A list of papers for machine learning, deep learning, reinforcement learning, NLP and something interesting.
Recommendations or contributions are all welcome!
- Bentchmark or Datasets
- Toolkit
- Language Models
- Visual Question Answering
- Representation Learning
- Natural Language Inference
- Machine Reading Comprehension
- Open Domain Question Answering(Information Retrieval)
- Claim Verification
- Document Summarization
- Commonsense Reasoning
- Machine Translation
- Natural Language Generation
- Interpretability of Machine Learning
- Low Resources Task
- Multi-Task Learning
- Knowledge
- Transfer Learning
- Attention Mechanism
- Reinforcement Learning
- Dialog System
- Graph Neural Network
- Self-Supervised Learning
- Semi-Supervised Learning
- Variational Auto Encoder
- GAN
- Theory
- Waiting List
- Some Interesting or Useful Blogs
CLEVR-Dialog: A Diagnostic Dataset for Multi-Round Reasoning in Visual Dialog
DREAM: A Challenge Dataset and Models for Dialogue-Based Reading Comprehension
DROP: A Reading Comprehension Benchmark Requiring Discrete Reasoning Over Paragraphs
A dataset for resolving referring expressions in spoken dialogue via contextual query rewrites (CQR)
SocialIQA: Commonsense Reasoning about Social Interactions
HEAD-QA: A Healthcare Dataset for Complex Reasoning
TweetQA: Question Answering in Social Media
Introducing long-form question answering
Multi-class Hierarchical Question Classification for Multiple Choice Science Exams
XCMRC: Evaluating Cross-lingual Machine Reading Comprehension
Coached Conversational Preference Elicitation
TABFACT: A LARGE-SCALE DATASET FOR TABLEBASED FACT VERIFICATION
A Repository of Conversational Datasets
MultiFC: A Real-World Multi-Domain Dataset for Evidence-Based Fact Checking of Claims
A Survey of Available Corpora for Building Data-Driven Dialogue Systems
The JDDC Corpus: A Large-Scale Multi-Turn Chinese Dialogue Dataset forE-commerce Customer Service
JEC-QA: A Legal-Domain Question Answering Dataset
SAMSum Corpus: A Human-annotated Dialogue Dataset for Abstractive Summarization
Break It Down: A Question Understanding Benchmark
SciREX: A Challenge Dataset for Document-Level Information Extraction
FALCON 2.0: An Entity and Relation Linking Tool over Wikidata
REALM: Retrieval-Augmented Language Model Pre-Training
Encoder-Agnostic Adaptation for Conditional Language Generation
Conditional BERT Contextual Augmentation
Distilling Task-Specific Knowledge from BERT into Simple Neural Networks
ERNIE: Enhanced Language Representation with Informative Entities
Pre-Training with Whole Word Masking for Chinese BERT
XLNet: Generalized Autoregressive Pretraining for Language Understanding
Linguistic Knowledge and Transferability of Contextual Representations
Can Unconditional Language Models Recover Arbitrary Sentences?
TO TUNE OR NOT TO TUNE? HOW ABOUT THE BEST OF BOTH WORLDS?
Tree Transformer: Integrating Tree Structures into Self-Attention
CLEVR-Dialog: A Diagnostic Dataset for Multi-Round Reasoning in Visual Dialog
- Late Fusion
- Hierarchical Recurrent Encoder
- Memory Network
- Github is here.
Learning to Reason: End-to-End Module Networks for Visual Question Answering
Visual Coreference Resolution in Visual Dialog using Neural Module Networks
MUREL: Multimodal Relational Reasoning for Visual Question Answering
ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks
LXMERT: Learning Cross-Modality Encoder Representations from Transformers
ELECTRA: Pre-training Text Encoders as Discriminators Rather Than Generators
Masking Orchestration: Multi-task Pretraining for Multi-role Dialogue Representation Learning
DRr-Net: Dynamic Re-read Network for Sentence Semantic Matching
Neural Natural Language Inference Models Enhanced with External Knowledge
Knowledge Base Relation Detection via Multi-View Matching
Document Modeling with Graph Attention Networks for Multi-grained Machine Reading Comprehension
Retrospective Reader for Machine Reading Comprehension
Unsupervised Domain Adaptation on Reading Comprehension
DREAM: A Challenge Dataset and Models for Dialogue-Based Reading Comprehension
Review Conversational Reading Comprehension
FlowQA: Grasping Flow in History for Conversational Machine Comprehension
- Using RNN to grasp historical information in conversational question answering.
SDNet: Contextualized Attention-based Deep Network for Conversational Question Answering
- Generate bert embedding for reading comprehensing and question answering.
FusionNet: Fusing via Fully-Aware Attention with Application to Machine Comprehension
- Extend existing attention approaches from three perspectives.
Densely Connected Attention Propagation for Reading Comprehension
- Propose DECAPROP (Densely Connected Attention Propagation), a novel architecture for reading comprehension.
S-Net: From Answer Extraction to Answer Generation for Machine Reading Comprehension
QANet: Combining Local Convolution with Global Self-Attention for Reading Comprehension
U-Net: Machine Reading Comprehension with Unanswerable Questions
Reinforced Mnemonic Reader for Machine Reading Comprehension
Read + Verify: Machine Reading Comprehension with Unanswerable Questions
Multihop Attention Networks for Question Answer Matching
DROP: A Reading Comprehension Benchmark Requiring Discrete Reasoning Over Paragraphs
Multi-Matching Network for Multiple Choice Reading Comprehension
Option Comparison Network for Multiple-choice Reading Comprehension
Dual Co-Matching Network for Multi-choice Reading Comprehension
Hierarchical Attention Flow for Multiple-Choice Reading Comprehension
Bidirectional Attentive Memory Networks for Question Answering over Knowledge Bases
Coarse-to-Fine Question Answering for Long Documents
Convolutional Spatial Attention Model for Reading Comprehension with Multiple-Choice Questions
Cognitive Graph for Multi-Hop Reading Comprehension at Scale
Neural Machine Reading Comprehension: Methods and Trends
A Multi-Type Multi-Span Network for Reading Comprehension that Requires Discrete Reasoning
Unsupervised Question Answering by Cloze Translation
Latent Retrieval for Weakly Supervised Open Domain Question Answering
Sentence-Level Evidence Embedding for Claim Verification with Hierarchical Attention Networks
Cooperative Generator-Discriminator Networks for Abstractive Summarization with Narrative Flow
Hierarchical Transformers for Multi-Document Summarization
Self-Supervised Learning for Contextualized Extractive Summarization
Fine-tune BERT for Extractive Summarization
Attention Is (not) All You Need for Commonsense Reasoning
Multimodal Dialog System: Generating Responses via Adaptive Decoders
A Contextual Hierarchical Attention Network with Adaptive Objective for Dialogue State Tracking
TripPy: A Triple Copy Strategy for Value Independent Neural Dialog State Tracking
Schema-Guided Multi-Domain Dialogue State Tracking with Graph Attention Neural Networks
Zero-Shot Transfer Learning with Synthesized Data for Multi-Domain Dialogue State Tracking
SOLOIST: Few-shot Task-Oriented Dialog with A Single Pre-trained Auto-regressive Model
Variational Hierarchical Dialog Autoencoder for Dialogue State Tracking Data Augmentation
An Efficient Approach to Encoding Context for Spoken Language Understanding
The Second Conversational Intelligence Challenge (ConvAI2)
A Hierarchical Latent Variable Encoder-Decoder Model for Generating Dialogues
Memory-augmented Dialogue Management for Task-oriented Dialogue Systems
Interconnected Question Generation with Coreference Alignment and Conversation Flow Modeling
Transferable Multi-Domain State Generator for Task-Oriented Dialogue Systems
Dialog State Tracking: A Neural Reading Comprehension Approach
SUMBT: Slot-Utterance Matching for Universal and Scalable Belief Tracking
Dialog State Tracking: A Neural Reading Comprehension Approach
HyST: A Hybrid Approach for Flexible and Accurate Dialogue State Tracking
Data-Efficient Goal-Oriented Conversation with Dialogue Knowledge Transfer Networks
Neural Assistant: Joint Action Prediction, Response Generation, and Latent Knowledge Reasoning
Conversation Generation with Concept Flow
Robust Zero-Shot Cross-Domain Slot Filling with Example Values
An Empirical Study of Spatial Attention Mechanisms in Deep Networks
An Introductory Survey on Attention Mechanisms in NLP Problems
Modeling Localness for Self-Attention Networks
Dynamically Context-Sensitive Time-Decay Attention for Dialogue Modeling
Context-Aware Self-Attention Networks
- Use summarized vectors of context or hidden states of context to add extra contextual information into the process of calculating the similarity of between each word in KEY and VALUE.
Document Modeling with External Attention for Sentence Extraction
Convolutional Self-Attention Networks
Are Sixteen Heads Really Better than One?
Compressive Transformers for Long-Range Sequence Modelling
DTMT: A Novel Deep Transition Architecture for Neural Machine Translation
- Tap the potential strength of deep transition between consecutive hidden states and propose a novel deep transition RNN-based architecture for NMT
- Propose a simple yet more effective linear transformation enhanced GRU for our deep transition RNMT, which provides a linear transformation path for deep transition of consecutive hidden states.
Leveraging Pre-trained Checkpoints for Sequence Generation Tasks
Unsupervised Pre-training for Natural Language Generation: A Literature Review
FlowSeq: Non-Autoregressive Conditional Sequence Generation with Generative Flow
Interpretable machine learning: definitions, methods, and applications
Frustratingly Poor Performance of Reading Comprehension Models on Non-adversarial Examples
Benchmarking Zero-shot Text Classification: Datasets, Evaluation and Entailment Approach
Path-Based Contextualization of Knowledge Graphs for Textual Entailment
Multi-Task Deep Neural Networks for Natural Language Understanding
- Better performance than BERT on natural language understanding tasks.
K-ADAPTER: Infusing Knowledge into Pre-Trained Models with Adapters
Aligning the Pretraining and Finetuning Objectives of Language Models
MacNet: Transferring Knowledge from Machine Comprehension to Sequence-to-Sequence Models
An Embarrassingly Simple Approach for Transfer Learning from Pretrained Language Models
MULTIQA: An Empirical Investigation of Generalization and Transfer in Reading Comprehension
Parameter-Efficient Transfer Learning for NLP
Pretraining Methods for Dialog Context Representation Learning
How to Get Past Sesame Street: Sentence-Level Pretraining Beyond Language Modeling
Learning Structured Representation for Text Classification via Reinforcement Learning
Episodic Memory Reader: Learning What to Remember for Question Answering from Streaming Data
GCC: Graph Contrastive Coding for Graph Neural Network Pre-Training
Simplifying Graph Convolutional Networks
Embedding Logical Queries on Knowledge Graphs
Graph-Bert: Only Attention is Needed for Learning Graph Representations
Language Model Pre-training for Hierarchical Document Representations
Improve Diverse Text Generation by Self Labeling Conditional Variational Auto Encoder
Neural Self Talk: Image Understanding via Continuous Questioning and Answering
Dual Supervised Learning for Natural Language Understanding and Generation
Structured Minimally Supervised Learning for Neural Relation Extraction
A Variational Approach to Weakly Supervised Document-Level Multi-Aspect Sentiment Classification
Effectiveness of Self Normalizing Neural Networks for Text Classification
Self-Supervised Learning for Contextualized Extractive Summarization
Self-Supervised Dialogue Learning
ALBERT: A LITE BERT FOR SELF-SUPERVISED LEARNING OF LANGUAGE REPRESENTATIONS
Multi-Task Self-Supervised Learning for Disfluency Detection
Pretraining with Contrastive Sentence Objectives Improves DiscoursePerformance of Language Models
Tri-Training: Exploiting Unlabeled Data Using Three Classifiers
Tri-net for Semi-Supervised Deep Learning
Semi-Supervised Learning with Ladder Networks
Unsupervised Data Augmentation for Consistency Training
Variational Pretraining for Semi-supervised Text Classification
Adversarial Training Methods for Semi-Supervised Text Classification
Adversarial Examples for Natural Language Classification Problems
DATA AUGMENTATION GENERATIVE ADVERSARIAL NETWORKS
DeepFakes and Beyond: A Survey of Face Manipulation and Fake Detection
On the Impact of the Activation Function on Deep Neural Networks Training
Unsupervised Context Retrieval for Long-tail Entities
Self-Knowledge Distillation in Natural Language Processing
Multi-Task Self-Supervised Learning for Disfluency Detection
Explore, Propose, and Assemble: An Interpretable Model for Multi-Hop Reading Comprehension
Towards Explainable NLP: A Generative Explanation Framework for Text Classification
Inter-sentence Relation Extraction with Document-level Graph Convolutional Neural Network
Retrieve, Read, Rerank: Towards End-to-End Multi-Document Reading Comprehension
Compositional Questions Do Not Necessitate Multi-hop Reasoning
Multi-hop Reading Comprehension through Question Decomposition and Rescoring
Selfie: Self-supervised Pretraining for Image Embedding
BERT and PALs: Projected Attention Layers for Efficient Adaptation in Multi-Task Learning
Attention, please! A Critical Review of Neural Attention Models in Natural Language Processing
Gating Mechanisms for Combining Character and Word-level Word Representations: An Empirical Study
Understanding the Behaviors of BERT in Ranking
Relational Graph Attention Networks
Dry, Focus, and Transcribe: End-to-End Integration of Dereverberation, Beamforming, and ASR
Model Compression with Multi-Task Knowledge Distillation for Web-scale Question Answering System
Dynamic Past and Future for Neural Machine Translation
Probing Prior Knowledge Needed in Challenging Chinese Machine Reading Comprehension
I Know What You Want: Semantic Learning for Text Comprehension
Gradient-based Inference for Networks with Output Constraints
Unifying Question Answering and Text Classification via Span Extraction
Modality Attention for End-to-End Audio-visual Speech Recognition
The Use of Unlabeled Data versus Labeled Data for Stopping Active Learning for Text Classification
Efficient and Robust Question Answering from Minimal Context over Documents
Debugging RL, Without the Agonizing Pain
ML and NLP Research Highlights of 2020
Recent Advances in Language Model Fine-tuning
技术分享丨ALBERT在CommonsenseQA方向的应用
🦄🤝🦄 Encoder-decoders in Transformers: a hybrid pre-trained architecture for seq2seq
Comparing Pre-trained Language Models with Semantic Parsing
To Tune or Not to Tune? Adapting Pretrained Representations to Diverse Tasks
Attention mechanism paper from another repo
Visualizing memorization in RNNs
INTERSPEECH 2017系列 | 语音识别之后处理技术
Yejin Choi - Language and X ∈ {vision, knowledge, world, mind, society...}
Better Heatmaps and Correlation Matrix Plots in Python
ICLR 2019: Overcoming limited data Summaries of papers that address learning from few examples