SQuAD: 100,000+ Questions for Machine Comprehension of Text

Abstract

We present the Stanford Question Answering Dataset (SQuAD), a new reading comprehension dataset consisting of 100,000+ questions posed by crowdworkers on a set of Wikipedia articles, where the answer to each question is a segment of text from the corresponding reading passage. We analyze the dataset to understand the types of reasoning required to answer the questions, leaning heavily on dependency and constituency trees. We build a strong logistic regression model, which achieves an F1 score of 51.0%, a significant improvement over a simple baseline (20%). However, human performance (86.8%) is much higher, indicating that the dataset presents a good challenge problem for future research. The dataset is freely available at https://stanford-qa.com

To appear in Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing (EMNLP)

References in corpus (2)

• Machine Comprehension Using Match-LSTM and Answer Pointer
• A Thorough Examination of the CNN/Daily Mail Reading Comprehension Task

Cited by in corpus (448)

• BioBERT: a pre-trained biomedical language representation model for biomedical text mining
• XLNet: Generalized Autoregressive Pretraining for Language Understanding
• Recent Trends in Deep Learning Based Natural Language Processing
• Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism
• CTRL: A Conditional Transformer Language Model for Controllable Generation
• ERNIE: Enhanced Representation through Knowledge Integration
• AraBERT: Transformer-based Model for Arabic Language Understanding
• Wizard of Wikipedia: Knowledge-Powered Conversational agents
• Multitask Prompted Training Enables Zero-Shot Task Generalization
• Dynamic Coattention Networks For Question Answering
• CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generation
• Machine Comprehension Using Match-LSTM and Answer Pointer
• QANet: Combining Local Convolution with Global Self-Attention for Reading Comprehension
• Deep Learning Based Text Classification: A Comprehensive Review
• SearchQA: A New Q&A Dataset Augmented with Context from a Search Engine
• Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity
• BERT Post-Training for Review Reading Comprehension and Aspect-based Sentiment Analysis
• Passage Re-ranking with BERT
• The Natural Language Decathlon: Multitask Learning as Question Answering
• A Simple Method for Commonsense Reasoning
• P-Tuning v2: Prompt Tuning Can Be Comparable to Fine-tuning Universally Across Scales and Tasks
• Adversarial Examples for Evaluating Reading Comprehension Systems
• Adaptation of Deep Bidirectional Multilingual Transformers for Russian Language
• Pathologies of Neural Models Make Interpretations Difficult
• MOPO: Model-based Offline Policy Optimization
• RoFormer: Enhanced Transformer with Rotary Position Embedding
• Adversarial Examples: Attacks and Defenses for Deep Learning
• You Only Look at One Sequence: Rethinking Transformer in Vision through Object Detection
• Personalizing Dialogue Agents: I have a dog, do you have pets too?
• Beyond Word Importance: Contextual Decomposition to Extract Interactions from LSTMs
• The NLP Cookbook: Modern Recipes for Transformer based Deep Learning Architectures
• A Simple Language Model for Task-Oriented Dialogue
• Evidence Aggregation for Answer Re-Ranking in Open-Domain Question Answering
• Transforming Question Answering Datasets Into Natural Language Inference Datasets
• Multilingual is not enough: BERT for Finnish
• Learning Intrinsic Sparse Structures within Long Short-Term Memory
• Semantic Models for the First-stage Retrieval: A Comprehensive Review
• Vision-and-Dialog Navigation
• Unicoder-VL: A Universal Encoder for Vision and Language by Cross-modal Pre-training
• Supervised and Unsupervised Neural Approaches to Text Readability
• HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering
• Multi-Perspective Context Matching for Machine Comprehension
• Neural Network Models for Paraphrase Identification, Semantic Textual Similarity, Natural Language Inference, and Question Answering
• LAMOL: LAnguage MOdeling for Lifelong Language Learning
• RACE: Large-scale ReAding Comprehension Dataset From Examinations
• Pretrained Transformers for Text Ranking: BERT and Beyond
• Entailment as Few-Shot Learner
• Learning to Generate Questions by Learning What not to Generate
• A Survey on Text Classification: From Shallow to Deep Learning
• StructBERT: Incorporating Language Structures into Pre-training for Deep Language Understanding
• MobileBERT: a Compact Task-Agnostic BERT for Resource-Limited Devices
• Beyond 512 Tokens: Siamese Multi-depth Transformer-based Hierarchical Encoder for Long-Form Document Matching
• Pre-training via Paraphrasing
• Reading Wikipedia to Answer Open-Domain Questions
• R${}^3$: Reinforced Reader-Ranker for Open-Domain Question Answering
• DCN+: Mixed Objective and Deep Residual Coattention for Question Answering
• Arabic Offensive Language on Twitter: Analysis and Experiments
• Neural Models for Information Retrieval
• A Joint Model for Question Answering and Question Generation
• Query-Reduction Networks for Question Answering
• NewsQA: A Machine Comprehension Dataset
• Generating Wikipedia by Summarizing Long Sequences
• ERNIE 2.0: A Continual Pre-training Framework for Language Understanding
• Improving Post Training Neural Quantization: Layer-wise Calibration and Integer Programming
• Structured Pruning of a BERT-based Question Answering Model
• ProtTrans: Towards Cracking the Language of Life's Code Through Self-Supervised Deep Learning and High Performance Computing
• Contrastive Out-of-Distribution Detection for Pretrained Transformers
• MEMEN: Multi-layer Embedding with Memory Networks for Machine Comprehension
• Adversarial NLI: A New Benchmark for Natural Language Understanding
• KERMIT: Generative Insertion-Based Modeling for Sequences
• InfoBERT: Improving Robustness of Language Models from An Information Theoretic Perspective
• XLDA: Cross-Lingual Data Augmentation for Natural Language Inference and Question Answering
• Multilingual Extractive Reading Comprehension by Runtime Machine Translation
• A Survey of Deep Learning for Scientific Discovery
• Embracing data abundance: BookTest Dataset for Reading Comprehension
• InterBERT: Vision-and-Language Interaction for Multi-modal Pretraining
• Evaluation of Neural Architectures Trained with Square Loss vs Cross-Entropy in Classification Tasks
• Q-BERT: Hessian Based Ultra Low Precision Quantization of BERT
• Learning from others' mistakes: Avoiding dataset biases without modeling them
• A Unified MRC Framework for Named Entity Recognition
• QuAC : Question Answering in Context
• DuReader: a Chinese Machine Reading Comprehension Dataset from Real-world Applications
• TVQA: Localized, Compositional Video Question Answering
• S-Net: From Answer Extraction to Answer Generation for Machine Reading Comprehension
• BAG: Bi-directional Attention Entity Graph Convolutional Network for Multi-hop Reasoning Question Answering
• Meta-evaluation of Conversational Search Evaluation Metrics
• BinaryBERT: Pushing the Limit of BERT Quantization
• Reweighted Proximal Pruning for Large-Scale Language Representation
• EvalAI: Towards Better Evaluation Systems for AI Agents
• Words or Characters? Fine-grained Gating for Reading Comprehension
• Only Train Once: A One-Shot Neural Network Training And Pruning Framework
• Adversarially Regularising Neural NLI Models to Integrate Logical Background Knowledge
• End-to-End Answer Chunk Extraction and Ranking for Reading Comprehension
• Innovative Bert-based Reranking Language Models for Speech Recognition
• Refiner: Refining Self-attention for Vision Transformers
• CoCo: Controllable Counterfactuals for Evaluating Dialogue State Trackers
• Reinforced Mnemonic Reader for Machine Reading Comprehension
• PAIR: Leveraging Passage-Centric Similarity Relation for Improving Dense Passage Retrieval
• Exploring Question Understanding and Adaptation in Neural-Network-Based Question Answering
• U-Net: Machine Reading Comprehension with Unanswerable Questions
• Pre-trained Language Models in Biomedical Domain: A Systematic Survey
• Neural Question Generation from Text: A Preliminary Study
• CLUECorpus2020: A Large-scale Chinese Corpus for Pre-training Language Model
• Stochastic Answer Networks for Machine Reading Comprehension
• Are Pre-trained Convolutions Better than Pre-trained Transformers?
• Linguistic Knowledge as Memory for Recurrent Neural Networks
• ES-ImageNet: A Million Event-Stream Classification Dataset for Spiking Neural Networks
• Dice Loss for Data-imbalanced NLP Tasks
• CO-Search: COVID-19 Information Retrieval with Semantic Search, Question Answering, and Abstractive Summarization
• A Survey on Explainability in Machine Reading Comprehension
• TyDi QA: A Benchmark for Information-Seeking Question Answering in Typologically Diverse Languages
• Convolutional Spatial Attention Model for Reading Comprehension with Multiple-Choice Questions
• A Comparative Study of Word Embeddings for Reading Comprehension
• Combining Fact Extraction and Verification with Neural Semantic Matching Networks
• Machine Reading Comprehension: a Literature Review
• Semi-Supervised QA with Generative Domain-Adaptive Nets
• ETC: Encoding Long and Structured Inputs in Transformers
• Spoken SQuAD: A Study of Mitigating the Impact of Speech Recognition Errors on Listening Comprehension
• Efficient and Robust Question Answering from Minimal Context over Documents
• Explicit Contextual Semantics for Text Comprehension
• AraELECTRA: Pre-Training Text Discriminators for Arabic Language Understanding
• TRANS-BLSTM: Transformer with Bidirectional LSTM for Language Understanding
• Unifying Question Answering, Text Classification, and Regression via Span Extraction
• A Co-Matching Model for Multi-choice Reading Comprehension
• SG-Net: Syntax-Guided Machine Reading Comprehension
• QuestEval: Summarization Asks for Fact-based Evaluation
• Pollux: Co-adaptive Cluster Scheduling for Goodput-Optimized Deep Learning
• Embedding-based Zero-shot Retrieval through Query Generation
• Word2Bits - Quantized Word Vectors
• Learning to Encode Position for Transformer with Continuous Dynamical Model
• GraphFlow: Exploiting Conversation Flow with Graph Neural Networks for Conversational Machine Comprehension
• MemexQA: Visual Memex Question Answering
• Taking a Stance on Fake News: Towards Automatic Disinformation Assessment via Deep Bidirectional Transformer Language Models for Stance Detection
• KG^2: Learning to Reason Science Exam Questions with Contextual Knowledge Graph Embeddings
• Factual Probing Is [MASK]: Learning vs. Learning to Recall
• Subword-augmented Embedding for Cloze Reading Comprehension
• Adversarial attacks against Fact Extraction and VERification
• On the Learnability of Concepts: With Applications to Comparing Word Embedding Algorithms
• Themis: Fair and Efficient GPU Cluster Scheduling
• A Survey on Neural Machine Reading Comprehension
• Multi-class Hierarchical Question Classification for Multiple Choice Science Exams
• A large-scale evaluation framework for EEG deep learning architectures
• Neural Passage Retrieval with Improved Negative Contrast
• Dynamic Fusion Networks for Machine Reading Comprehension
• GLU Variants Improve Transformer
• GO FIGURE: A Meta Evaluation of Factuality in Summarization
• PALM: Pre-training an Autoencoding&Autoregressive Language Model for Context-conditioned Generation
• Read + Verify: Machine Reading Comprehension with Unanswerable Questions
• KELM: Knowledge Enhanced Pre-Trained Language Representations with Message Passing on Hierarchical Relational Graphs
• HOList: An Environment for Machine Learning of Higher-Order Theorem Proving
• Probing and Fine-tuning Reading Comprehension Models for Few-shot Event Extraction
• Grounded Recurrent Neural Networks
• Multimodal Attribute Extraction
• CraftAssist: A Framework for Dialogue-enabled Interactive Agents
• Phase Conductor on Multi-layered Attentions for Machine Comprehension
• Structural Embedding of Syntactic Trees for Machine Comprehension
• Transformer-Based Models for Question Answering on COVID19
• Model-Based Visual Planning with Self-Supervised Functional Distances
• Question Answering from Unstructured Text by Retrieval and Comprehension
• Difficulty Controllable Generation of Reading Comprehension Questions
• Simple and Effective Curriculum Pointer-Generator Networks for Reading Comprehension over Long Narratives
• I-BERT: Integer-only BERT Quantization
• To Tune or Not To Tune? How About the Best of Both Worlds?
• Using AntiPatterns to avoid MLOps Mistakes
• Adversarial TableQA: Attention Supervision for Question Answering on Tables
• Weaver: Deep Co-Encoding of Questions and Documents for Machine Reading
• Beyond Leaderboards: A survey of methods for revealing weaknesses in Natural Language Inference data and models
• Review Conversational Reading Comprehension
• BERT Based Multilingual Machine Comprehension in English and Hindi
• HULK: An Energy Efficiency Benchmark Platform for Responsible Natural Language Processing
• Smarnet: Teaching Machines to Read and Comprehend Like Human
• Finding Answers from the Word of God: Domain Adaptation for Neural Networks in Biblical Question Answering
• Wide-minima Density Hypothesis and the Explore-Exploit Learning Rate Schedule
• What Happened? Leveraging VerbNet to Predict the Effects of Actions in Procedural Text
• Accelerating Sparse Deep Neural Networks
• Ruminating Reader: Reasoning with Gated Multi-Hop Attention
• Automatic Judgment Prediction via Legal Reading Comprehension
• Low-Rank Bottleneck in Multi-head Attention Models
• Tracking State Changes in Procedural Text: A Challenge Dataset and Models for Process Paragraph Comprehension
• BERT-based Ensembles for Modeling Disclosure and Support in Conversational Social Media Text
• Multi-Stage Pre-training for Low-Resource Domain Adaptation
• Attention-Guided Answer Distillation for Machine Reading Comprehension
• KDLSQ-BERT: A Quantized Bert Combining Knowledge Distillation with Learned Step Size Quantization
• Accelerating Sparse DNN Models without Hardware-Support via Tile-Wise Sparsity
• NetReduce: RDMA-Compatible In-Network Reduction for Distributed DNN Training Acceleration
• A Deep Look into Neural Ranking Models for Information Retrieval
• MinTL: Minimalist Transfer Learning for Task-Oriented Dialogue Systems
• Ranking Paragraphs for Improving Answer Recall in Open-Domain Question Answering
• Natural Question Generation with Reinforcement Learning Based Graph-to-Sequence Model
• Multilingual Question Answering from Formatted Text applied to Conversational Agents
• Rethinking Automatic Evaluation in Sentence Simplification
• Yuanfudao at SemEval-2018 Task 11: Three-way Attention and Relational Knowledge for Commonsense Machine Comprehension
• Unanswerable Questions about Images and Texts
• Information Leakage in Embedding Models
• ExpMRC: Explainability Evaluation for Machine Reading Comprehension
• Automatic Article Commenting: the Task and Dataset
• Cross-Lingual Natural Language Generation via Pre-Training
• Multi-Passage Machine Reading Comprehension with Cross-Passage Answer Verification
• MCQA: Multimodal Co-attention Based Network for Question Answering
• Indic-Transformers: An Analysis of Transformer Language Models for Indian Languages
• Attention-guided Generative Models for Extractive Question Answering
• Open Domain Question Answering Using Early Fusion of Knowledge Bases and Text
• Automating Reading Comprehension by Generating Question and Answer Pairs
• Interpretable Multi-Step Reasoning with Knowledge Extraction on Complex Healthcare Question Answering
• Supervised and Unsupervised Transfer Learning for Question Answering
• Artificial Intelligence Strategies for National Security and Safety Standards
• Distributed Representation for Traditional Chinese Medicine Herb via Deep Learning Models
• Interactive Language Learning by Question Answering
• On Learning Universal Representations Across Languages
• GOBO: Quantizing Attention-Based NLP Models for Low Latency and Energy Efficient Inference
• On the comparability of Pre-trained Language Models
• Joint Training of Candidate Extraction and Answer Selection for Reading Comprehension
• SafeLife 1.0: Exploring Side Effects in Complex Environments
• FlowDelta: Modeling Flow Information Gain in Reasoning for Conversational Machine Comprehension
• Can Neural Networks Understand Logical Entailment?
• RecipeQA: A Challenge Dataset for Multimodal Comprehension of Cooking Recipes
• Pitfalls of Explainable ML: An Industry Perspective
• Explicit Utilization of General Knowledge in Machine Reading Comprehension
• Length-Adaptive Transformer: Train Once with Length Drop, Use Anytime with Search
• Photon: A Robust Cross-Domain Text-to-SQL System
• A Survey on Machine Reading Comprehension: Tasks, Evaluation Metrics and Benchmark Datasets
• Procedural Reading Comprehension with Attribute-Aware Context Flow
• Bidirectional Attention for SQL Generation
• Natural Language Generation with Neural Variational Models
• Multi-Task Learning with Multi-View Attention for Answer Selection and Knowledge Base Question Answering
• DocVQA: A Dataset for VQA on Document Images
• ASR-GLUE: A New Multi-task Benchmark for ASR-Robust Natural Language Understanding
• Knowledge-driven Data Construction for Zero-shot Evaluation in Commonsense Question Answering
• The SPPD System for Schema Guided Dialogue State Tracking Challenge
• DeFormer: Decomposing Pre-trained Transformers for Faster Question Answering
• Improving Neural Question Generation using Answer Separation
• Sequence-to-Nuggets: Nested Entity Mention Detection via Anchor-Region Networks
• Open Korean Corpora: A Practical Report
• Gradient-Based Adversarial Training on Transformer Networks for Detecting Check-Worthy Factual Claims
• Complicating the Social Networks for Better Storytelling: An Empirical Study of Chinese Historical Text and Novel
• Comparative Study of Machine Learning Models and BERT on SQuAD
• Zero-shot Fact Verification by Claim Generation
• Learning to update Auto-associative Memory in Recurrent Neural Networks for Improving Sequence Memorization
• Attention on Abstract Visual Reasoning
• Two-Stage Synthesis Networks for Transfer Learning in Machine Comprehension
• Fine-Tuning by Curriculum Learning for Non-Autoregressive Neural Machine Translation
• ALP-KD: Attention-Based Layer Projection for Knowledge Distillation
• The Benchmark Lottery
• Analyzing Compositionality-Sensitivity of NLI Models
• RPT: Relational Pre-trained Transformer Is Almost All You Need towards Democratizing Data Preparation
• Hierarchical Question Answering for Long Documents
• Meaningful Answer Generation of E-Commerce Question-Answering
• Multi-node Bert-pretraining: Cost-efficient Approach
• Pre-training Text Representations as Meta Learning
• Syntactic Scaffolds for Semantic Structures
• RefNet: A Reference-aware Network for Background Based Conversation
• Recurrent Neural Network-Based Semantic Variational Autoencoder for Sequence-to-Sequence Learning
• Improving Machine Reading Comprehension with Single-choice Decision and Transfer Learning
• QAInfomax: Learning Robust Question Answering System by Mutual Information Maximization
• Cross-Lingual Transfer Learning for Question Answering
• Task Selection Policies for Multitask Learning
• Query-based Attention CNN for Text Similarity Map
• Human Evaluation of Spoken vs. Visual Explanations for Open-Domain QA
• EmbRace: Accelerating Sparse Communication for Distributed Training of NLP Neural Networks
• A Large-Scale Rich Context Query and Recommendation Dataset in Online Knowledge-Sharing
• Reinforced Extractive Summarization with Question-Focused Rewards
• ReviewQA: a relational aspect-based opinion reading dataset
• AR-LSAT: Investigating Analytical Reasoning of Text
• BiQGEMM: Matrix Multiplication with Lookup Table For Binary-Coding-based Quantized DNNs
• Fused Acoustic and Text Encoding for Multimodal Bilingual Pretraining and Speech Translation
• Whatcha lookin' at? DeepLIFTing BERT's Attention in Question Answering
• Demystifying the MLPerf Benchmark Suite
• ColdGANs: Taming Language GANs with Cautious Sampling Strategies
• Question Generation by Transformers
• Enhancing Answer Boundary Detection for Multilingual Machine Reading Comprehension
• Making Neural Machine Reading Comprehension Faster
• An Attention Mechanism for Answer Selection Using a Combined Global and Local View
• HAS-QA: Hierarchical Answer Spans Model for Open-domain Question Answering
• Direction is what you need: Improving Word Embedding Compression in Large Language Models
• Pay Attention when Required
• Contrastive Distillation on Intermediate Representations for Language Model Compression
• LRC-BERT: Latent-representation Contrastive Knowledge Distillation for Natural Language Understanding
• FLEX: Unifying Evaluation for Few-Shot NLP
• Text Embeddings for Retrieval From a Large Knowledge Base
• HyperGrid: Efficient Multi-Task Transformers with Grid-wise Decomposable Hyper Projections
• Pre-trained Language Model for Biomedical Question Answering
• Hessian-Aware Pruning and Optimal Neural Implant
• LogiQA: A Challenge Dataset for Machine Reading Comprehension with Logical Reasoning
• Are you tough enough? Framework for Robustness Validation of Machine Comprehension Systems
• Identifying Well-formed Natural Language Questions
• How To Evaluate Your Dialogue System: Probe Tasks as an Alternative for Token-level Evaluation Metrics
• Towards Automated Anamnesis Summarization: BERT-based Models for Symptom Extraction
• Hindi Question Generation Using Dependency Structures
• Contextual Aware Joint Probability Model Towards Question Answering System
• Transformer on a Diet
• Robust Reading Comprehension with Linguistic Constraints via Posterior Regularization
• QADiscourse -- Discourse Relations as QA Pairs: Representation, Crowdsourcing and Baselines
• Reading Comprehension as Natural Language Inference: A Semantic Analysis
• SPARTA: Efficient Open-Domain Question Answering via Sparse Transformer Matching Retrieval
• ReCO: A Large Scale Chinese Reading Comprehension Dataset on Opinion
• Position Masking for Language Models
• TORQUE: A Reading Comprehension Dataset of Temporal Ordering Questions
• XDA: Accurate, Robust Disassembly with Transfer Learning
• Natural Language Inference in Context -- Investigating Contextual Reasoning over Long Texts
• Extracting Semantics from Maintenance Records
• SGD-QA: Fast Schema-Guided Dialogue State Tracking for Unseen Services
• Interpretation of Natural Language Rules in Conversational Machine Reading
• EfficientQA : a RoBERTa Based Phrase-Indexed Question-Answering System
• A Benchmark for Structured Procedural Knowledge Extraction from Cooking Videos
• A Rigorous Study on Named Entity Recognition: Can Fine-tuning Pretrained Model Lead to the Promised Land?
• Pre-training for Abstractive Document Summarization by Reinstating Source Text
• TutorialVQA: Question Answering Dataset for Tutorial Videos
• Augmenting Neural Networks with First-order Logic
• Closed-Book Training to Improve Summarization Encoder Memory
• Towards a Better Metric for Evaluating Question Generation Systems
• Daydream: Accurately Estimating the Efficacy of Optimizations for DNN Training
• NSURL-2019 Shared Task 8: Semantic Question Similarity in Arabic
• Look at the First Sentence: Position Bias in Question Answering
• AmazonQA: A Review-Based Question Answering Task
• Scientific Claim Verification with VERT5ERINI
• Performance Analysis and Characterization of Training Deep Learning Models on Mobile Devices
• Identifying Introductions in Podcast Episodes from Automatically Generated Transcripts
• Conversational Question Answering: A Survey
• PreCo: A Large-scale Dataset in Preschool Vocabulary for Coreference Resolution
• VidLanKD: Improving Language Understanding via Video-Distilled Knowledge Transfer
• Knowledge Based Machine Reading Comprehension
• Does it care what you asked? Understanding Importance of Verbs in Deep Learning QA System
• Span Detection for Aspect-Based Sentiment Analysis in Vietnamese
• BEAMetrics: A Benchmark for Language Generation Evaluation Evaluation
• Improving Commonsense Question Answering by Graph-based Iterative Retrieval over Multiple Knowledge Sources
• Adaptations of ROUGE and BLEU to Better Evaluate Machine Reading Comprehension Task
• Event Detection as Question Answering with Entity Information
• Demystifying BERT: Implications for Accelerator Design
• Semantic Graphs for Generating Deep Questions
• Phrase-Indexed Question Answering: A New Challenge for Scalable Document Comprehension
• Talk to Papers: Bringing Neural Question Answering to Academic Search
• Revisiting the Open-Domain Question Answering Pipeline
• Efficient Meta Lifelong-Learning with Limited Memory
• Large-scale Cloze Test Dataset Created by Teachers
• Multi-Mention Learning for Reading Comprehension with Neural Cascades
• Learning from Data-Rich Problems: A Case Study on Genetic Variant Calling
• Attentive Convolution: Equipping CNNs with RNN-style Attention Mechanisms
• Improving Question Generation with Sentence-level Semantic Matching and Answer Position Inferring
• Product-Aware Answer Generation in E-Commerce Question-Answering
• Improving Human Text Comprehension through Semi-Markov CRF-based Neural Section Title Generation
• NukeBERT: A Pre-trained language model for Low Resource Nuclear Domain
• Bilingual Language Modeling, A transfer learning technique for Roman Urdu
• Linguistically-Enriched and Context-Aware Zero-shot Slot Filling
• An Experimental Evaluation of Transformer-based Language Models in the Biomedical Domain
• VisBERT: Hidden-State Visualizations for Transformers
• MRNN: A Multi-Resolution Neural Network with Duplex Attention for Document Retrieval in the Context of Question Answering
• Unsupervised Domain Adaptation on Reading Comprehension
• The Training of Neuromodels for Machine Comprehension of Text. Brain2Text Algorithm
• Follow Your Path: a Progressive Method for Knowledge Distillation
• GenNet : Reading Comprehension with Multiple Choice Questions using Generation and Selection model
• ManyModalQA: Modality Disambiguation and QA over Diverse Inputs
• Shatter: An Efficient Transformer Encoder with Single-Headed Self-Attention and Relative Sequence Partitioning
• A Multi-Resolution Word Embedding for Document Retrieval from Large Unstructured Knowledge Bases
• MLPerf Mobile Inference Benchmark
• Commonsense knowledge adversarial dataset that challenges ELECTRA
• Answering questions by learning to rank -- Learning to rank by answering questions
• Textbook Question Answering with Multi-modal Context Graph Understanding and Self-supervised Open-set Comprehension
• Conditioning LSTM Decoder and Bi-directional Attention Based Question Answering System
• MRCBert: A Machine Reading ComprehensionApproach for Unsupervised Summarization
• Using Holographically Compressed Embeddings in Question Answering
• Implicit Argument Prediction as Reading Comprehension
• Achieving Human Parity on Visual Question Answering
• Zero-Shot Open-Book Question Answering
• A Multilingual Modeling Method for Span-Extraction Reading Comprehension
• Compositional Language Understanding with Text-based Relational Reasoning
• An Information Retrieval Approach to Building Datasets for Hate Speech Detection
• Ember: No-Code Context Enrichment via Similarity-Based Keyless Joins
• Picking Apart Story Salads
• MergeDistill: Merging Pre-trained Language Models using Distillation
• Leveraging Clinical Context for User-Centered Explainability: A Diabetes Use Case
• Automatic Claim Review for Climate Science via Explanation Generation
• Semantic-Based Self-Critical Training For Question Generation
• Effectiveness of Deep Networks in NLP using BiDAF as an example architecture
• Iterative Multi-document Neural Attention for Multiple Answer Prediction
• ElimiNet: A Model for Eliminating Options for Reading Comprehension with Multiple Choice Questions
• Auto-Classification of Retinal Diseases in the Limit of Sparse Data Using a Two-Streams Machine Learning Model
• Resource-Size matters: Improving Neural Named Entity Recognition with Optimized Large Corpora
• Situation and Behavior Understanding by Trope Detection on Films
• Answer Generation through Unified Memories over Multiple Passages
• WaLDORf: Wasteless Language-model Distillation On Reading-comprehension
• A Study of the Tasks and Models in Machine Reading Comprehension
• Pay More Attention - Neural Architectures for Question-Answering
• Deep Contextual Embeddings for Address Classification in E-commerce
• Abductive Reasoning as Self-Supervision for Common Sense Question Answering
• SemEval-2020 Task 5: Counterfactual Recognition
• Open-Domain Question Answering with Pre-Constructed Question Spaces
• Geometry matters: Exploring language examples at the decision boundary
• Learning Representations and Agents for Information Retrieval
• Hierarchical Multitask Learning Approach for BERT
• BiST: Bi-directional Spatio-Temporal Reasoning for Video-Grounded Dialogues
• Empirical Evaluation of Multi-task Learning in Deep Neural Networks for Natural Language Processing
• Interactive Machine Comprehension with Information Seeking Agents
• Bayesian Attention Modules
• Query-Based Named Entity Recognition
• Asking Complex Questions with Multi-hop Answer-focused Reasoning
• Inquisitive Question Generation for High Level Text Comprehension
• MIX : a Multi-task Learning Approach to Solve Open-Domain Question Answering
• A More Efficient Chinese Named Entity Recognition base on BERT and Syntactic Analysis
• blessing in disguise: Designing Robust Turing Test by Employing Algorithm Unrobustness
• Teaching Syntax by Adversarial Distraction
• ComQA:Compositional Question Answering via Hierarchical Graph Neural Networks
• Understanding in Artificial Intelligence
• Mitigating the Position Bias of Transformer Models in Passage Re-Ranking
• Explaining the Deep Natural Language Processing by Mining Textual Interpretable Features
• Using the Hammer Only on Nails: A Hybrid Method for Evidence Retrieval for Question Answering
• ISS-MULT: Intelligent Sample Selection for Multi-Task Learning in Question Answering
• CALM: Continuous Adaptive Learning for Language Modeling
• Word Embedding-based Text Processing for Comprehensive Summarization and Distinct Information Extraction
• Leveraging Personal Navigation Assistant Systems Using Automated Social Media Traffic Reporting
• Data-Informed Global Sparseness in Attention Mechanisms for Deep Neural Networks
• When to Fold'em: How to answer Unanswerable questions
• The RLLChatbot: a solution to the ConvAI challenge
• Can questions summarize a corpus? Using question generation for characterizing COVID-19 research
• A Coarse to Fine Question Answering System based on Reinforcement Learning
• Improve Query Focused Abstractive Summarization by Incorporating Answer Relevance
• Dual Attention Network for Product Compatibility and Function Satisfiability Analysis
• Itsy Bitsy SpiderNet: Fully Connected Residual Network for Fraud Detection
• CAESAR: Context Awareness Enabled Summary-Attentive Reader
• Tag and Correct: Question aware Open Information Extraction with Two-stage Decoding
• End-to-End Learning for Answering Structured Queries Directly over Text
• ParaQG: A System for Generating Questions and Answers from Paragraphs
• LRTuner: A Learning Rate Tuner for Deep Neural Networks
• Fine-tuning Multi-hop Question Answering with Hierarchical Graph Network
• Interpreting Language Models Through Knowledge Graph Extraction
• XAlgo: a Design Probe of Explaining Algorithms' Internal States via Question-Answering
• A Base Camp for Scaling AI
• How to Pre-Train Your Model? Comparison of Different Pre-Training Models for Biomedical Question Answering
• Weighted Global Normalization for Multiple Choice Reading Comprehension over Long Documents
• POSSCORE: A Simple Yet Effective Evaluation of Conversational Search with Part of Speech Labelling
• A3Net: Adversarial-and-Attention Network for Machine Reading Comprehension
• Exploring a Unified Sequence-To-Sequence Transformer for Medical Product Safety Monitoring in Social Media
• Towards Universal Dense Retrieval for Open-domain Question Answering
• LV-BERT: Exploiting Layer Variety for BERT
• The Lower The Simpler: Simplifying Hierarchical Recurrent Models
• Unsupervised Multiple Choices Question Answering: Start Learning from Basic Knowledge
• A cost-benefit analysis of cross-lingual transfer methods
• Ensemble ALBERT on SQuAD 2.0
• Text Counterfactuals via Latent Optimization and Shapley-Guided Search
• CHIME: Cross-passage Hierarchical Memory Network for Generative Review Question Answering
• Learning to Generate Questions with Adaptive Copying Neural Networks
• ODSQA: Open-domain Spoken Question Answering Dataset
• Large Product Key Memory for Pretrained Language Models
• Learn to Resolve Conversational Dependency: A Consistency Training Framework for Conversational Question Answering
• Multi-Perspective Fusion Network for Commonsense Reading Comprehension
• What Makes a Star Teacher? A Hierarchical BERT Model for Evaluating Teacher's Performance in Online Education
• Question-Aware Sentence Gating Networks for Question and Answering
• Bew: Towards Answering Business-Entity-Related Web Questions
• AGenT Zero: Zero-shot Automatic Multiple-Choice Question Generation for Skill Assessments