Separation
• A Constrained Sequence-to-Sequence Neural Model for Sentence Simplification
• Deep multi-task mining Calabi-Yau four-folds
• Generating Descriptions with Grounded and Co-Referenced People
• Graph-Segmenter: Graph Transformer with Boundary-aware Attention for Semantic Segmentation
• PTransIPs: Identification of phosphorylation sites enhanced by protein PLM embeddings
• VQA-MHUG: A Gaze Dataset to Study Multimodal Neural Attention in Visual Question Answering
• TTS-Portuguese Corpus: a corpus for speech synthesis in Brazilian Portuguese
• COSPLAY: Concept Set Guided Personalized Dialogue Generation Across Both Party Personas
• Domain Control for Neural Machine Translation
• Neural Machine Translation with Monolingual Translation Memory
• Word-level Sign Language Recognition with Multi-stream Neural Networks Focusing on Local Regions and Skeletal Information
• Skeleton Key: Image Captioning by Skeleton-Attribute Decomposition
• Hierarchical Aggregations for High-Dimensional Multiplex Graph Embedding
• Neural Network-Based Abstract Generation for Opinions and Arguments
• Production Ready Chatbots: Generate if not Retrieve
• Grounding Referring Expressions in Images by Variational Context
• Attention Optimization for Abstractive Document Summarization
• "You Know What to Do": Proactive Detection of YouTube Videos Targeted by Coordinated Hate Attacks
• Exploiting Linguistic Resources for Neural Machine Translation Using Multi-task Learning
• Dial2Desc: End-to-end Dialogue Description Generation
• Multilingual Name Entity Recognition and Intent Classification Employing Deep Learning Architectures
• Named Entity Disambiguation using Deep Learning on Graphs
• SALSA-TEXT : self attentive latent space based adversarial text generation
• Neural Machine Translation with Noisy Lexical Constraints
• Hierarchical Matching and Reasoning for Multi-Query Image Retrieval
• A Static and Dynamic Attention Framework for Multi Turn Dialogue Generation
• Aspect-Based Relational Sentiment Analysis Using a Stacked Neural Network Architecture
• Towards Understanding Theoretical Advantages of Complex-Reaction Networks
• Neural Personalized Response Generation as Domain Adaptation
• Question Answering over Knowledge Base using Language Model Embeddings
• CATA++: A Collaborative Dual Attentive Autoencoder Method for Recommending Scientific Articles
• DeepIntent: ImplicitIntent based Android IDS with E2E Deep Learning architecture
• LSTMVis: A Tool for Visual Analysis of Hidden State Dynamics in Recurrent Neural Networks
• Efficient Folded Attention for 3D Medical Image Reconstruction and Segmentation
• Visual Question Answering with Memory-Augmented Networks
• Pop Music Highlighter: Marking the Emotion Keypoints
• Dual Ask-Answer Network for Machine Reading Comprehension
• Progressive Transformers for End-to-End Sign Language Production
• Fact-based Text Editing
• Relative Positional Encoding for Transformers with Linear Complexity
• A Condense-then-Select Strategy for Text Summarization
• Deconvolution-Based Global Decoding for Neural Machine Translation
• Deep Recurrent Neural Network for Protein Function Prediction from Sequence
• SAC: Accelerating and Structuring Self-Attention via Sparse Adaptive Connection
• Plasma Confinement Mode Classification Using a Sequence-to-Sequence Neural Network With Attention
• Detecting mental disorder on social media: a ChatGPT-augmented explainable approach
• Transforming the Bootstrap: Using Transformers to Compute Scattering Amplitudes in Planar N = 4 Super Yang-Mills Theory
• Unsupervised Word Segmentation from Speech with Attention
• Polyglot Semantic Parsing in APIs
• Learning to Optimize in Swarms
• Tensor2Tensor for Neural Machine Translation
• Fair Comparison: Quantifying Variance in Resultsfor Fine-grained Visual Categorization
• Textual Explanations for Self-Driving Vehicles
• Self-Attentional Credit Assignment for Transfer in Reinforcement Learning
• End-to-End Spoken Language Understanding: Performance analyses of a voice command task in a low resource setting
• AAG-Stega: Automatic Audio Generation-based Steganography
• Machine learning classification of non-Markovian noise disturbing quantum dynamics
• Because Every Sensor Is Unique, so Is Every Pair: Handling Dynamicity in Traffic Forecasting
• Folksonomication: Predicting Tags for Movies from Plot Synopses Using Emotion Flow Encoded Neural Network
• PharmMT: A Neural Machine Translation Approach to Simplify Prescription Directions
• Multi-organ segmentation: a progressive exploration of learning paradigms under scarce annotation
• Convolution-enhanced Evolving Attention Networks
• CodeSum: Translate Program Language to Natural Language
• Deep Learning-Based Modeling of 5G Core Control Plane for 5G Network Digital Twin
• CSVideoNet: A Real-time End-to-end Learning Framework for High-frame-rate Video Compressive Sensing
• Dual-interest Factorization-heads Attention for Sequential Recommendation
• Why Do Masked Neural Language Models Still Need Common Sense Knowledge?
• A Dual-Stream Recurrence-Attention Network With Global-Local Awareness for Emotion Recognition in Textual Dialog
• Planning on the fast lane: Learning to interact using attention mechanisms in path integral inverse reinforcement learning
• Detecting Backdoors in Neural Networks Using Novel Feature-Based Anomaly Detection
• Sequential Interpretability: Methods, Applications, and Future Direction for Understanding Deep Learning Models in the Context of Sequential Data
• Emphasizing Unseen Words: New Vocabulary Acquisition for End-to-End Speech Recognition
• DeepSI: Interactive Deep Learning for Semantic Interaction
• MM-ALT: A Multimodal Automatic Lyric Transcription System
• A Minimal Span-Based Neural Constituency Parser
• Learning Second-Order Attentive Context for Efficient Correspondence Pruning
• A Multi-Object Rectified Attention Network for Scene Text Recognition
• Autonomization of Monoidal Categories
• Sequence-to-sequence models for workload interference
• Simplify-then-Translate: Automatic Preprocessing for Black-Box Machine Translation
• Context- and Sequence-Aware Convolutional Recurrent Encoder for Neural Machine Translation
• EdgeRec: Recommender System on Edge in Mobile Taobao
• Adapting the Neural Encoder-Decoder Framework from Single to Multi-Document Summarization
• $k$-Nearest Neighbor Augmented Neural Networks for Text Classification
• Decentralized policy learning with partial observation and mechanical constraints for multiperson modeling
• Adversarial System Variant Approximation to Quantify Process Model Generalization
• Prior Knowledge Driven Label Embedding for Slot Filling in Natural Language Understanding
• A Deep Learning Approach with an Attention Mechanism for Automatic Sleep Stage Classification
• WAY: Estimation of Vessel Destination in Worldwide AIS Trajectory
• Improving Device Directedness Classification of Utterances with Semantic Lexical Features
• Acquiring Knowledge from Pre-trained Model to Neural Machine Translation
• Flow-based Spatio-Temporal Structured Prediction of Motion Dynamics
• An Effective Automatic Image Annotation Model Via Attention Model and Data Equilibrium
• A Hierarchical Contextual Attention-based GRU Network for Sequential Recommendation
• Enhance Temporal Relations in Audio Captioning with Sound Event Detection
• DenseAttentionSeg: Segment Hands from Interacted Objects Using Depth Input
• Recent Advances in Text Analysis
• DeepCover: Advancing RNN Test Coverage and Online Error Prediction using State Machine Extraction
• In Conclusion Not Repetition: Comprehensive Abstractive Summarization With Diversified Attention Based On Determinantal Point Processes
• Incremental Adaptation of NMT for Professional Post-editors: A User Study
• CoVA: Context-aware Visual Attention for Webpage Information Extraction
• Identifying Harm Events in Clinical Care through Medical Narratives
• Reducing Bias in Production Speech Models
• Towards Understanding Neural Machine Translation with Word Importance
• SEMOUR: A Scripted Emotional Speech Repository for Urdu
• Grounded Conversation Generation as Guided Traverses in Commonsense Knowledge Graphs
• A Reinforced Generation of Adversarial Examples for Neural Machine Translation
• Learn To Remember: Transformer with Recurrent Memory for Document-Level Machine Translation
• On the comparability of Pre-trained Language Models
• Leveraging Subword Embeddings for Multinational Address Parsing
• Neural Machine Translation with Word Predictions
• From Handcrafted Features to LLMs: A Brief Survey for Machine Translation Quality Estimation
• DeepMnemonic: Password Mnemonic Generation via Deep Attentive Encoder-Decoder Model
• Human Action Generation with Generative Adversarial Networks
• A Deep Prediction Network for Understanding Advertiser Intent and Satisfaction
• Cascaded Text Generation with Markov Transformers
• Differentiable architecture search with multi-dimensional attention for spiking neural networks
• Sparse Attentive Memory Network for Click-through Rate Prediction with Long Sequences
• Interpreting Recurrent and Attention-Based Neural Models: a Case Study on Natural Language Inference
• Unified Question Generation with Continual Lifelong Learning
• A Re-classification of Information Seeking Tasks and Their Computational Solutions
• Neural Network Methods for Radiation Detectors and Imaging
• Recurrent Neural Networks for Fuzz Testing Web Browsers
• Can Neural Networks Understand Logical Entailment?
• Gradient Scheduling with Global Momentum for Non-IID Data Distributed Asynchronous Training
• Transformer-Based Neural Text Generation with Syntactic Guidance
• LEAN: Light and Efficient Audio Classification Network
• Multi-turn Inference Matching Network for Natural Language Inference
• Multilingual Multi-Aspect Explainability Analyses on Machine Reading Comprehension Models
• Adaptive Parameterization for Neural Dialogue Generation
• A Comparison of Feature-Based and Neural Scansion of Poetry
• Hierarchical Context Tagging for Utterance Rewriting
• Context, Attention and Audio Feature Explorations for Audio Visual Scene-Aware Dialog
• Improving Generalization of Transfer Learning Across Domains Using Spatio-Temporal Features in Autonomous Driving
• Explainable Fact-checking through Question Answering
• Mutual Information Scaling and Expressive Power of Sequence Models
• Learning Edge Properties in Graphs from Path Aggregations
• Building a Parallel Corpus and Training Translation Models Between Luganda and English
• Stacked Cross-modal Feature Consolidation Attention Networks for Image Captioning
• OCoR: An Overlapping-Aware Code Retriever
• Exploring TTS without T Using Biologically/Psychologically Motivated Neural Network Modules (ZeroSpeech 2020)
• Autoencoder as Assistant Supervisor: Improving Text Representation for Chinese Social Media Text Summarization
• Neural Baselines for Word Alignment
• Automatically Labeling Low Quality Content on Wikipedia by Leveraging Patterns in Editing Behaviors
• Neural Machine Translation with Byte-Level Subwords
• MA-VAE: Multi-head Attention-based Variational Autoencoder Approach for Anomaly Detection in Multivariate Time-series Applied to Automotive Endurance Powertrain Testing
• Abstractive Text Summarization using Attentive GRU based Encoder-Decoder
• Do End-to-End Speech Recognition Models Care About Context?
• Practical Program Repair via Preference-based Ensemble Strategy
• Learning to Perform Role-Filler Binding with Schematic Knowledge
• Attention-based Neural Load Forecasting: A Dynamic Feature Selection Approach
• DPCSpell: A Transformer-based Detector-Purificator-Corrector Framework for Spelling Error Correction of Bangla and Resource Scarce Indic Languages
• Translation-Enhanced Multilingual Text-to-Image Generation
• Dynamic Multi-Branch Layers for On-Device Neural Machine Translation
• AdCOFE: Advanced Contextual Feature Extraction in Conversations for emotion classification
• On Synthetic Data for Back Translation
• Enhancing Keyphrase Extraction from Microblogs using Human Reading Time
• Multi-Task Learning with Shared Encoder for Non-Autoregressive Machine Translation
• Non-Fluent Synthetic Target-Language Data Improve Neural Machine Translation
• An Interpretable Deep Learning System for Automatically Scoring Request for Proposals
• Proactive Prioritization of App Issues via Contrastive Learning
• A Unifying Framework of Attention-based Neural Load Forecasting
• PriGen: Towards Automated Translation of Android Applications' Code to Privacy Captions
• Improving Sentiment Analysis By Emotion Lexicon Approach on Vietnamese Texts
• Secost: Sequential co-supervision for large scale weakly labeled audio event detection
• XAI Methods for Neural Time Series Classification: A Brief Review
• Modeling user context for valence prediction from narratives
• Does Yoga Make You Happy? Analyzing Twitter User Happiness using Textual and Temporal Information
• Modeling relation paths for knowledge base completion via joint adversarial training
• Dual Pointer Network for Fast Extraction of Multiple Relations in a Sentence
• Program Language Translation Using a Grammar-Driven Tree-to-Tree Model
• Incremental Natural Language Processing: Challenges, Strategies, and Evaluation
• An attention-based Bi-GRU-CapsNet model for hypernymy detection between compound entities
• AttendNets: Tiny Deep Image Recognition Neural Networks for the Edge via Visual Attention Condensers
• Fine-Tuning by Curriculum Learning for Non-Autoregressive Neural Machine Translation
• Multi-Component Graph Convolutional Collaborative Filtering
• A multi-label classification method using a hierarchical and transparent representation for paper-reviewer recommendation
• Recognizing Handwritten Mathematical Expressions as LaTex Sequences Using a Multiscale Robust Neural Network
• Visually Grounded Word Embeddings and Richer Visual Features for Improving Multimodal Neural Machine Translation
• Chunk-Based Bi-Scale Decoder for Neural Machine Translation
• Towards Neural Decompilation
• Instance-aware Image and Sentence Matching with Selective Multimodal LSTM
• Why Pay More When You Can Pay Less: A Joint Learning Framework for Active Feature Acquisition and Classification
• Generating captions without looking beyond objects
• Multimodal Memory Modelling for Video Captioning
• Attention based end to end Speech Recognition for Voice Search in Hindi and English
• Guiding attention in Sequence-to-sequence models for Dialogue Act prediction
• Neural Class Expression Synthesis
• WikiReading: A Novel Large-scale Language Understanding Task over Wikipedia
• Structured-based Curriculum Learning for End-to-end English-Japanese Speech Translation
• Analysis of Twitter Users' Lifestyle Choices using Joint Embedding Model
• GraphFM: Graph Factorization Machines for Feature Interaction Modeling
• PARK: Personalized academic retrieval with knowledge-graphs
• On the Gap Between Strict-Saddles and True Convexity: An Omega(log d) Lower Bound for Eigenvector Approximation
• Neural Chinese Word Segmentation as Sequence to Sequence Translation
• End2End Acoustic to Semantic Transduction
• Autonomous In-Situ Soundscape Augmentation via Joint Selection of Masker and Gain
• Churn Intent Detection in Multilingual Chatbot Conversations and Social Media
• Machine Translation Approaches and Survey for Indian Languages
• Multi-node Bert-pretraining: Cost-efficient Approach
• A Context-Aware User-Item Representation Learning for Item Recommendation
• Sparsely constrained neural networks for model discovery of PDEs
• To Compress, or Not to Compress: Characterizing Deep Learning Model Compression for Embedded Inference
• Towards Proof Synthesis Guided by Neural Machine Translation for Intuitionistic Propositional Logic
• Probing Neural Dialog Models for Conversational Understanding
• Syntactic Scaffolds for Semantic Structures
• Dense Recurrent Neural Networks for Scene Labeling
• Transformers for End-to-End InfoSec Tasks: A Feasibility Study
• CAPE: Encoding Relative Positions with Continuous Augmented Positional Embeddings
• Efficiency Metrics for Data-Driven Models: A Text Summarization Case Study
• MUSE: Music Recommender System with Shuffle Play Recommendation Enhancement
• Diverse Pretrained Context Encodings Improve Document Translation
• Spatio-Temporal Momentum: Jointly Learning Time-Series and Cross-Sectional Strategies
• Generating Responses Expressing Emotion in an Open-domain Dialogue System
• SocialInteractionGAN: Multi-person Interaction Sequence Generation
• Categorical Representation Learning: Morphism is All You Need
• SideControl: Controlled Open-domain Dialogue Generation via Additive Side Networks
• A Multi-task Multi-stage Transitional Training Framework for Neural Chat Translation
• End-to-End Multi-View Networks for Text Classification
• SuperChat: Dialogue Generation by Transfer Learning from Vision to Language using Two-dimensional Word Embedding and Pretrained ImageNet CNN Models
• LSTM Easy-first Dependency Parsing with Pre-trained Word Embeddings and Character-level Word Embeddings in Vietnamese
• Unsupervised Cyberbullying Detection via Time-Informed Gaussian Mixture Model
• Utilizing Character and Word Embeddings for Text Normalization with Sequence-to-Sequence Models
• Towards Abstraction from Extraction: Multiple Timescale Gated Recurrent Unit for Summarization
• Towards Faithfulness in Open Domain Table-to-text Generation from an Entity-centric View
• Heterogeneity-aware Cross-school Electives Recommendation: a Hybrid Federated Approach
• Insights on Neural Representations for End-to-End Speech Recognition
• Adding Knowledge to Unsupervised Algorithms for the Recognition of Intent
• Deep Learning in Multiple Multistep Time Series Prediction
• Delving Deeper into the Decoder for Video Captioning
• Set-to-Sequence Methods in Machine Learning: a Review
• Object Based Attention Through Internal Gating
• Top-down Visual Saliency Guided by Captions
• Recurrent Neural Networks as Weighted Language Recognizers
• Robust Beam Search for Encoder-Decoder Attention Based Speech Recognition without Length Bias
• Low-rank passthrough neural networks
• AGBoost: Attention-based Modification of Gradient Boosting Machine
• Modeling Attention Flow on Graphs
• Revisiting Random Forests in a Comparative Evaluation of Graph Convolutional Neural Network Variants for Traffic Prediction
• Product Title Generation for Conversational Systems using BERT
• Tag-less Back-Translation
• Improving Neural Text Simplification Model with Simplified Corpora
• Hamming OCR: A Locality Sensitive Hashing Neural Network for Scene Text Recognition
• Automatically Generating Commit Messages from Diffs using Neural Machine Translation
• Clustering Text Using Attention
• Capacity Control of ReLU Neural Networks by Basis-path Norm
• Towards Natural Language Question Answering over Earth Observation Linked Data using Attention-based Neural Machine Translation
• NUIG-Shubhanker@Dravidian-CodeMix-FIRE2020: Sentiment Analysis of Code-Mixed Dravidian text using XLNet
• Approximating meta-heuristics with homotopic recurrent neural networks
• Regularizing Output Distribution of Abstractive Chinese Social Media Text Summarization for Improved Semantic Consistency
• Action Classification and Highlighting in Videos
• Sentiment Analysis with Contextual Embeddings and Self-Attention
• Image Captioning with Object Detection and Localization
• Parallel and Limited Data Voice Conversion Using Stochastic Variational Deep Kernel Learning
• Would You Ask it that Way? Measuring and Improving Question Naturalness for Knowledge Graph Question Answering
• Improving Semantic Relevance for Sequence-to-Sequence Learning of Chinese Social Media Text Summarization
• Sentiment Analysis on Inflation after Covid-19
• Empowering A* Search Algorithms with Neural Networks for Personalized Route Recommendation
• SelfSeg: A Self-supervised Sub-word Segmentation Method for Neural Machine Translation
• Automatic Conditional Generation of Personalized Social Media Short Texts
• Improving Neural Machine Translation with Pre-trained Representation
• MQTransformer: Multi-Horizon Forecasts with Context Dependent and Feedback-Aware Attention
• Semi-supervised Multimodal Representation Learning through a Global Workspace
• Visualizing RNN States with Predictive Semantic Encodings
• Exploring Retraining-Free Speech Recognition for Intra-sentential Code-Switching
• Algorithms For Automatic Accentuation And Transcription Of Russian Texts In Speech Recognition Systems
• The Costs and Benefits of Goal-Directed Attention in Deep Convolutional Neural Networks
• Untangling tradeoffs between recurrence and self-attention in neural networks
• An Efficient Character-Level Neural Machine Translation
• Modeling Fluency and Faithfulness for Diverse Neural Machine Translation
• Multi Agent Navigation in Unconstrained Environments using a Centralized Attention based Graphical Neural Network Controller
• Korean-to-Chinese Machine Translation using Chinese Character as Pivot Clue
• Learning to Optimise General TSP Instances
• Towards Solving Text-based Games by Producing Adaptive Action Spaces
• How To Evaluate Your Dialogue System: Probe Tasks as an Alternative for Token-level Evaluation Metrics
• Automated proof synthesis for propositional logic with deep neural networks
• Multimodal Dialogue State Tracking By QA Approach with Data Augmentation
• Self-Attention Enhanced Patient Journey Understanding in Healthcare System
• Jointly Trained Sequential Labeling and Classification by Sparse Attention Neural Networks
• A Study of the Plausibility of Attention between RNN Encoders in Natural Language Inference
• ViNTER: Image Narrative Generation with Emotion-Arc-Aware Transformer
• Measuring Faithful and Plausible Visual Grounding in VQA
• Optimal Mini-Batch Size Selection for Fast Gradient Descent
• A State-of-the-art Survey of Artificial Neural Networks for Whole-slide Image Analysis:from Popular Convolutional Neural Networks to Potential Visual Transformers
• This Reads Like That: Deep Learning for Interpretable Natural Language Processing
• Be Concise and Precise: Synthesizing Open-Domain Entity Descriptions from Facts
• A human-inspired recognition system for premodern Japanese historical documents
• Ask Questions with Double Hints: Visual Question Generation with Answer-awareness and Region-reference
• Restoring ancient text using deep learning: a case study on Greek epigraphy
• Word Embeddings via Tensor Factorization
• Subjective Bias in Abstractive Summarization
• Incremental Blockwise Beam Search for Simultaneous Speech Translation with Controllable Quality-Latency Tradeoff
• Hybrid Neural Models For Sequence Modelling: The Best Of Three Worlds
• BSpell: A CNN-Blended BERT Based Bangla Spell Checker
• The Rediscovery Hypothesis: Language Models Need to Meet Linguistics
• Learning Noise-Invariant Representations for Robust Speech Recognition
• Learning a natural-language to LTL executable semantic parser for grounded robotics
• A Skeleton-Based Model for Promoting Coherence Among Sentences in Narrative Story Generation
• AlignVE: Visual Entailment Recognition Based on Alignment Relations
• AutoSTR: Efficient Backbone Search for Scene Text Recognition
• AttnMove: History Enhanced Trajectory Recovery via Attentional Network
• It Takes Two Flints to Make a Fire: Multitask Learning of Neural Relation and Explanation Classifiers
• Can NMT Understand Me? Towards Perturbation-based Evaluation of NMT Models for Code Generation
• Weakly Supervised Reasoning by Neuro-Symbolic Approaches
• Machine-learning Based Extraction of the Short-Range Part of the Interaction in Non-contact Atomic Force Microscopy
• Attention-based Mixture Density Recurrent Networks for History-based Recommendation
• Neural Melody Composition from Lyrics
• Accelerating Asynchronous Stochastic Gradient Descent for Neural Machine Translation
• Learning Oculomotor Behaviors from Scanpath
• Equivalence of Segmental and Neural Transducer Modeling: A Proof of Concept
• Contextual Temperature for Language Modeling
• Learning Effective Representations for Person-Job Fit by Feature Fusion
• Enhancing Semantic Understanding with Self-supervised Methods for Abstractive Dialogue Summarization
• On-the-Fly Syntax Highlighting using Neural Networks
• Investigating Linguistic Pattern Ordering in Hierarchical Natural Language Generation
• Multi-hop Inference for Question-driven Summarization
• CORE-ReID V2: Advancing the Domain Adaptation for Object Re-Identification with Optimized Training and Ensemble Fusion
• Teaching Machines to Code: Neural Markup Generation with Visual Attention
• Attentive Explanations: Justifying Decisions and Pointing to the Evidence (Extended Abstract)
• $A^{4}NT$: Author Attribute Anonymity by Adversarial Training of Neural Machine Translation
• On Attention Modules for Audio-Visual Synchronization
• HorNet: A Hierarchical Offshoot Recurrent Network for Improving Person Re-ID via Image Captioning
• Multi Task Deep Morphological Analyzer: Context Aware Joint Morphological Tagging and Lemma Prediction
• Perturbation-based Self-supervised Attention for Attention Bias in Text Classification
• Comparative Analysis of Agent-Oriented Task Assignment and Path Planning Algorithms Applied to Drone Swarms
• Sinhala-English Parallel Word Dictionary Dataset
• Block-wise Dynamic Sparseness
• A Cluster Ranking Model for Full Anaphora Resolution
• Long-Range Transformer Architectures for Document Understanding
• Towards Better Multi-modal Keyphrase Generation via Visual Entity Enhancement and Multi-granularity Image Noise Filtering
• Neural Machine Translation with 4-Bit Precision and Beyond
• Core Semantic First: A Top-down Approach for AMR Parsing
• The TALP-UPC System for the WMT Similar Language Task: Statistical vs Neural Machine Translation
• A new rotating machinery fault diagnosis method based on the Time Series Transformer
• DuTrust: A Sentiment Analysis Dataset for Trustworthiness Evaluation
• Document-level Neural Machine Translation with Document Embeddings
• De-identification of Unstructured Clinical Texts from Sequence to Sequence Perspective
• The relational processing limits of classic and contemporary neural network models of language processing
• Supervised Visual Attention for Simultaneous Multimodal Machine Translation
• End-to-End Non-Autoregressive Neural Machine Translation with Connectionist Temporal Classification
• MSVD-Turkish: A Comprehensive Multimodal Dataset for Integrated Vision and Language Research in Turkish
• Learning Contextual Hierarchical Structure of Medical Concepts with Poincairé Embeddings to Clarify Phenotypes
• Creating a New Persian Poet Based on Machine Learning
• Fast and Simple Mixture of Softmaxes with BPE and Hybrid-LightRNN for Language Generation
• A Resource for Studying Chatino Verbal Morphology
• Semantic Graphs for Generating Deep Questions
• Title-Guided Encoding for Keyphrase Generation
• Semantic-Unit-Based Dilated Convolution for Multi-Label Text Classification
• Fine-grained Human Evaluation of Transformer and Recurrent Approaches to Neural Machine Translation for English-to-Chinese
• Improving unsupervised neural aspect extraction for online discussions using out-of-domain classification
• Improved English to Russian Translation by Neural Suffix Prediction
• Guiding Attention in End-to-End Driving Models
• Voice Imitating Text-to-Speech Neural Networks
• Learning Frame Level Attention for Environmental Sound Classification
• WeightNet: Revisiting the Design Space of Weight Networks
• Video Sentiment Analysis with Bimodal Information-augmented Multi-Head Attention
• Optimal Quantization for Batch Normalization in Neural Network Deployments and Beyond
• daVinciNet: Joint Prediction of Motion and Surgical State in Robot-Assisted Surgery
• Persian Keyphrase Generation Using Sequence-to-Sequence Models
• Attention for Causal Relationship Discovery from Biological Neural Dynamics
• Learning to Detect Opinion Snippet for Aspect-Based Sentiment Analysis
• Incremental processing of noisy user utterances in the spoken language understanding task
• Endowing Deep 3D Models with Rotation Invariance Based on Principal Component Analysis
• Koopman Learning with Episodic Memory
• Seq2seq Translation Model for Sequential Recommendation
• Multi-Horizon Forecasting for Limit Order Books: Novel Deep Learning Approaches and Hardware Acceleration using Intelligent Processing Units
• Extending a model for ontology-based Arabic-English machine translation
• Generating Rich Product Descriptions for Conversational E-commerce Systems
• Cleansing Jewel: A Neural Spelling Correction Model Built On Google OCR-ed Tibetan Manuscripts
• Integrating Image Features with Convolutional Sequence-to-sequence Network for Multilingual Visual Question Answering
• Author Name Disambiguation via Heterogeneous Network Embedding from Structural and Semantic Perspectives
• Drivers of the decrease of patent similarities from 1976 to 2021
• Regression as Classification: Influence of Task Formulation on Neural Network Features
• Neighbors Are Not Strangers: Improving Non-Autoregressive Translation under Low-Frequency Lexical Constraints
• A Correlational Encoder Decoder Architecture for Pivot Based Sequence Generation
• Astronomical image time series classification using CONVolutional attENTION (ConvEntion)
• Investigation of learning abilities on linguistic features in sequence-to-sequence text-to-speech synthesis
• DM${}^2$S${}^2$: Deep Multi-Modal Sequence Sets with Hierarchical Modality Attention
• The boundaries of meaning: a case study in neural machine translation
• Attention-based Ingredient Phrase Parser
• The Monte Carlo Transformer: a stochastic self-attention model for sequence prediction
• Few-Shot Object Recognition from Machine-Labeled Web Images
• AICAttack: Adversarial Image Captioning Attack with Attention-Based Optimization
• A low latency ASR-free end to end spoken language understanding system
• Symbolic integration by integrating learning models with different strengths and weaknesses
• Improving Next-Application Prediction with Deep Personalized-Attention Neural Network
• Partially-Aligned Data-to-Text Generation with Distant Supervision
• SEOVER: Sentence-level Emotion Orientation Vector based Conversation Emotion Recognition Model
• Polygonizer: An auto-regressive building delineator
• Deep Multi-View Learning for Tire Recommendation
• Cross-Media Keyphrase Prediction: A Unified Framework with Multi-Modality Multi-Head Attention and Image Wordings
• Looking for change? Roll the Dice and demand Attention
• MSSRNet: Manipulating Sequential Style Representation for Unsupervised Text Style Transfer
• A Deep Learning Approach to Automate High-Resolution Blood Vessel Reconstruction on Computerized Tomography Images With or Without the Use of Contrast Agent
• An Attention-Based Speaker Naming Method for Online Adaptation in Non-Fixed Scenarios
• Alphanetv4: Alpha Mining Model
• A Corpus for English-Japanese Multimodal Neural Machine Translation with Comparable Sentences
• Integrated Training for Sequence-to-Sequence Models Using Non-Autoregressive Transformer
• Dependent Gated Reading for Cloze-Style Question Answering
• SP-GPT2: Semantics Improvement in Vietnamese Poetry Generation
• Analysis of Bag-of-n-grams Representation's Properties Based on Textual Reconstruction
• Demographic-Guided Attention in Recurrent Neural Networks for Modeling Neuropathophysiological Heterogeneity
• Relevance-Promoting Language Model for Short-Text Conversation
• Separate and Attend in Personal Email Search
• Improved Predictive Deep Temporal Neural Networks with Trend Filtering
• Towards one-shot learning for rare-word translation with external experts
• Attention improves concentration when learning node embeddings
• Replicated Siamese LSTM in Ticketing System for Similarity Learning and Retrieval in Asymmetric Texts
• Paraphrase Generation as Unsupervised Machine Translation
• Learning Spatial-Semantic Context with Fully Convolutional Recurrent Network for Online Handwritten Chinese Text Recognition
• Does Attention Mechanism Possess the Feature of Human Reading? A Perspective of Sentiment Classification Task
• Context-Aware Sequence-to-Sequence Models for Conversational Systems
• EmotionX-DLC: Self-Attentive BiLSTM for Detecting Sequential Emotions in Dialogue
• Attention Mechanism with Energy-Friendly Operations
• Shift-Reduce Constituent Parsing with Neural Lookahead Features
• Can you tell? SSNet -- a Sagittal Stratum-inspired Neural Network Framework for Sentiment Analysis
• Learning Permutation Invariant Representations using Memory Networks
• Caption Generation on Scenes with Seen and Unseen Object Categories
• Exploring Textual and Speech information in Dialogue Act Classification with Speaker Domain Adaptation
• I Have Seen Enough: A Teacher Student Network for Video Classification Using Fewer Frames
• Visual Concept Reasoning Networks
• simNet: Stepwise Image-Topic Merging Network for Generating Detailed and Comprehensive Image Captions
• Query-based Interactive Recommendation by Meta-Path and Adapted Attention-GRU
• NERO: A Neural Rule Grounding Framework for Label-Efficient Relation Extraction
• MULE: Multimodal Universal Language Embedding
• Multi-Reference Training with Pseudo-References for Neural Translation and Text Generation
• Exploiting Unlabeled Data for Neural Grammatical Error Detection
• Lessons Learned from Applying off-the-shelf BERT: There is no Silver Bullet
• Semi-Supervised Confidence Network aided Gated Attention based Recurrent Neural Network for Clickbait Detection
• Deep Understanding based Multi-Document Machine Reading Comprehension
• Exact-K Recommendation via Maximal Clique Optimization
• Machine Translation between Vietnamese and English: an Empirical Study
• An Attention Model for group-level emotion recognition
• Scene Parsing via Dense Recurrent Neural Networks with Attentional Selection
• Statistical Parametric Speech Synthesis Using Bottleneck Representation From Sequence Auto-encoder
• ReDecode Framework for Iterative Improvement in Paraphrase Generation
• Grading video interviews with fairness considerations
• Translating Natural Language to SQL using Pointer-Generator Networks and How Decoding Order Matters
• Analyzing Architectures for Neural Machine Translation Using Low Computational Resources
• Black-box Adversarial Sample Generation Based on Differential Evolution
• Wavelet Denoising and Attention-based RNN-ARIMA Model to Predict Forex Price
• FPETS : Fully Parallel End-to-End Text-to-Speech System
• Self-Attention-Based Message-Relevant Response Generation for Neural Conversation Model
• Unsupervised Neural Dialect Translation with Commonality and Diversity Modeling
• Transferable Natural Language Interface to Structured Queries aided by Adversarial Generation
• Multi-Level Attention Pooling for Graph Neural Networks: Unifying Graph Representations with Multiple Localities
• Probabilistic Transformers
• Deep Learning: Our Miraculous Year 1990-1991
• Exclusion and Inclusion -- A model agnostic approach to feature importance in DNNs
• Borrowing from Similar Code: A Deep Learning NLP-Based Approach for Log Statement Automation
• Enhancing Fine-grained Sentiment Classification Exploiting Local Context Embedding
• Sequence-to-Set Semantic Tagging: End-to-End Multi-label Prediction using Neural Attention for Complex Query Reformulation and Automated Text Categorization
• Transformer in action: a comparative study of transformer-based acoustic models for large scale speech recognition applications
• Disruption in the Chinese E-Commerce During COVID-19
• Improving the sample-efficiency of neural architecture search with reinforcement learning
• Enhance Long Text Understanding via Distilled Gist Detector from Abstractive Summarization
• Neural Twins Talk
• Development of an Extractive Title Generation System Using Titles of Papers of Top Conferences for Intermediate English Students
• Non-Projective Dependency Parsing via Latent Heads Representation (LHR)
• LeBenchmark: A Reproducible Framework for Assessing Self-Supervised Representation Learning from Speech
• Deep Exemplar Networks for VQA and VQG
• OSU Multimodal Machine Translation System Report
• Visual Agreement Regularized Training for Multi-Modal Machine Translation
• Rhythm-controllable Attention with High Robustness for Long Sentence Speech Synthesis
• On the Learning Dynamics of Attention Networks
• Do Context-Aware Translation Models Pay the Right Attention?
• Evaluating Sequence-to-Sequence Learning Models for If-Then Program Synthesis
• Everybody Compose: Deep Beats To Music
• A Multi-Turn Emotionally Engaging Dialog Model
• Navigational Instruction Generation as Inverse Reinforcement Learning with Neural Machine Translation
• TextCNN with Attention for Text Classification
• Attend to the beginning: A study on using bidirectional attention for extractive summarization
• Beyond Individual Input for Deep Anomaly Detection on Tabular Data
• Know Deeper: Knowledge-Conversation Cyclic Utilization Mechanism for Open-domain Dialogue Generation
• Probabilistic Attention for Interactive Segmentation
• Neural paraphrasing by automatically crawled and aligned sentence pairs
• Automatic Acrostic Couplet Generation with Three-Stage Neural Network Pipelines
• A Hierarchical Attention Based Seq2seq Model for Chinese Lyrics Generation
• On the Definition of Japanese Word
• Retrosynthetic reaction prediction using neural sequence-to-sequence models
• Character-Level Neural Translation for Multilingual Media Monitoring in the SUMMA Project
• Relevance in Dialogue: Is Less More? An Empirical Comparison of Existing Metrics, and a Novel Simple Metric
• VANiLLa : Verbalized Answers in Natural Language at Large Scale
• LIG-CRIStAL System for the WMT17 Automatic Post-Editing Task
• Assessing the Helpfulness of Review Content for Explaining Recommendations
• Neural MultiVoice Models for Expressing Novel Personalities in Dialog
• Neural and Statistical Methods for Leveraging Meta-information in Machine Translation
• Real-time low-resource phoneme recognition on edge devices
• A Sketch-Based Neural Model for Generating Commit Messages from Diffs
• Unsupervised Neural Text Simplification
• Review-Driven Multi-Label Music Style Classification by Exploiting Style Correlations
• Query Tracking for E-commerce Conversational Search: A Machine Comprehension Perspective
• A Simple and Interpretable Predictive Model for Healthcare
• Effective Decoder Masking for Transformer Based End-to-End Speech Recognition
• Concept Tagging for Natural Language Understanding: Two Decadelong Algorithm Development
• Joint learning of interpretation and distillation
• An Investigation of Warning Erroneous Chat Translations in Cross-lingual Communication
• Interpreting Models by Allowing to Ask
• Direct data-driven forecast of local turbulent heat flux in Rayleigh-Bénard convection
• Understood in Translation, Transformers for Domain Understanding
• Continuous Space Reordering Models for Phrase-based MT
• Dual-CLVSA: a Novel Deep Learning Approach to Predict Financial Markets with Sentiment Measurements
• Sequential Routing Framework: Fully Capsule Network-based Speech Recognition
• Where are we in semantic concept extraction for Spoken Language Understanding?
• Can "consciousness" be observed from large language model (LLM) internal states? Dissecting LLM representations obtained from Theory of Mind test with Integrated Information Theory and Span Representation analysis
• Synthesizing Photorealistic Images with Deep Generative Learning
• S-OHEM: Stratified Online Hard Example Mining for Object Detection
• Cross-Modal Alignment with Mixture Experts Neural Network for Intral-City Retail Recommendation
• A copula-based visualization technique for a neural network
• Guessing State Tracking for Visual Dialogue
• Incorporating Chinese Radicals Into Neural Machine Translation: Deeper Than Character Level
• Generation of Synthetic Electronic Medical Record Text
• Power Law Graph Transformer for Machine Translation and Representation Learning
• Do Encoder Representations of Generative Dialogue Models Encode Sufficient Information about the Task ?
• Bag-of-Vector Embeddings of Dependency Graphs for Semantic Induction
• CanvasGAN: A simple baseline for text to image generation by incrementally patching a canvas
• Predicting and Explaining Hearing Aid Usage Using Encoder-Decoder with Attention Mechanism and SHAP
• On Inductive Biases for Machine Learning in Data Constrained Settings
• SAMbA: Speech enhancement with Asynchronous ad-hoc Microphone Arrays
• Conditionally Learn to Pay Attention for Sequential Visual Task
• Type-driven Neural Programming by Example
• Timestamping Documents and Beliefs
• Differentiable Disentanglement Filter: an Application Agnostic Core Concept Discovery Probe
• Improved and Robust Controversy Detection in General Web Pages Using Semantic Approaches under Large Scale Conditions
• Learning Top-k Subtask Planning Tree based on Discriminative Representation Pre-training for Decision Making
• A deep Natural Language Inference predictor without language-specific training data
• Learning When to Concentrate or Divert Attention: Self-Adaptive Attention Temperature for Neural Machine Translation
• Detect the Interactions that Matter in Matter: Geometric Attention for Many-Body Systems
• Quantity vs. Quality of Monolingual Source Data in Automatic Text Translation: Can It Be Too Little If It Is Too Good?
• Sparsely Activated Networks: A new method for decomposing and compressing data
• Learning to Encode Evolutionary Knowledge for Automatic Commenting Long Novels
• Towards Faster k-Nearest-Neighbor Machine Translation
• SU-RUG at the CoNLL-SIGMORPHON 2017 shared task: Morphological Inflection with Attentional Sequence-to-Sequence Models
• Self-attention based end-to-end Hindi-English Neural Machine Translation
• AGenT Zero: Zero-shot Automatic Multiple-Choice Question Generation for Skill Assessments
• Ordinal Common-sense Inference
• Decomposing Complex Questions Makes Multi-Hop QA Easier and More Interpretable
• Modeling of Rakugo Speech and Its Limitations: Toward Speech Synthesis That Entertains Audiences
• A Data-Efficient Deep Learning Based Smartphone Application For Detection Of Pulmonary Diseases Using Chest X-rays
• Mapping the Internet: Modelling Entity Interactions in Complex Heterogeneous Networks
• A crossover code for high-dimensional composition
• Sequential Variational Autoencoders for Collaborative Filtering
• Master Thesis: Neural Sign Language Translation by Learning Tokenization
• Text-to-hashtag Generation using Seq2seq Learning
• Cross-lingual Word Embeddings beyond Zero-shot Machine Translation
• Comparative Visual Analytics for Assessing Medical Records with Sequence Embedding
• End-to-end Silent Speech Recognition with Acoustic Sensing
• Evaluating Syntactic Properties of Seq2seq Output with a Broad Coverage HPSG: A Case Study on Machine Translation
• A Three Step Training Approach with Data Augmentation for Morphological Inflection
• Challenges and Thrills of Legal Arguments
• An Empirical Study on End-to-End Singing Voice Synthesis with Encoder-Decoder Architectures
• SocialML: machine learning for social media video creators
• Using holistic event information in the trigger
• CASE: Context-Aware Semantic Expansion
• Generating Descriptions for Sequential Images with Local-Object Attention and Global Semantic Context Modelling
• Future-Prediction-Based Model for Neural Machine Translation
• Cross-Level Cross-Scale Cross-Attention Network for Point Cloud Representation
• Joint Intent Detection And Slot Filling Based on Continual Learning Model
• Imperial College London Submission to VATEX Video Captioning Task
• Residual Switching Network for Portfolio Optimization
• Stochastic Dynamics for Video Infilling
• Pediatric Bone Age Prediction Using Deep Learning
• Modeling Programs Hierarchically with Stack-Augmented LSTM
• GRET: Global Representation Enhanced Transformer
• Neural Twins Talk & Alternative Calculations
• SeaPearl: A Constraint Programming Solver guided by Reinforcement Learning
• Regularized Context Gates on Transformer for Machine Translation
• Itinerary-aware Personalized Deep Matching at Fliggy
• A Hierarchical Approach to Neural Context-Aware Modeling
• CLARA: Clinical Report Auto-completion
• A Self-Attention Network for Hierarchical Data Structures with an Application to Claims Management
• The Helsinki Neural Machine Translation System
• Image to Video Domain Adaptation Using Web Supervision
• Meta-Learning a Dynamical Language Model
• Learning Fast Matching Models from Weak Annotations
• Generating an Overview Report over Many Documents
• Improving Prosody Modelling with Cross-Utterance BERT Embeddings for End-to-end Speech Synthesis
• PLSUM: Generating PT-BR Wikipedia by Summarizing Multiple Websites
• Domain-Constrained Advertising Keyword Generation