Sequence to Sequence Learning with Neural Networks

Abstract

Deep Neural Networks (DNNs) are powerful models that have achieved excellent performance on difficult learning tasks. Although DNNs work well whenever large labeled training sets are available, they cannot be used to map sequences to sequences. In this paper, we present a general end-to-end approach to sequence learning that makes minimal assumptions on the sequence structure. Our method uses a multilayered Long Short-Term Memory (LSTM) to map the input sequence to a vector of a fixed dimensionality, and then another deep LSTM to decode the target sequence from the vector. Our main result is that on an English to French translation task from the WMT'14 dataset, the translations produced by the LSTM achieve a BLEU score of 34.8 on the entire test set, where the LSTM's BLEU score was penalized on out-of-vocabulary words. Additionally, the LSTM did not have difficulty on long sentences. For comparison, a phrase-based SMT system achieves a BLEU score of 33.3 on the same dataset. When we used the LSTM to rerank the 1000 hypotheses produced by the aforementioned SMT system, its BLEU score increases to 36.5, which is close to the previous best result on this task. The LSTM also learned sensible phrase and sentence representations that are sensitive to word order and are relatively invariant to the active and the passive voice. Finally, we found that reversing the order of the words in all source sentences (but not target sentences) improved the LSTM's performance markedly, because doing so introduced many short term dependencies between the source and the target sentence which made the optimization problem easier.

9 pages

References in corpus (2)

• On the difficulty of training Recurrent Neural Networks
• Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation

Cited by in corpus (1069)

• Deep Learning in Neural Networks: An Overview
• Recurrent Neural Network Regularization
• Attention-Based Models for Speech Recognition
• Unifying Visual-Semantic Embeddings with Multimodal Neural Language Models
• Show and Tell: Lessons learned from the 2015 MSCOCO Image Captioning Challenge
• Skip-Thought Vectors
• Medical image denoising using convolutional denoising autoencoders
• Deep Captioning with Multimodal Recurrent Neural Networks (m-RNN)
• Focusing Attention: Towards Accurate Text Recognition in Natural Images
• Deep Bayesian Active Learning with Image Data
• Probabilistic Backpropagation for Scalable Learning of Bayesian Neural Networks
• SleepEEGNet: Automated Sleep Stage Scoring with Sequence to Sequence Deep Learning Approach
• Layer Normalization
• Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting
• A Literature Survey of Recent Advances in Chatbots
• A Survey on Anomaly Detection for Technical Systems using LSTM Networks
• CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generation
• Gated Feedback Recurrent Neural Networks
• Multi-Task Learning with Deep Neural Networks: A Survey
• Grammar as a Foreign Language
• Generative Moment Matching Networks
• Variational Autoencoder for Deep Learning of Images, Labels and Captions
• GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding
• Hyperparameter Search in Machine Learning
• Professor Forcing: A New Algorithm for Training Recurrent Networks
• Massively Multilingual Neural Machine Translation in the Wild: Findings and Challenges
• Ask the GRU: Multi-Task Learning for Deep Text Recommendations
• Working Memory Connections for LSTM
• Towards a Human-like Open-Domain Chatbot
• Adversarial Attacks on Deep Learning Models in Natural Language Processing: A Survey
• Deep Representation Learning of Patient Data from Electronic Health Records (EHR): A Systematic Review
• Self-Taught Convolutional Neural Networks for Short Text Clustering
• Neural Paraphrase Generation with Stacked Residual LSTM Networks
• A Survey of Human Activity Recognition in Smart Homes Based on IoT Sensors Algorithms: Taxonomies, Challenges, and Opportunities with Deep Learning
• Representation learning for very short texts using weighted word embedding aggregation
• CodeBLEU: a Method for Automatic Evaluation of Code Synthesis
• Residual Attention U-Net for Automated Multi-Class Segmentation of COVID-19 Chest CT Images
• Evaluating the State-of-the-Art of End-to-End Natural Language Generation: The E2E NLG Challenge
• Applying Neural Networks in Optical Communication Systems: Possible Pitfalls
• Fathom: Reference Workloads for Modern Deep Learning Methods
• Exploring Chemical Space using Natural Language Processing Methodologies for Drug Discovery
• SMILES Transformer: Pre-trained Molecular Fingerprint for Low Data Drug Discovery
• Learning Combinatorial Optimization on Graphs: A Survey with Applications to Networking
• Multi-Sensor Prognostics using an Unsupervised Health Index based on LSTM Encoder-Decoder
• Variational Recurrent Auto-Encoders
• Deep Residual Correction Network for Partial Domain Adaptation
• How Does Learning Rate Decay Help Modern Neural Networks?
• Recurrent Neural Networks (RNNs): A gentle Introduction and Overview
• Argoverse: 3D Tracking and Forecasting with Rich Maps
• Parallel Multi-Dimensional LSTM, With Application to Fast Biomedical Volumetric Image Segmentation
• Latent ODEs for Irregularly-Sampled Time Series
• Auto-DeepLab: Hierarchical Neural Architecture Search for Semantic Image Segmentation
• Augmenting Data with Mixup for Sentence Classification: An Empirical Study
• Silent Speech Interfaces for Speech Restoration: A Review
• Rolling-Unrolling LSTMs for Action Anticipation from First-Person Video
• Enable Deep Learning on Mobile Devices: Methods, Systems, and Applications
• Evaluating Deep Learning Approaches for Covid19 Fake News Detection
• Tweet2Vec: Learning Tweet Embeddings Using Character-level CNN-LSTM Encoder-Decoder
• Self-Attention Networks for Connectionist Temporal Classification in Speech Recognition
• Neural Machine Translation and Sequence-to-sequence Models: A Tutorial
• Deep Closest Point: Learning Representations for Point Cloud Registration
• Deep Learning and Knowledge-Based Methods for Computer Aided Molecular Design -- Toward a Unified Approach: State-of-the-Art and Future Directions
• Evaluating Two-Stream CNN for Video Classification
• Compressing Recurrent Neural Network with Tensor Train
• Neural Turing Machines
• WT5?! Training Text-to-Text Models to Explain their Predictions
• Federated Learning Of Out-Of-Vocabulary Words
• Rearrangement: A Challenge for Embodied AI
• Learning Deep Transformer Models for Machine Translation
• CoaCor: Code Annotation for Code Retrieval with Reinforcement Learning
• The Missing Ingredient in Zero-Shot Neural Machine Translation
• Personalized Bundle List Recommendation
• Reward Augmented Maximum Likelihood for Neural Structured Prediction
• GMAN: A Graph Multi-Attention Network for Traffic Prediction
• Extraction of Salient Sentences from Labelled Documents
• PointRNN: Point Recurrent Neural Network for Moving Point Cloud Processing
• Representation Learning for Natural Language Processing
• Adding Interpretable Attention to Neural Translation Models Improves Word Alignment
• GluonTS: Probabilistic Time Series Models in Python
• Human Trajectory Prediction using Spatially aware Deep Attention Models
• Solar wind prediction using deep learning
• Recurrent Neural Networks for Time Series Forecasting
• Spatial-Temporal Fusion Graph Neural Networks for Traffic Flow Forecasting
• Distance-based Self-Attention Network for Natural Language Inference
• Artificial Neural Network Based Breast Cancer Screening: A Comprehensive Review
• Chinese Poetry Generation with Planning based Neural Network
• The Sockeye 2 Neural Machine Translation Toolkit at AMTA 2020
• PolyGen: An Autoregressive Generative Model of 3D Meshes
• Exploring Human Mobility for Multi-Pattern Passenger Prediction: A Graph Learning Framework
• GERE: Generative Evidence Retrieval for Fact Verification
• Unsupervised Translation of Programming Languages
• User-Centric Conversational Recommendation with Multi-Aspect User Modeling
• Sample Efficient Text Summarization Using a Single Pre-Trained Transformer
• A Siamese Long Short-Term Memory Architecture for Human Re-Identification
• Towards Dynamic and Safe Configuration Tuning for Cloud Databases
• TabularNet: A Neural Network Architecture for Understanding Semantic Structures of Tabular Data
• Soft Contextual Data Augmentation for Neural Machine Translation
• Semantic Modelling with Long-Short-Term Memory for Information Retrieval
• Scaling Memory-Augmented Neural Networks with Sparse Reads and Writes
• Multi-lingual Intent Detection and Slot Filling in a Joint BERT-based Model
• Natural Language Understanding with the Quora Question Pairs Dataset
• Topic-Guided Variational Autoencoders for Text Generation
• Evaluating Mixed-initiative Conversational Search Systems via User Simulation
• Temporal Attention Model for Neural Machine Translation
• Artificial Intelligence for Social Good: A Survey
• Deep Learning for Plasma Tomography and Disruption Prediction from Bolometer Data
• Double Trouble in Double Descent : Bias and Variance(s) in the Lazy Regime
• Out of Distribution Generalization in Machine Learning
• HIBERT: Document Level Pre-training of Hierarchical Bidirectional Transformers for Document Summarization
• Encoding Source Language with Convolutional Neural Network for Machine Translation
• Learn an Effective Lip Reading Model without Pains
• An Empirical Comparison of Simple Domain Adaptation Methods for Neural Machine Translation
• AR-Net: A simple Auto-Regressive Neural Network for time-series
• Adversarial Examples in Modern Machine Learning: A Review
• Machine Reading Comprehension: The Role of Contextualized Language Models and Beyond
• Video Representation Learning by Dense Predictive Coding
• Attention-based Convolutional Autoencoders for 3D-Variational Data Assimilation
• Deep Learning for Symbolic Mathematics
• TAP-Net: Transport-and-Pack using Reinforcement Learning
• Hybrid Tensor Decomposition in Neural Network Compression
• Few-Shot Bot: Prompt-Based Learning for Dialogue Systems
• Explaining Question Answering Models through Text Generation
• Gmail Smart Compose: Real-Time Assisted Writing
• Generative Language Modeling for Automated Theorem Proving
• Massively Multilingual Neural Machine Translation
• Label-Consistent Backdoor Attacks
• Towards Transparent AI Systems: Interpreting Visual Question Answering Models
• A Comprehensive Survey of Machine Learning Based Localization with Wireless Signals
• Towards Ecologically Valid Research on Language User Interfaces
• Open-Domain Conversational Agents: Current Progress, Open Problems, and Future Directions
• LightRNN: Memory and Computation-Efficient Recurrent Neural Networks
• Learn to Design the Heuristics for Vehicle Routing Problem
• Minimizing the Bag-of-Ngrams Difference for Non-Autoregressive Neural Machine Translation
• Neural Speaker Diarization with Speaker-Wise Chain Rule
• Answer-based Adversarial Training for Generating Clarification Questions
• All SMILES Variational Autoencoder
• Combining Static and Dynamic Features for Multivariate Sequence Classification
• Not All Neural Embeddings are Born Equal
• Reflection Backdoor: A Natural Backdoor Attack on Deep Neural Networks
• Voice Transformer Network: Sequence-to-Sequence Voice Conversion Using Transformer with Text-to-Speech Pretraining
• A Transformer-based Approach for Source Code Summarization
• Learning from Few Samples: A Survey
• Robust Neural Machine Translation with Doubly Adversarial Inputs
• Deep-Sentiment: Sentiment Analysis Using Ensemble of CNN and Bi-LSTM Models
• DDTCDR: Deep Dual Transfer Cross Domain Recommendation
• Comparative evaluation of CNN architectures for Image Caption Generation
• A Survey of Natural Language Generation Techniques with a Focus on Dialogue Systems - Past, Present and Future Directions
• An Experimental Study of LSTM Encoder-Decoder Model for Text Simplification
• Revisiting Challenges in Data-to-Text Generation with Fact Grounding
• Spatio-Temporal Graph Transformer Networks for Pedestrian Trajectory Prediction
• Keyphrase Generation for Scientific Document Retrieval
• Improved Neural Machine Translation with a Syntax-Aware Encoder and Decoder
• Tabular Benchmarks for Joint Architecture and Hyperparameter Optimization
• Controlling the Output Length of Neural Machine Translation
• Multi-modal gated recurrent units for image description
• GypSum: Learning Hybrid Representations for Code Summarization
• ConvLab: Multi-Domain End-to-End Dialog System Platform
• Deep Learning for Spatio-Temporal Data Mining: A Survey
• A Call for Prudent Choice of Subword Merge Operations in Neural Machine Translation
• Imitation Learning for Non-Autoregressive Neural Machine Translation
• Gated Recurrent Neural Tensor Network
• Short-term daily precipitation forecasting with seasonally-integrated autoencoder
• ProcessTransformer: Predictive Business Process Monitoring with Transformer Network
• Memory-Augmented Recurrent Neural Networks Can Learn Generalized Dyck Languages
• Multimodal Transformer with Multi-View Visual Representation for Image Captioning
• Discrete and continuous representations and processing in deep learning: Looking forward
• Bridging the Gap between Training and Inference for Neural Machine Translation
• GenNI: Human-AI Collaboration for Data-Backed Text Generation
• DivGraphPointer: A Graph Pointer Network for Extracting Diverse Keyphrases
• They, Them, Theirs: Rewriting with Gender-Neutral English
• Incorporating Global Visual Features into Attention-Based Neural Machine Translation
• Multi-step Reasoning via Recurrent Dual Attention for Visual Dialog
• Human few-shot learning of compositional instructions
• Towards Transfer Learning for End-to-End Speech Synthesis from Deep Pre-Trained Language Models
• A Survey of Deep Learning Approaches for OCR and Document Understanding
• Leveraging Multilingual Transformers for Hate Speech Detection
• GDP: Generalized Device Placement for Dataflow Graphs
• Revisiting Low-Resource Neural Machine Translation: A Case Study
• Temporal Learning and Sequence Modeling for a Job Recommender System
• Using Whole Document Context in Neural Machine Translation
• Task-Oriented Dialog Systems that Consider Multiple Appropriate Responses under the Same Context
• A Survey on Causal Inference
• Interactive Attention for Neural Machine Translation
• Spatio-Temporal Attention Models for Grounded Video Captioning
• Solving Optimization Problems through Fully Convolutional Networks: an Application to the Travelling Salesman Problem
• COMET: Commonsense Transformers for Automatic Knowledge Graph Construction
• iPerceive: Applying Common-Sense Reasoning to Multi-Modal Dense Video Captioning and Video Question Answering
• Can We Generate Shellcodes via Natural Language? An Empirical Study
• TranSmart: A Practical Interactive Machine Translation System
• Recurrent Attentive Neural Process for Sequential Data
• Neural Language Generation: Formulation, Methods, and Evaluation
• On Using SpecAugment for End-to-End Speech Translation
• Improving Sequence-to-Sequence Learning via Optimal Transport
• A Comprehensive Survey of Multilingual Neural Machine Translation
• MalBERT: Using Transformers for Cybersecurity and Malicious Software Detection
• What-If Motion Prediction for Autonomous Driving
• AdaDurIAN: Few-shot Adaptation for Neural Text-to-Speech with DurIAN
• Pythia: Grammar-Based Fuzzing of REST APIs with Coverage-guided Feedback and Learning-based Mutations
• Say As You Wish: Fine-grained Control of Image Caption Generation with Abstract Scene Graphs
• Recent advances in deep learning theory
• SEQ^3: Differentiable Sequence-to-Sequence-to-Sequence Autoencoder for Unsupervised Abstractive Sentence Compression
• Audio Captioning using Pre-Trained Large-Scale Language Model Guided by Audio-based Similar Caption Retrieval
• Embedding API Dependency Graph for Neural Code Generation
• Large-Scale User Modeling with Recurrent Neural Networks for Music Discovery on Multiple Time Scales
• Discrete Graph Structure Learning for Forecasting Multiple Time Series
• Anchor Diffusion for Unsupervised Video Object Segmentation
• Exploration of Neural Machine Translation in Autoformalization of Mathematics in Mizar
• You Impress Me: Dialogue Generation via Mutual Persona Perception
• Local Translation Prediction with Global Sentence Representation
• Searching for Effective Neural Extractive Summarization: What Works and What's Next
• Towards Conversational Recommendation over Multi-Type Dialogs
• SEED: Semantics Enhanced Encoder-Decoder Framework for Scene Text Recognition
• A Scale Invariant Flatness Measure for Deep Network Minima
• A Behavioral Approach to Visual Navigation with Graph Localization Networks
• BIGPATENT: A Large-Scale Dataset for Abstractive and Coherent Summarization
• Prompt Agnostic Essay Scorer: A Domain Generalization Approach to Cross-prompt Automated Essay Scoring
• Implicit Dimension Identification in User-Generated Text with LSTM Networks
• A backdoor attack against LSTM-based text classification systems
• Joint Source-Target Self Attention with Locality Constraints
• Effects of padding on LSTMs and CNNs
• On Generalization Bounds of a Family of Recurrent Neural Networks
• EvoJAX: Hardware-Accelerated Neuroevolution
• Morphological Word Segmentation on Agglutinative Languages for Neural Machine Translation
• Reinforcement Learning Based Emotional Editing Constraint Conversation Generation
• Improving Image Captioning by Leveraging Intra- and Inter-layer Global Representation in Transformer Network
• A Knowledge-Enhanced Pretraining Model for Commonsense Story Generation
• Bengali Abstractive News Summarization(BANS): A Neural Attention Approach
• An Embarrassingly Simple Approach for Transfer Learning from Pretrained Language Models
• Federated Learning of N-gram Language Models
• A Deep Neural Network Approach To Parallel Sentence Extraction
• Merlion: A Machine Learning Library for Time Series
• Conversing by Reading: Contentful Neural Conversation with On-demand Machine Reading
• Improving Background Based Conversation with Context-aware Knowledge Pre-selection
• SummAE: Zero-Shot Abstractive Text Summarization using Length-Agnostic Auto-Encoders
• Fast Transient Simulation of High-Speed Channels Using Recurrent Neural Network
• Improving Robustness of Task Oriented Dialog Systems
• Abstractive Dialog Summarization with Semantic Scaffolds
• Matrix Encoding Networks for Neural Combinatorial Optimization
• Extreme Classification in Log Memory using Count-Min Sketch: A Case Study of Amazon Search with 50M Products
• Exploring Benefits of Transfer Learning in Neural Machine Translation
• Attention Optimization for Abstractive Document Summarization
• Competence-based Curriculum Learning for Neural Machine Translation
• Alleviating Exposure Bias via Contrastive Learning for Abstractive Text Summarization
• Augmenting Neural Machine Translation with Knowledge Graphs
• Universal linguistic inductive biases via meta-learning
• Exploiting Out-of-Domain Parallel Data through Multilingual Transfer Learning for Low-Resource Neural Machine Translation
• Conditional Self-Attention for Query-based Summarization
• Multi-Range Attentive Bicomponent Graph Convolutional Network for Traffic Forecasting
• Neural Machine Translating from Natural Language to SPARQL
• Robust End-to-End Focal Liver Lesion Detection using Unregistered Multiphase Computed Tomography Images
• On Compositionality in Neural Machine Translation
• Zero-Shot Paraphrase Generation with Multilingual Language Models
• Synergy between Machine/Deep Learning and Software Engineering: How Far Are We?
• Kernel Change-point Detection with Auxiliary Deep Generative Models
• A Novel Approach Based Deep RNN Using Hybrid NARX-LSTM Model For Solar Power Forecasting
• Improving Multimodal Accuracy Through Modality Pre-training and Attention
• Controllable Sentence Simplification: Employing Syntactic and Lexical Constraints
• Image denoising and restoration with CNN-LSTM Encoder Decoder with Direct Attention
• Fine Grained Knowledge Transfer for Personalized Task-oriented Dialogue Systems
• Deep Imitation Learning for Bimanual Robotic Manipulation
• A Short Survey On Memory Based Reinforcement Learning
• Dual Metric Learning for Effective and Efficient Cross-Domain Recommendations
• LiDAR-based Online 3D Video Object Detection with Graph-based Message Passing and Spatiotemporal Transformer Attention
• A State Aggregation Approach for Solving Knapsack Problem with Deep Reinforcement Learning
• Low-Rank Bottleneck in Multi-head Attention Models
• Generate, Delete and Rewrite: A Three-Stage Framework for Improving Persona Consistency of Dialogue Generation
• On Exposure Bias, Hallucination and Domain Shift in Neural Machine Translation
• Constrained Combinatorial Optimization with Reinforcement Learning
• On the Initialization of Long Short-Term Memory Networks
• Fair Comparison: Quantifying Variance in Resultsfor Fine-grained Visual Categorization
• RobustScanner: Dynamically Enhancing Positional Clues for Robust Text Recognition
• Theoretical Insights Into Multiclass Classification: A High-dimensional Asymptotic View
• A practical approach to dialogue response generation in closed domains
• Dual Attention Suppression Attack: Generate Adversarial Camouflage in Physical World
• Prediction of Soil Moisture Content Based On Satellite Data and Sequence-to-Sequence Networks
• Neural Polysynthetic Language Modelling
• Deep Learning for Embodied Vision Navigation: A Survey
• Style Example-Guided Text Generation using Generative Adversarial Transformers
• Salus: Fine-Grained GPU Sharing Primitives for Deep Learning Applications
• PharmMT: A Neural Machine Translation Approach to Simplify Prescription Directions
• Deep Reinforced Query Reformulation for Information Retrieval
• Improved Zero-shot Neural Machine Translation via Ignoring Spurious Correlations
• Chat as Expected: Learning to Manipulate Black-box Neural Dialogue Models
• Predictive Auto-scaling with OpenStack Monasca
• Neural Language Models as Psycholinguistic Subjects: Representations of Syntactic State
• Neural Machine Translation For Paraphrase Generation
• A Linear Dynamical System Model for Text
• Demystifying Deep Learning in Predictive Spatio-Temporal Analytics: An Information-Theoretic Framework
• A Deep Reinforcement Learning Algorithm Using Dynamic Attention Model for Vehicle Routing Problems
• End-to-end training of object class detectors for mean average precision
• Paraphrase Augmented Task-Oriented Dialog Generation
• Can SGD Learn Recurrent Neural Networks with Provable Generalization?
• A Multi-Object Rectified Attention Network for Scene Text Recognition
• CDL: Curriculum Dual Learning for Emotion-Controllable Response Generation
• Bias-based Universal Adversarial Patch Attack for Automatic Check-out
• End-to-End Speaker Diarization for an Unknown Number of Speakers with Encoder-Decoder Based Attractors
• On the Dimensionality of Embeddings for Sparse Features and Data
• Multi-Scale RCNN Model for Financial Time-series Classification
• Sequence-to-sequence models for workload interference
• Adversarial Examples on Object Recognition: A Comprehensive Survey
• Non-Autoregressive Neural Dialogue Generation
• Improving Sign Language Translation with Monolingual Data by Sign Back-Translation
• DeepMnemonic: Password Mnemonic Generation via Deep Attentive Encoder-Decoder Model
• PlumeNet: Large-Scale Air Quality Forecasting Using A Convolutional LSTM Network
• Effects of Word-frequency based Pre- and Post- Processings for Audio Captioning
• Anomaly Detection for Industrial Control Systems Using Sequence-to-Sequence Neural Networks
• AdaptSum: Towards Low-Resource Domain Adaptation for Abstractive Summarization
• T-BERT -- Model for Sentiment Analysis of Micro-blogs Integrating Topic Model and BERT
• Topic-Driven and Knowledge-Aware Transformer for Dialogue Emotion Detection
• SimCLS: A Simple Framework for Contrastive Learning of Abstractive Summarization
• Approximating Activation Functions
• A Unified Generative Framework for Aspect-Based Sentiment Analysis
• Image-Question-Answer Synergistic Network for Visual Dialog
• Gated Embeddings in End-to-End Speech Recognition for Conversational-Context Fusion
• Understanding and Improving Encoder Layer Fusion in Sequence-to-Sequence Learning
• Retrieving Sequential Information for Non-Autoregressive Neural Machine Translation
• Incremental Adaptation of NMT for Professional Post-editors: A User Study
• TLDR: Token Loss Dynamic Reweighting for Reducing Repetitive Utterance Generation
• Acquiring Knowledge from Pre-trained Model to Neural Machine Translation
• Adversarial Learning of Deepfakes in Accounting
• Hard-Coded Gaussian Attention for Neural Machine Translation
• Tactical Rewind: Self-Correction via Backtracking in Vision-and-Language Navigation
• Equivalent and Approximate Transformations of Deep Neural Networks
• Beam Search with Bidirectional Strategies for Neural Response Generation
• Relational Data Synthesis using Generative Adversarial Networks: A Design Space Exploration
• A Survey of Document Grounded Dialogue Systems (DGDS)
• Spatial-Channel Transformer Network for Trajectory Prediction on the Traffic Scenes
• Label-aware Document Representation via Hybrid Attention for Extreme Multi-Label Text Classification
• KdConv: A Chinese Multi-domain Dialogue Dataset Towards Multi-turn Knowledge-driven Conversation
• Neural Machine Translation: Challenges, Progress and Future
• Marathi To English Neural Machine Translation With Near Perfect Corpus And Transformers
• ConfuciuX: Autonomous Hardware Resource Assignment for DNN Accelerators using Reinforcement Learning
• LAVA NAT: A Non-Autoregressive Translation Model with Look-Around Decoding and Vocabulary Attention
• Black Box Recursive Translations for Molecular Optimization
• Probabilistic Time Series Forecasting with Implicit Quantile Networks
• Learning Individual Speaking Styles for Accurate Lip to Speech Synthesis
• Dynamic Partial Removal: A Neural Network Heuristic for Large Neighborhood Search
• Interconnected Question Generation with Coreference Alignment and Conversation Flow Modeling
• Automatic Source Code Summarization with Extended Tree-LSTM
• DAL: Dual Adversarial Learning for Dialogue Generation
• Fashion Retail: Forecasting Demand for New Items
• OCC: A Smart Reply System for Efficient In-App Communications
• On the Generation of Medical Dialogues for COVID-19
• Solving Optical Tomography with Deep Learning
• Neural Forecasting of the Italian Sovereign Bond Market with Economic News
• Graph-based Multi-hop Reasoning for Long Text Generation
• Compositional Generalization for Primitive Substitutions
• An end-to-end Generative Retrieval Method for Sponsored Search Engine --Decoding Efficiently into a Closed Target Domain
• Low-Resource Neural Machine Translation for Southern African Languages
• CoCoSum: Contextual Code Summarization with Multi-Relational Graph Neural Network
• Extracting Symptoms and their Status from Clinical Conversations
• Context based Text-generation using LSTM networks
• Deep learning for time series classification
• Contrastive Learning with Adversarial Perturbations for Conditional Text Generation
• OCoR: An Overlapping-Aware Code Retriever
• Coherent Comment Generation for Chinese Articles with a Graph-to-Sequence Model
• Sub-Seasonal Climate Forecasting via Machine Learning: Challenges, Analysis, and Advances
• Scaling Multi-Domain Dialogue State Tracking via Query Reformulation
• Lattice-Based Transformer Encoder for Neural Machine Translation
• ReCoSa: Detecting the Relevant Contexts with Self-Attention for Multi-turn Dialogue Generation
• Collaborative City Digital Twin For Covid-19 Pandemic: A Federated Learning Solution
• Generating Emotionally Aligned Responses in Dialogues using Affect Control Theory
• Synchronous Speech Recognition and Speech-to-Text Translation with Interactive Decoding
• Machine Translation: A Literature Review
• Reinforcement Learning Based Text Style Transfer without Parallel Training Corpus
• LGESQL: Line Graph Enhanced Text-to-SQL Model with Mixed Local and Non-Local Relations
• Photon: A Robust Cross-Domain Text-to-SQL System
• Language Models are Good Translators
• Scalable Transformers for Neural Machine Translation
• Positional Encoding to Control Output Sequence Length
• Saliency-driven Word Alignment Interpretation for Neural Machine Translation
• Adaptive Parameterization for Neural Dialogue Generation
• Mutual Information Scaling and Expressive Power of Sequence Models
• Generating Commit Messages from Git Diffs
• Synchronous Bidirectional Inference for Neural Sequence Generation
• A Novel Framework for Neural Architecture Search in the Hill Climbing Domain
• Norm-Based Curriculum Learning for Neural Machine Translation
• FastS2S-VC: Streaming Non-Autoregressive Sequence-to-Sequence Voice Conversion
• Gender Bias in Multilingual Neural Machine Translation: The Architecture Matters
• Image Transformation can make Neural Networks more robust against Adversarial Examples
• Neural Machine Translation: A Review of Methods, Resources, and Tools
• Multi-label Prediction in Time Series Data using Deep Neural Networks
• Clinical Text Summarization with Syntax-Based Negation and Semantic Concept Identification
• A Unified Linear-Time Framework for Sentence-Level Discourse Parsing
• ENGINE: Energy-Based Inference Networks for Non-Autoregressive Machine Translation
• Lattice Transformer for Speech Translation
• Improved Natural Language Generation via Loss Truncation
• Mixed Pooling Multi-View Attention Autoencoder for Representation Learning in Healthcare
• ISTD-GCN: Iterative Spatial-Temporal Diffusion Graph Convolutional Network for Traffic Speed Forecasting
• Adversarial Training with Contrastive Learning in NLP
• Towards Neural Decompilation
• Incremental Learning Using a Grow-and-Prune Paradigm with Efficient Neural Networks
• Keep CALM and Explore: Language Models for Action Generation in Text-based Games
• A Simple Dual-decoder Model for Generating Response with Sentiment
• AdvKnn: Adversarial Attacks On K-Nearest Neighbor Classifiers With Approximate Gradients
• Multilingual Multi-Domain Adaptation Approaches for Neural Machine Translation
• Detecting Context Dependent Messages in a Conversational Environment
• AdapNet: Adaptability Decomposing Encoder-Decoder Network for Weakly Supervised Action Recognition and Localization
• Reducing Quantity Hallucinations in Abstractive Summarization
• Deep Risk Model: A Deep Learning Solution for Mining Latent Risk Factors to Improve Covariance Matrix Estimation
• Insertion-Deletion Transformer
• Intelligent Video Editing: Incorporating Modern Talking Face Generation Algorithms in a Video Editor
• On Sparsifying Encoder Outputs in Sequence-to-Sequence Models
• A study of latent monotonic attention variants
• Deep Neural Network Based Active User Detection for Grant-free NOMA Systems
• Cycle-Consistent Adversarial Autoencoders for Unsupervised Text Style Transfer
• An Features Extraction and Recognition Method for Underwater Acoustic Target Based on ATCNN
• Multiscale Collaborative Deep Models for Neural Machine Translation
• Topic-aware Pointer-Generator Networks for Summarizing Spoken Conversations
• Efficient strategies for hierarchical text classification: External knowledge and auxiliary tasks
• Constrained Decoding for Neural NLG from Compositional Representations in Task-Oriented Dialogue
• Neural Chinese Word Segmentation as Sequence to Sequence Translation
• Probing Neural Dialog Models for Conversational Understanding
• Context Aware Machine Learning
• Large-Scale Self- and Semi-Supervised Learning for Speech Translation
• Anomaly Detection using Deep Reconstruction and Forecasting for Autonomous Systems
• Fast Sequence Generation with Multi-Agent Reinforcement Learning
• Towards Proof Synthesis Guided by Neural Machine Translation for Intuitionistic Propositional Logic
• A Generalized Reinforcement Learning Algorithm for Online 3D Bin-Packing
• Enterprise to Computer: Star Trek chatbot
• Uncertainty-Aware Lookahead Factor Models for Quantitative Investing
• CNN Is All You Need
• ReWE: Regressing Word Embeddings for Regularization of Neural Machine Translation Systems
• Learning Forward Reuse Distance
• Multi-Modal Generative Adversarial Network for Short Product Title Generation in Mobile E-Commerce
• Neural Machine Transliteration: Preliminary Results
• Opinion Recommendation using Neural Memory Model
• Transformers for One-Shot Visual Imitation
• Fully-hierarchical fine-grained prosody modeling for interpretable speech synthesis
• A Robust Hierarchical Graph Convolutional Network Model for Collaborative Filtering
• Towards Neural Machine Translation with Partially Aligned Corpora
• A Supervised Word Alignment Method based on Cross-Language Span Prediction using Multilingual BERT
• Delhi air quality prediction using LSTM deep learning models with a focus on COVID-19 lockdown
• The 2020 ESPnet update: new features, broadened applications, performance improvements, and future plans
• Denoising Pre-Training and Data Augmentation Strategies for Enhanced RDF Verbalization with Transformers
• Shared-Private Bilingual Word Embeddings for Neural Machine Translation
• Mask CTC: Non-Autoregressive End-to-End ASR with CTC and Mask Predict
• LSTM Easy-first Dependency Parsing with Pre-trained Word Embeddings and Character-level Word Embeddings in Vietnamese
• Neural Name Translation Improves Neural Machine Translation
• Generating Multiple Diverse Responses with Multi-Mapping and Posterior Mapping Selection
• Neural Network for NILM Based on Operational State Change Classification
• Bilingual-GAN: A Step Towards Parallel Text Generation
• Exploring Neural Models for Parsing Natural Language into First-Order Logic
• End-to-End Knowledge-Routed Relational Dialogue System for Automatic Diagnosis
• Enabling Automatic Repair of Source Code Vulnerabilities Using Data-Driven Methods
• Doubly-Attentive Decoder for Multi-modal Neural Machine Translation
• SuperChat: Dialogue Generation by Transfer Learning from Vision to Language using Two-dimensional Word Embedding and Pretrained ImageNet CNN Models
• Improving Question Generation With to the Point Context
• Deep execution monitor for robot assistive tasks
• Human Motion Anticipation with Symbolic Label
• Image Captioning based on Deep Learning Methods: A Survey
• AQEyes: Visual Analytics for Anomaly Detection and Examination of Air Quality Data
• Learning to Flip Successive Cancellation Decoding of Polar Codes with LSTM Networks
• Electrocardiogram Classification and Visual Diagnosis of Atrial Fibrillation with DenseECG
• Hierarchically Regularized Deep Forecasting
• Can You be More Social? Injecting Politeness and Positivity into Task-Oriented Conversational Agents
• A contribution to Optimal Transport on incomparable spaces
• Neural Response Generation with Meta-Words
• Trimming and Improving Skip-thought Vectors
• What Is Considered Complete for Visual Recognition?
• Distributional Reinforcement Learning for Energy-Based Sequential Models
• Weight Pruning via Adaptive Sparsity Loss
• A Markovian Model-Driven Deep Learning Framework for Massive MIMO CSI Feedback
• Generate, Prune, Select: A Pipeline for Counterspeech Generation against Online Hate Speech
• Retrieve and Refine: Exemplar-based Neural Comment Generation
• Incorporating Transformer and LSTM to Kalman Filter with EM algorithm for state estimation
• Audio-Linguistic Embeddings for Spoken Sentences
• Attention-based Vocabulary Selection for NMT Decoding
• Improving Semantic Relevance for Sequence-to-Sequence Learning of Chinese Social Media Text Summarization
• Activity2Vec: Learning ADL Embeddings from Sensor Data with a Sequence-to-Sequence Model
• Informative Image Captioning with External Sources of Information
• Automatic Conditional Generation of Personalized Social Media Short Texts
• Argument Generation with Retrieval, Planning, and Realization
• A Hierarchical Reinforced Sequence Operation Method for Unsupervised Text Style Transfer
• End-to-End Spoken Language Translation
• Discovery of Natural Language Concepts in Individual Units of CNNs
• Session-based Sequential Skip Prediction via Recurrent Neural Networks
• Adaptive Sequence Submodularity
• Evaluating Rewards for Question Generation Models
• Self-Attentive Model for Headline Generation
• A Data Efficient End-To-End Spoken Language Understanding Architecture
• On the Communication Latency of Wireless Decentralized Learning
• CoTK: An Open-Source Toolkit for Fast Development and Fair Evaluation of Text Generation
• Teaching Machines to Converse
• Visual Storytelling via Predicting Anchor Word Embeddings in the Stories
• Modeling Fluency and Faithfulness for Diverse Neural Machine Translation
• Fill in the Blanks: Imputing Missing Sentences for Larger-Context Neural Machine Translation
• Semantic-aware Image Deblurring
• Learning from Fact-checkers: Analysis and Generation of Fact-checking Language
• Improving Robustness and Generality of NLP Models Using Disentangled Representations
• HyperGrid: Efficient Multi-Task Transformers with Grid-wise Decomposable Hyper Projections
• Learning to Rank Learning Curves
• From Standard Summarization to New Tasks and Beyond: Summarization with Manifold Information
• Unsupervised Multimodal Neural Machine Translation with Pseudo Visual Pivoting
• Towards Unsupervised Language Understanding and Generation by Joint Dual Learning
• Designing Precise and Robust Dialogue Response Evaluators
• Generation of Realistic Cloud Access Times for Mobile Application Testing using Transfer Learning
• Active${}^2$ Learning: Actively reducing redundancies in Active Learning methods for Sequence Tagging and Machine Translation
• A Survey on Understanding, Visualizations, and Explanation of Deep Neural Networks
• Towards Natural Language Question Answering over Earth Observation Linked Data using Attention-based Neural Machine Translation
• Zero-shot Generalization in Dialog State Tracking through Generative Question Answering
• Why Neural Machine Translation Prefers Empty Outputs
• A Taxonomy of Empathetic Response Intents in Human Social Conversations
• MixSeq: Connecting Macroscopic Time Series Forecasting with Microscopic Time Series Data
• Smart at what cost? Characterising Mobile Deep Neural Networks in the wild
• A Unified Generative Framework for Various NER Subtasks
• Prevent the Language Model from being Overconfident in Neural Machine Translation
• Target Conditioned Sampling: Optimizing Data Selection for Multilingual Neural Machine Translation
• Question Answering as an Automatic Evaluation Metric for News Article Summarization
• Adaptive Nearest Neighbor Machine Translation
• Mollifying Networks
• Plug-Tagger: A Pluggable Sequence Labeling Framework Using Language Models
• Pre-Training for Query Rewriting in A Spoken Language Understanding System
• Regularizing Dialogue Generation by Imitating Implicit Scenarios
• Code-switching pre-training for neural machine translation
• Gaussian Smoothen Semantic Features (GSSF) -- Exploring the Linguistic Aspects of Visual Captioning in Indian Languages (Bengali) Using MSCOCO Framework
• memeBot: Towards Automatic Image Meme Generation
• AR: Auto-Repair the Synthetic Data for Neural Machine Translation
• Learning Oculomotor Behaviors from Scanpath
• Generating similes effortlessly like a Pro: A Style Transfer Approach for Simile Generation
• Learning Latent Local Conversation Modes for Predicting Community Endorsement in Online Discussions
• Sequence to Multi-Sequence Learning via Conditional Chain Mapping for Mixture Signals
• SACT: Self-Aware Multi-Space Feature Composition Transformer for Multinomial Attention for Video Captioning
• DiaNet: BERT and Hierarchical Attention Multi-Task Learning of Fine-Grained Dialect
• SASRA: Semantically-aware Spatio-temporal Reasoning Agent for Vision-and-Language Navigation in Continuous Environments
• Building Large Machine Reading-Comprehension Datasets using Paragraph Vectors
• DeepSoft: A vision for a deep model of software
• Text Generation with Exemplar-based Adaptive Decoding
• Evaluating Explanation Methods for Neural Machine Translation
• TensorCoder: Dimension-Wise Attention via Tensor Representation for Natural Language Modeling
• Parallel Data Augmentation for Formality Style Transfer
• A New Look at Ghost Normalization
• Towards a parallel corpus of Portuguese and the Bantu language Emakhuwa of Mozambique
• Learning from the Best: Rationalizing Prediction by Adversarial Information Calibration
• Practical Perspectives on Quality Estimation for Machine Translation
• Threshold-Based Retrieval and Textual Entailment Detection on Legal Bar Exam Questions
• Partial Discharge Detection on Aerial Covered Conductors Using Time-Series Decomposition and Long Short-term Memory Network
• Document-editing Assistants and Model-based Reinforcement Learning as a Path to Conversational AI
• A dataset for resolving referring expressions in spoken dialogue via contextual query rewrites (CQR)
• Unsupervised Representation Learning of DNA Sequences
• Learning Effective Representations for Person-Job Fit by Feature Fusion
• CFGs-2-NLU: Sequence-to-Sequence Learning for Mapping Utterances to Semantics and Pragmatics
• Candidate Fusion: Integrating Language Modelling into a Sequence-to-Sequence Handwritten Word Recognition Architecture
• LeafNATS: An Open-Source Toolkit and Live Demo System for Neural Abstractive Text Summarization
• Extract and Edit: An Alternative to Back-Translation for Unsupervised Neural Machine Translation
• Privacy Policy Question Answering Assistant: A Query-Guided Extractive Summarization Approach
• Word-based Domain Adaptation for Neural Machine Translation
• Tensorized Transformer for Dynamical Systems Modeling
• Evaluating Off-the-Shelf Machine Listening and Natural Language Models for Automated Audio Captioning
• One-Shot Learning on Attributed Sequences
• Efficient Synthesis of Compact Deep Neural Networks
• Learning from Videos with Deep Convolutional LSTM Networks
• Rethinking Perturbations in Encoder-Decoders for Fast Training
• Hierarchical Recurrent Neural Network for Video Summarization
• Graph Attention Recurrent Neural Networks for Correlated Time Series Forecasting -- Full version
• Unsupervised Representation for EHR Signals and Codes as Patient Status Vector
• Continuous 3D Multi-Channel Sign Language Production via Progressive Transformers and Mixture Density Networks
• Fast Prototyping a Dialogue Comprehension System for Nurse-Patient Conversations on Symptom Monitoring
• Learning to Reuse Translations: Guiding Neural Machine Translation with Examples
• Integrating Image Captioning with Rule-based Entity Masking
• Sentiment Analysis of German Twitter
• Scenario optimization for optimal training of Echo State Networks
• Fine-grained Sentiment Controlled Text Generation
• This Email Could Save Your Life: Introducing the Task of Email Subject Line Generation
• Keyword Extraction for Improved Document Retrieval in Conversational Search
• Variational Tracking and Prediction with Generative Disentangled State-Space Models
• Creative Procedural-Knowledge Extraction From Web Design Tutorials
• Spatio-Temporal LSTM with Trust Gates for 3D Human Action Recognition
• Attention Guided Dialogue State Tracking with Sparse Supervision
• CORE: Automatic Molecule Optimization Using Copy & Refine Strategy
• Deep Reinforcement Learning with Quantum-inspired Experience Replay
• Self-Attentive Constituency Parsing for UCCA-based Semantic Parsing
• Adaptive Transfer Learning of Multi-View Time Series Classification
• Automated Query Reformulation for Efficient Search based on Query Logs From Stack Overflow
• MATINF: A Jointly Labeled Large-Scale Dataset for Classification, Question Answering and Summarization
• Improving Question Generation with Sentence-level Semantic Matching and Answer Position Inferring
• Neural Academic Paper Generation
• Task-Oriented Conversation Generation Using Heterogeneous Memory Networks
• Using Sequence-to-Sequence Learning for Repairing C Vulnerabilities
• Learning Vehicle Routing Problems using Policy Optimisation
• Discriminative Multi-modality Speech Recognition
• Federated Natural Language Generation for Personalized Dialogue System
• Continuous Prediction of Lower-Limb Kinematics From Multi-Modal Biomedical Signals
• DeepPoison: Feature Transfer Based Stealthy Poisoning Attack
• Contrastive Attention Mechanism for Abstractive Sentence Summarization
• Persian Keyphrase Generation Using Sequence-to-Sequence Models
• Syntax-Infused Variational Autoencoder for Text Generation
• Context Attentive Document Ranking and Query Suggestion
• Efficient Computation Reduction in Bayesian Neural Networks Through Feature Decomposition and Memorization
• Speech-to-speech Translation between Untranscribed Unknown Languages
• Boosting Naturalness of Language in Task-oriented Dialogues via Adversarial Training
• DeepFault: Fault Localization for Deep Neural Networks
• Infusing Sequential Information into Conditional Masked Translation Model with Self-Review Mechanism
• A Competence-aware Curriculum for Visual Concepts Learning via Question Answering
• An Empirical Investigation of Global and Local Normalization for Recurrent Neural Sequence Models Using a Continuous Relaxation to Beam Search
• Pointing Novel Objects in Image Captioning
• Target Guided Emotion Aware Chat Machine
• Pre-training via Leveraging Assisting Languages and Data Selection for Neural Machine Translation
• Network Automatic Pruning: Start NAP and Take a Nap
• A New Perspective for Flexible Feature Gathering in Scene Text Recognition Via Character Anchor Pooling
• Task-Level Curriculum Learning for Non-Autoregressive Neural Machine Translation
• On the Discrepancy between Density Estimation and Sequence Generation
• Computational Morphology with Neural Network Approaches
• Improving Human Text Comprehension through Semi-Markov CRF-based Neural Section Title Generation
• Pretraining Techniques for Sequence-to-Sequence Voice Conversion
• Improving the Transferability of Adversarial Examples with New Iteration Framework and Input Dropout
• Automatic Neural Lyrics and Melody Composition
• A Worrying Analysis of Probabilistic Time-series Models for Sales Forecasting
• Pruning-then-Expanding Model for Domain Adaptation of Neural Machine Translation
• Multi-Service Mobile Traffic Forecasting via Convolutional Long Short-Term Memories
• Differential Recurrent Neural Network and its Application for Human Activity Recognition
• Automatic Fairness Testing of Neural Classifiers through Adversarial Sampling
• Understanding Contexts Inside Robot and Human Manipulation Tasks through a Vision-Language Model and Ontology System in a Video Stream
• GraphTTS: graph-to-sequence modelling in neural text-to-speech
• Multi-task Learning for Multilingual Neural Machine Translation
• A Syllable-Structured, Contextually-Based Conditionally Generation of Chinese Lyrics
• ISA: An Intelligent Shopping Assistant
• Improving Bidirectional Decoding with Dynamic Target Semantics in Neural Machine Translation
• Forecasting in multivariate irregularly sampled time series with missing values
• Embeddings and Representation Learning for Structured Data
• Recurrent Neural Network-based Model for Accelerated Trajectory Analysis in AIMD Simulations
• Improving generation quality of pointer networks via guided attention
• Meta-Curriculum Learning for Domain Adaptation in Neural Machine Translation
• Human Action Sequence Classification
• Multi-Task Time Series Forecasting With Shared Attention
• Multilingual Speech Recognition for Low-Resource Indian Languages using Multi-Task conformer
• Computer Assisted Translation with Neural Quality Estimation and Automatic Post-Editing
• Improving type information inferred by decompilers with supervised machine learning
• Automated Radiological Report Generation For Chest X-Rays With Weakly-Supervised End-to-End Deep Learning
• Latent Space Cartography: Generalised Metric-Inspired Measures and Measure-Based Transformations for Generative Models
• Controlling Utterance Length in NMT-based Word Segmentation with Attention
• RefSum: Refactoring Neural Summarization
• Bilingual Mutual Information Based Adaptive Training for Neural Machine Translation
• 3D Human motion anticipation and classification
• Condition-Transforming Variational AutoEncoder for Conversation Response Generation
• Exploiting Method Names to Improve Code Summarization: A Deliberation Multi-Task Learning Approach
• A Large-Scale CNN Ensemble for Medication Safety Analysis
• Neural network-based modelling of unresolved stresses in a turbulent reacting flow with mean shear
• Semantic Parsing with Dual Learning
• Alleviate Exposure Bias in Sequence Prediction \\ with Recurrent Neural Networks
• A Transformer-based Audio Captioning Model with Keyword Estimation
• Constrained Text Generation with Global Guidance -- Case Study on CommonGen
• Multilevel Text Normalization with Sequence-to-Sequence Networks and Multisource Learning
• Towards Enhancing Database Education: Natural Language Generation Meets Query Execution Plans
• Retrieve Synonymous keywords for Frequent Queries in Sponsored Search in a Data Augmentation Way
• Controllable and Diverse Text Generation in E-commerce
• Sequence-Level Training for Non-Autoregressive Neural Machine Translation
• PoMo: Generating Entity-Specific Post-Modifiers in Context
• On the Regularity of Attention
• Learning to Select Context in a Hierarchical and Global Perspective for Open-domain Dialogue Generation
• Meta Back-translation
• Learning Knowledge Graph-based World Models of Textual Environments
• Tackling Graphical NLP problems with Graph Recurrent Networks
• Sequence to General Tree: Knowledge-Guided Geometry Word Problem Solving
• Real-Time Neural Network Scheduling of Emergency Medical Mask Production during COVID-19
• SMART: Simultaneous Multi-Agent Recurrent Trajectory Prediction
• Multilingual Dialogue Generation with Shared-Private Memory
• Language Tags Matter for Zero-Shot Neural Machine Translation
• Partially-Aligned Data-to-Text Generation with Distant Supervision
• Artificial Neural Network for Cybersecurity: A Comprehensive Review
• Lessons Learned from Applying off-the-shelf BERT: There is no Silver Bullet
• Sentence-Level BERT and Multi-Task Learning of Age and Gender in Social Media
• Android Security using NLP Techniques: A Review
• Simulating multi-exit evacuation using deep reinforcement learning
• The Pitfall of Evaluating Performance on Emerging AI Accelerators
• Character n-gram Embeddings to Improve RNN Language Models
• Ensemble Fine-tuned mBERT for Translation Quality Estimation
• Memory Augmented Multi-Instance Contrastive Predictive Coding for Sequential Recommendation
• I-BERT: Inductive Generalization of Transformer to Arbitrary Context Lengths
• KoSpeech: Open-Source Toolkit for End-to-End Korean Speech Recognition
• Guiding Topic Flows in the Generative Chatbot by Enhancing the ConceptNet with the Conversation Corpora
• Integrated Training for Sequence-to-Sequence Models Using Non-Autoregressive Transformer
• Co-Attention Hierarchical Network: Generating Coherent Long Distractors for Reading Comprehension
• Empirical Autopsy of Deep Video Captioning Frameworks
• Go From the General to the Particular: Multi-Domain Translation with Domain Transformation Networks
• DeepSmartFuzzer: Reward Guided Test Generation For Deep Learning
• Relevance-Promoting Language Model for Short-Text Conversation
• Self-and-Mixed Attention Decoder with Deep Acoustic Structure for Transformer-based LVCSR
• Human-like general language processing
• Neural Machine Translation with Explicit Phrase Alignment
• Deep learning approaches for neural decoding: from CNNs to LSTMs and spikes to fMRI
• The MUIR Framework: Cross-Linking MOOC Resources to Enhance Discussion Forums
• Improved Word Sense Disambiguation Using Pre-Trained Contextualized Word Representations
• A Feasible Framework for Arbitrary-Shaped Scene Text Recognition
• A Framework for Hierarchical Multilingual Machine Translation
• Dialogue Generation on Infrequent Sentence Functions via Structured Meta-Learning
• JASS: Japanese-specific Sequence to Sequence Pre-training for Neural Machine Translation
• Improving Long Distance Slot Carryover in Spoken Dialogue Systems
• Alignment Attention by Matching Key and Query Distributions
• When to Talk: Chatbot Controls the Timing of Talking during Multi-turn Open-domain Dialogue Generation
• Relational State-Space Model for Stochastic Multi-Object Systems
• Coursera Corpus Mining and Multistage Fine-Tuning for Improving Lectures Translation
• Data Troubles in Sentence Level Confidence Estimation for Machine Translation
• User-in-the-loop Adaptive Intent Detection for Instructable Digital Assistant
• Machine Translation Evaluation with Neural Networks
• Emotion Eliciting Machine: Emotion Eliciting Conversation Generation based on Dual Generator
• Understanding Pure Character-Based Neural Machine Translation: The Case of Translating Finnish into English
• Sample-Efficient Model-based Actor-Critic for an Interactive Dialogue Task
• Assessing the Bilingual Knowledge Learned by Neural Machine Translation Models
• Weakly Supervised POS Taggers Perform Poorly on Truly Low-Resource Languages
• A Neural, Interactive-predictive System for Multimodal Sequence to Sequence Tasks
• An Overview on Data Representation Learning: From Traditional Feature Learning to Recent Deep Learning
• Look-ahead Attention for Generation in Neural Machine Translation
• Deep Generation of Coq Lemma Names Using Elaborated Terms
• Knowledge-graph based Proactive Dialogue Generation with Improved Meta-Learning
• Hierarchical Memory Decoding for Video Captioning
• Coarse-to-fine: A RNN-based hierarchical attention model for vehicle re-identification
• Blind Adversarial Training: Balance Accuracy and Robustness
• Microblog Hashtag Generation via Encoding Conversation Contexts
• Explicit Reordering for Neural Machine Translation
• Prose for a Painting
• Selective Knowledge Distillation for Neural Machine Translation
• Predicting the Mumble of Wireless Channel with Sequence-to-Sequence Models
• Doubly Sparse: Sparse Mixture of Sparse Experts for Efficient Softmax Inference
• Synchronous Bidirectional Neural Machine Translation
• A Stock Selection Method Based on Earning Yield Forecast Using Sequence Prediction Models
• GraphPB: Graphical Representations of Prosody Boundary in Speech Synthesis
• WSRNet: Joint Spotting and Recognition of Handwritten Words
• Promoting Diversity for End-to-End Conversation Response Generation
• On the Importance of Local Information in Transformer Based Models
• Learning to Generate Code Comments from Class Hierarchies
• Sequence Generation: From Both Sides to the Middle
• Tree-Structured Semantic Encoder with Knowledge Sharing for Domain Adaptation in Natural Language Generation
• A Compare Aggregate Transformer for Understanding Document-grounded Dialogue
• A Context Integrated Relational Spatio-Temporal Model for Demand and Supply Forecasting
• Word, Subword or Character? An Empirical Study of Granularity in Chinese-English NMT
• An Interactive Machine Translation Framework for Modernizing Historical Documents
• Long-Short Term Masking Transformer: A Simple but Effective Baseline for Document-level Neural Machine Translation
• Characterization of Gravitational Waves Signals Using Neural Networks
• Central Yup'ik and Machine Translation of Low-Resource Polysynthetic Languages
• Tell-the-difference: Fine-grained Visual Descriptor via a Discriminating Referee
• Mixture of Speaker-type PLDAs for Children's Speech Diarization
• Knowledge Efficient Deep Learning for Natural Language Processing
• Opinion-aware Answer Generation for Review-driven Question Answering in E-Commerce
• A constrained recursion algorithm for batch normalization of tree-sturctured LSTM
• An Empirical Study of Generation Order for Machine Translation
• Fully Dynamic Inference with Deep Neural Networks
• Sound2Sight: Generating Visual Dynamics from Sound and Context
• Feedback Recurrent AutoEncoder
• NaviGAN: A Generative Approach for Socially Compliant Navigation
• Dynamic Graph Embedding via LSTM History Tracking
• Correction of Faulty Background Knowledge based on Condition Aware and Revise Transformer for Question Answering
• ANA at SemEval-2020 Task 4: mUlti-task learNIng for cOmmonsense reasoNing (UNION)
• Deep Transfer Learning for Thermal Dynamics Modeling in Smart Buildings
• Revisiting Regex Generation for Modeling Industrial Applications by Incorporating Byte Pair Encoder
• Sequence-to-Set Semantic Tagging: End-to-End Multi-label Prediction using Neural Attention for Complex Query Reformulation and Automated Text Categorization
• A Variational View on Bootstrap Ensembles as Bayesian Inference
• Learning Various Length Dependence by Dual Recurrent Neural Networks
• Bridging the Gap Between Training and Inference for Spatio-Temporal Forecasting
• Learning to Model Aspects of Hearing Perception Using Neural Loss Functions
• Deep Exemplar Networks for VQA and VQG
• Generating Pertinent and Diversified Comments with Topic-aware Pointer-Generator Networks
• Decoding of visual-related information from the human EEG using an end-to-end deep learning approach
• CounterExample Guided Neural Synthesis
• Explainable Deep RDFS Reasoner
• How Chaotic Are Recurrent Neural Networks?
• Balancing Cost and Benefit with Tied-Multi Transformers
• SMArtCast: Predicting soil moisture interpolations into the future using Earth observation data in a deep learning framework
• Fast and Accurate Deep Bidirectional Language Representations for Unsupervised Learning
• Sequential Gating Ensemble Network for Noise Robust Multi-Scale Face Restoration
• High-performance Decoder for Convolutional Code with Deep Neural Network
• Machine Translation with Unsupervised Length-Constraints
• Hierarchical Cross-Modal Agent for Robotics Vision-and-Language Navigation
• Privacy-aware VR streaming
• Learning Evolved Combinatorial Symbols with a Neuro-symbolic Generative Model
• Dating Documents using Graph Convolution Networks
• Probabilistic Modeling for Novelty Detection with Applications to Fraud Identification
• Self-supervised Regularization for Text Classification
• Smoothing and Shrinking the Sparse Seq2Seq Search Space
• Neural Code Summarization
• Benchmarking Approximate Inference Methods for Neural Structured Prediction
• Experiments with Rich Regime Training for Deep Learning
• Learning to Stop in Structured Prediction for Neural Machine Translation
• Triple M: A Practical Text-to-speech Synthesis System With Multi-guidance Attention And Multi-band Multi-time LPCNet
• End-to-End Language Identification using Multi-Head Self-Attention and 1D Convolutional Neural Networks
• KoreALBERT: Pretraining a Lite BERT Model for Korean Language Understanding
• $k$-Neighbor Based Curriculum Sampling for Sequence Prediction
• Neural Multi-Source Morphological Reinflection
• NNStreamer: Efficient and Agile Development of On-Device AI Systems
• Towards Fully Automated Manga Translation
• Seq2Biseq: Bidirectional Output-wise Recurrent Neural Networks for Sequence Modelling
• Multi-view Temporal Alignment for Non-parallel Articulatory-to-Acoustic Speech Synthesis
• Neural Text Generation from Rich Semantic Representations
• Disentangling semantics in language through VAEs and a certain architectural choice
• Knowing When to Stop: Evaluation and Verification of Conformity to Output-size Specifications
• Domain Adaptation of NMT models for English-Hindi Machine Translation Task at AdapMT ICON 2020
• Differentiable Sampling with Flexible Reference Word Order for Neural Machine Translation
• Leaking Sensitive Financial Accounting Data in Plain Sight using Deep Autoencoder Neural Networks
• End-to-End Interpretation of the French Street Name Signs Dataset
• BERT-hLSTMs: BERT and Hierarchical LSTMs for Visual Storytelling
• Language Generation via Combinatorial Constraint Satisfaction: A Tree Search Enhanced Monte-Carlo Approach
• Investigating Catastrophic Forgetting During Continual Training for Neural Machine Translation
• A Non-linear Function-on-Function Model for Regression with Time Series Data
• Simultaneously forecasting global geomagnetic activity using Recurrent Networks
• ReAssert: Deep Learning for Assert Generation
• Compositional pre-training for neural semantic parsing
• BERT-JAM: Boosting BERT-Enhanced Neural Machine Translation with Joint Attention
• Accurate and Energy-Efficient Classification with Spiking Random Neural Network: Corrected and Expanded Version
• MLAS: Metric Learning on Attributed Sequences
• A Semi-Supervised Approach for Low-Resourced Text Generation
• Disruption in the Chinese E-Commerce During COVID-19
• A Deep Learning Technique using Low Sampling rate for residential Non Intrusive Load Monitoring
• Detecting Logical Relation In Contract Clauses
• EmpBot: A T5-based Empathetic Chatbot focusing on Sentiments
• Self-attention Multi-view Representation Learning with Diversity-promoting Complementarity
• Hierarchical Aspect-guided Explanation Generation for Explainable Recommendation
• Semi-Autoregressive Image Captioning
• Building an Efficient and Effective Retrieval-based Dialogue System via Mutual Learning
• Learning Neural Templates for Recommender Dialogue System
• Learning Neural Models for Natural Language Processing in the Face of Distributional Shift
• Graphine: A Dataset for Graph-aware Terminology Definition Generation
• Empathetic Dialogue Generation with Pre-trained RoBERTa-GPT2 and External Knowledge
• Sequence-to-Sequence Learning on Keywords for Efficient FAQ Retrieval
• A Dual-Decoder Conformer for Multilingual Speech Recognition
• Incorporating Reachability Knowledge into a Multi-Spatial Graph Convolution Based Seq2Seq Model for Traffic Forecasting
• A Joint and Domain-Adaptive Approach to Spoken Language Understanding
• Towards Controlled and Diverse Generation of Article Comments
• On the Copying Behaviors of Pre-Training for Neural Machine Translation
• Putting words into the system's mouth: A targeted attack on neural machine translation using monolingual data poisoning
• Automatic Acrostic Couplet Generation with Three-Stage Neural Network Pipelines
• A Hierarchical Attention Based Seq2seq Model for Chinese Lyrics Generation
• Memory and attention in deep learning
• A Training-free and Reference-free Summarization Evaluation Metric via Centrality-weighted Relevance and Self-referenced Redundancy
• Stuck? No worries!: Task-aware Command Recommendation and Proactive Help for Analysts
• byteSteady: Fast Classification Using Byte-Level n-Gram Embeddings
• Symmetric Wasserstein Autoencoders
• Towards Fully Interpretable Deep Neural Networks: Are We There Yet?
• Maria: A Visual Experience Powered Conversational Agent
• Improving Performance of Seen and Unseen Speech Style Transfer in End-to-end Neural TTS
• Modeling Worlds in Text
• On the Definition of Japanese Word
• Alternated Training with Synthetic and Authentic Data for Neural Machine Translation
• Guiding Teacher Forcing with Seer Forcing for Neural Machine Translation
• Crosslingual Embeddings are Essential in UNMT for Distant Languages: An English to IndoAryan Case Study
• Deep Learning: Hydrodynamics, and Lie-Poisson Hamilton-Jacobi Theory
• Depth Growing for Neural Machine Translation
• Approximate Fixed-Points in Recurrent Neural Networks
• Improving Computer Generated Dialog with Auxiliary Loss Functions and Custom Evaluation Metrics
• Language Embeddings for Typology and Cross-lingual Transfer Learning
• A Neural Turing~Machine for Conditional Transition Graph Modeling
• A Neural Attention Model for Categorizing Patient Safety Events
• On the benefits of maximum likelihood estimation for Regression and Forecasting
• Grammatical Error Correction as GAN-like Sequence Labeling
• LIG-CRIStAL System for the WMT17 Automatic Post-Editing Task
• VANiLLa : Verbalized Answers in Natural Language at Large Scale
• Additional Shared Decoder on Siamese Multi-view Encoders for Learning Acoustic Word Embeddings
• DyKgChat: Benchmarking Dialogue Generation Grounding on Dynamic Knowledge Graphs
• Read, Attend and Comment: A Deep Architecture for Automatic News Comment Generation
• Towards Controllable and Personalized Review Generation
• Semi-supervised Text Style Transfer: Cross Projection in Latent Space
• Clinical Text Generation through Leveraging Medical Concept and Relations
• DLGNet-Task: An End-to-end Neural Network Framework for Modeling Multi-turn Multi-domain Task-Oriented Dialogue
• StyleDGPT: Stylized Response Generation with Pre-trained Language Models
• Master Thesis: Neural Sign Language Translation by Learning Tokenization
• OrderNet: Ordering by Example
• Incorporating Behavioral Hypotheses for Query Generation
• Learning by stochastic serializations
• Learning to Encode Evolutionary Knowledge for Automatic Commenting Long Novels
• DORB: Dynamically Optimizing Multiple Rewards with Bandits
• To Schedule or not to Schedule: Extracting Task Specific Temporal Entities and Associated Negation Constraints
• Malicious Requests Detection with Improved Bidirectional Long Short-term Memory Neural Networks
• Incorporating a Local Translation Mechanism into Non-autoregressive Translation
• AriEL: volume coding for sentence generation
• Hybrid Embedded Deep Stacked Sparse Autoencoder with w_LPPD SVM Ensemble
• Application of Deep Interpolation Network for Clustering of Physiologic Time Series
• Dual Attentive Sequential Learning for Cross-Domain Click-Through Rate Prediction
• MultiOpEd: A Corpus of Multi-Perspective News Editorials
• Machine Translation for Machines: the Sentiment Classification Use Case
• Learning to Generate Multiple Style Transfer Outputs for an Input Sentence
• Improving Prosody Modelling with Cross-Utterance BERT Embeddings for End-to-end Speech Synthesis
• Adversarial Generation and Encoding of Nested Texts
• Automating App Review Response Generation
• Chess2vec: Learning Vector Representations for Chess
• Bi-Decoder Augmented Network for Neural Machine Translation
• Focus-Constrained Attention Mechanism for CVAE-based Response Generation
• Deep Learning in Ultrasound Elastography Imaging
• Autoregressive Knowledge Distillation through Imitation Learning
• Regressing Word and Sentence Embeddings for Regularization of Neural Machine Translation
• Dynamic Programming Encoding for Subword Segmentation in Neural Machine Translation
• Examining the causal structures of deep neural networks using information theory
• A New Data Normalization Method to Improve Dialogue Generation by Minimizing Long Tail Effect
• Learning from Multiple Time Series: A Deep Disentangled Approach to Diversified Time Series Forecasting
• PDPGD: Primal-Dual Proximal Gradient Descent Adversarial Attack
• Developing neural machine translation models for Hungarian-English
• Dialogue Inspectional Summarization with Factual Inconsistency Awareness
• Medicines Question Answering System, MeQA
• Reducing the impact of out of vocabulary words in the translation of natural language questions into SPARQL queries
• Massive Styles Transfer with Limited Labeled Data
• Universality of Gradient Descent Neural Network Training
• Accelerating Genome Sequence Analysis via Efficient Hardware/Algorithm Co-Design
• Neural or Statistical: An Empirical Study on Language Models for Chinese Input Recommendation on Mobile
• Empirical Analysis of Korean Public AI Hub Parallel Corpora and in-depth Analysis using LIWC
• A Dataset and Baselines for Multilingual Reply Suggestion
• Cluster-and-Conquer: A Framework For Time-Series Forecasting
• Improving Truthfulness of Headline Generation
• A Preliminary Study of a Two-Stage Paradigm for Preserving Speaker Identity in Dysarthric Voice Conversion
• Adaptive Bridge between Training and Inference for Dialogue
• Building A User-Centric and Content-Driven Socialbot
• Neural network based limiter with transfer learning
• Learning to Detect Unacceptable Machine Translations for Downstream Tasks
• Iterative Self-Learning: Semi-Supervised Improvement to Dataset Volumes and Model Accuracy
• Token Manipulation Generative Adversarial Network for Text Generation
• Generating summaries tailored to target characteristics
• Unsupervised Context Rewriting for Open Domain Conversation
• Response-Anticipated Memory for On-Demand Knowledge Integration in Response Generation
• CoRGi: Content-Rich Graph Neural Networks with Attention
• Explaining the Attention Mechanism of End-to-End Speech Recognition Using Decision Trees
• Pairwise Neural Machine Translation Evaluation
• Disarranged Zone Learning (DZL): An unsupervised and dynamic automatic stenosis recognition methodology based on coronary angiography
• Improving Zero-shot Multilingual Neural Machine Translation for Low-Resource Languages
• Mapping Language to Programs using Multiple Reward Components with Inverse Reinforcement Learning
• Big Bidirectional Insertion Representations for Documents
• Jejueo Datasets for Machine Translation and Speech Synthesis
• Link Prediction for Temporally Consistent Networks
• DSNet: Dynamic Skin Deformation Prediction by Recurrent Neural Network
• Nana-HDR: A Non-attentive Non-autoregressive Hybrid Model for TTS
• Deep Minimax Probability Machine
• Urban Traffic Flow Forecast Based on FastGCRNN
• Byte-Pair Encoding for Text-to-SQL Generation
• Multi-Step Chord Sequence Prediction Based on Aggregated Multi-Scale Encoder-Decoder Network
• Navigating the Kaleidoscope of COVID-19 Misinformation Using Deep Learning
• Isometric Graph Neural Networks
• CodeQA: A Question Answering Dataset for Source Code Comprehension
• Total Recall: a Customized Continual Learning Method for Neural Semantic Parsers
• A Three Step Training Approach with Data Augmentation for Morphological Inflection
• Robust Retrieval Augmented Generation for Zero-shot Slot Filling
• Iterative Edit-Based Unsupervised Sentence Simplification
• Text Recognition in Real Scenarios with a Few Labeled Samples
• Looking for Confirmations: An Effective and Human-Like Visual Dialogue Strategy
• Sequential Modelling with Applications to Music Recommendation, Fact-Checking, and Speed Reading
• SummerTime: Text Summarization Toolkit for Non-experts
• Stylized Text Generation Using Wasserstein Autoencoders with a Mixture of Gaussian Prior
• Augmenting BERT-style Models with Predictive Coding to Improve Discourse-level Representations
• AfroMT: Pretraining Strategies and Reproducible Benchmarks for Translation of 8 African Languages
• HintedBT: Augmenting Back-Translation with Quality and Transliteration Hints
• Decoupling Hierarchical Recurrent Neural Networks With Locally Computable Losses
• Medically Aware GPT-3 as a Data Generator for Medical Dialogue Summarization
• Competence-based Curriculum Learning for Multilingual Machine Translation
• Understanding Neural Machine Translation by Simplification: The Case of Encoder-free Models
• Thinking Clearly, Talking Fast: Concept-Guided Non-Autoregressive Generation for Open-Domain Dialogue Systems
• A Three-Stage Learning Framework for Low-Resource Knowledge-Grounded Dialogue Generation
• ARMAN: Pre-training with Semantically Selecting and Reordering of Sentences for Persian Abstractive Summarization
• Language Model-Driven Unsupervised Neural Machine Translation
• Encouraging Paragraph Embeddings to Remember Sentence Identity Improves Classification
• Highly Parallel Autoregressive Entity Linking with Discriminative Correction
• Automatic Generation of Personalized Comment Based on User Profile
• Towards Making the Most of Dialogue Characteristics for Neural Chat Translation
• ConRPG: Paraphrase Generation using Contexts as Regularizer
• Text AutoAugment: Learning Compositional Augmentation Policy for Text Classification
• Table-to-Text Natural Language Generation with Unseen Schemas
• Scheduled Sampling Based on Decoding Steps for Neural Machine Translation
• Recurrent multiple shared layers in Depth for Neural Machine Translation
• Keeping Notes: Conditional Natural Language Generation with a Scratchpad Mechanism
• Learning Source Phrase Representations for Neural Machine Translation
• A New Sentence Ordering Method Using BERT Pretrained Model
• Modular End-to-end Automatic Speech Recognition Framework for Acoustic-to-word Model
• Computational Analysis of Deformable Manifolds: from Geometric Modelling to Deep Learning
• MvSR-NAT: Multi-view Subset Regularization for Non-Autoregressive Machine Translation
• Generating Questions for Knowledge Bases via Incorporating Diversified Contexts and Answer-Aware Loss
• What can Neural Referential Form Selectors Learn?
• FOX-NAS: Fast, On-device and Explainable Neural Architecture Search
• Emotional speech synthesis with rich and granularized control
• Neural Twins Talk & Alternative Calculations
• Knowledge Distillation from BERT Transformer to Speech Transformer for Intent Classification
• Training Neural Machine Translation (NMT) Models using Tensor Train Decomposition on TensorFlow (T3F)
• Deep Natural Language Processing for LinkedIn Search Systems
• Conditioned Time-Dilated Convolutions for Sound Event Detection
• Semantic Representation for Dialogue Modeling
• Learn to Focus: Hierarchical Dynamic Copy Network for Dialogue State Tracking
• Syntax Customized Video Captioning by Imitating Exemplar Sentences
• Modeling Bilingual Conversational Characteristics for Neural Chat Translation
• Residual Tree Aggregation of Layers for Neural Machine Translation
• Imperial College London Submission to VATEX Video Captioning Task
• Importance-based Neuron Allocation for Multilingual Neural Machine Translation
• Diversifying Topic-Coherent Response Generation for Natural Multi-turn Conversations
• Multi-Modal Association based Grouping for Form Structure Extraction
• Form2Seq : A Framework for Higher-Order Form Structure Extraction
• Predictive Coding Networks Meet Action Recognition
• Language coverage and generalization in RNN-based continuous sentence embeddings for interacting agents
• Improving Word Representations: A Sub-sampled Unigram Distribution for Negative Sampling
• Cross-Modal Transformer-Based Neural Correction Models for Automatic Speech Recognition
• A Topic Guided Pointer-Generator Model for Generating Natural Language Code Summaries
• A language processing algorithm for predicting tactical solutions to an operational planning problem under uncertainty
• Tabula nearly rasa: Probing the Linguistic Knowledge of Character-Level Neural Language Models Trained on Unsegmented Text
• Can Transformers Jump Around Right in Natural Language? Assessing Performance Transfer from SCAN
• A new approach to forecast service parts demand by integrating user preferences into multi-objective optimization
• Invertible Attention
• Spending Money Wisely: Online Electronic Coupon Allocation based on Real-Time User Intent Detection
• XL-Sum: Large-Scale Multilingual Abstractive Summarization for 44 Languages
• Leveraging Acoustic and Linguistic Embeddings from Pretrained speech and language Models for Intent Classification
• Variational Bayesian Sequence-to-Sequence Networks for Memory-Efficient Sign Language Translation
• Introducing the Hidden Neural Markov Chain framework
• Learning Composable Behavior Embeddings for Long-horizon Visual Navigation
• Understanding and Enhancing the Use of Context for Machine Translation
• A Concept Knowledge-Driven Keywords Retrieval Framework for Sponsored Search
• Learning to Decipher Hate Symbols
• Two Demonstrations of the Machine Translation Applications to Historical Documents
• Machine translation considering context information using Encoder-Decoder model
• Synergetic Learning of Heterogeneous Temporal Sequences for Multi-Horizon Probabilistic Forecasting
• Irregular Convolutional Auto-Encoder on Point Clouds
• AGSTN: Learning Attention-adjusted Graph Spatio-Temporal Networks for Short-term Urban Sensor Value Forecasting
• Joint Intent Detection And Slot Filling Based on Continual Learning Model
• Affinity-aware Compression and Expansion Network for Human Parsing
• Few-Shot Semantic Parsing for New Predicates
• The LOB Recreation Model: Predicting the Limit Order Book from TAQ History Using an Ordinary Differential Equation Recurrent Neural Network
• Corpora Generation for Grammatical Error Correction
• Self-Checking Deep Neural Networks in Deployment
• SunCast: Solar Irradiance Nowcasting from Geosynchronous Satellite Data
• Learning by Planning: Language-Guided Global Image Editing
• One2Set: Generating Diverse Keyphrases as a Set
• Analysis of Convolutional Decoder for Image Caption Generation
• VATEX Captioning Challenge 2019: Multi-modal Information Fusion and Multi-stage Training Strategy for Video Captioning
• Self-Learning for Zero Shot Neural Machine Translation
• Adversarial Machine Learning in Text Analysis and Generation
• Improve Diverse Text Generation by Self Labeling Conditional Variational Auto Encoder
• CUED_speech at TREC 2020 Podcast Summarisation Track
• Machine Translation in Pronunciation Space
• Token-wise Curriculum Learning for Neural Machine Translation
• ROPE: Reading Order Equivariant Positional Encoding for Graph-based Document Information Extraction
• DICE: Deep Significance Clustering for Outcome-Aware Stratification
• Improving Generalization of Deep Networks for Inverse Reconstruction of Image Sequences
• A Multiplexed Network for End-to-End, Multilingual OCR
• Deep Learning for Latent Events Forecasting in Twitter Aided Caching Networks
• CNN with large memory layers
• PLAN-B: Predicting Likely Alternative Next Best Sequences for Action Prediction
• Neural Network-Based Dynamic Threshold Detection for Non-Volatile Memories
• Overprotective Training Environments Fall Short at Testing Time: Let Models Contribute to Their Own Training
• Predicting future astronomical events using deep learning
• Dual Past and Future for Neural Machine Translation
• A Robust Data-Driven Approach for Dialogue State Tracking of Unseen Slot Values
• Continuity of Topic, Interaction, and Query: Learning to Quote in Online Conversations
• Repairing Pronouns in Translation with BERT-Based Post-Editing
• Actions Generation from Captions
• Dyadic Human Motion Prediction
• Automated Knee X-ray Report Generation
• Balancing Robustness and Sensitivity using Feature Contrastive Learning
• Dual-CLVSA: a Novel Deep Learning Approach to Predict Financial Markets with Sentiment Measurements
• Towards Controlled Transformation of Sentiment in Sentences
• Understood in Translation, Transformers for Domain Understanding
• Research on All-content Text Recognition Method for Financial Ticket Image
• Improvement of a dedicated model for open domain persona-aware dialogue generation
• Proteno: Text Normalization with Limited Data for Fast Deployment in Text to Speech Systems
• DVE: Dynamic Variational Embeddings with Applications in Recommender Systems
• The Role of Interpretable Patterns in Deep Learning for Morphology
• Sensor-Based Continuous Hand Gesture Recognition by Long Short-Term Memory
• Data-Efficient Methods for Dialogue Systems
• Reciprocal Supervised Learning Improves Neural Machine Translation
• Delexicalized Paraphrase Generation
• Put Chatbot into Its Interlocutor's Shoes: New Framework to Learn Chatbot Responding with Intention
• Modeling Coverage for Non-Autoregressive Neural Machine Translation
• Multilingual Neural Semantic Parsing for Low-Resourced Languages
• Math Operation Embeddings for Open-ended Solution Analysis and Feedback
• Learning to Summarize Passages: Mining Passage-Summary Pairs from Wikipedia Revision Histories
• Atom Responding Machine for Dialog Generation
• Estimating Rationally Inattentive Utility Functions with Deep Clustering for Framing - Applications in YouTube Engagement Dynamics
• CLARA: Clinical Report Auto-completion
• Acoustic-to-Word Models with Conversational Context Information
• Predicting Path Failure In Time-Evolving Graphs
• Input-to-Output Gate to Improve RNN Language Models
• Towards User-Driven Neural Machine Translation
• Guider l'attention dans les modeles de sequence a sequence pour la prediction des actes de dialogue
• Unsupervised Spoken Term Discovery on Untranscribed Speech
• Unsupervised learning for economic risk evaluation in the context of Covid-19 pandemic
• The University of Sydney's Machine Translation System for WMT19
• End-to-end Silent Speech Recognition with Acoustic Sensing
• Neural Data-to-Text Generation with Dynamic Content Planning
• Bag-of-Vector Embeddings of Dependency Graphs for Semantic Induction
• Robot Gaining Accurate Pouring Skills through Self-Supervised Learning and Generalization
• Decoupling feature propagation from the design of graph auto-encoders