Teaching Machines to Read and Comprehend

Teaching machines to read natural language documents remains an elusive challenge. Machine reading systems can be tested on their ability to answer questions posed on the contents of documents that they have seen, but until now large scale training and test datasets have been missing for this type of evaluation. In this work we define a new methodology that resolves this bottleneck and provides large scale supervised reading comprehension data. This allows us to develop a class of attention based deep neural networks that learn to read real documents and answer complex questions with minimal prior knowledge of language structure.

• Publication year

  2015

• Venue

  Neural Information Processing Systems

• Publication date

  2015-06-10

• Fields of study

  Linguistics, Computer Science

• Identifiers
  arXiv 1506.03340
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Weakly Supervised Memory Networks

  2015cited by this paper
• DRAW: A Recurrent Neural Network For Image Generation

  2015cited by this paper
• End-To-End Memory Networks

  2015cited by this paper
• Sequence to Sequence Learning with Neural Networks

  2014cited by this paper
• Recurrent Models of Visual Attention

  2014cited by this paper
• Semantic Frame Identification with Distributed Word Representations

  2014cited by this paper
• Frame-Semantic Parsing

  2014cited by this paper
• Memory Networks

  2014cited by this paper
• Neural Machine Translation by Jointly Learning to Align and Translate

  2014cited by this paper
• A Convolutional Neural Network for Modelling Sentences

  2014cited by this paper
• MCTest: A Challenge Dataset for the Open-Domain Machine Comprehension of Text

  2013cited by this paper
• Supervised Sequence Labelling with Recurrent Neural Networks

  2012influential reference
• Natural Language Processing (Almost) from Scratch

  2011cited by this paper
• Machine Reading at the University of Washington

  2010cited by this paper
• Automatic Generation of Story Highlights

  2010cited by this paper
• Enhancing Single-Document Summarization by Combining RankNet and Third-Party Sources

  2007cited by this paper
• A Rule-based Question Answering System for Reading Comprehension Tests

  2000cited by this paper
• Long Short-Term Memory

  1997cited by this paper
• Understanding natural language

  1972cited by this paper
• “Cloze Procedure”: A New Tool for Measuring Readability

  1953cited by this paper

• Unlocking the potential of news: A systematic review of advantages and challenges for event detection and analysis

  2026cites this paper
• A Deep Learning Framework for Extracting and Summarizing Text from Images

  2026influential citation
• FlashEvaluator: Expanding Search Space with Parallel Evaluation

  2026cites this paper
• Unsupervised Text Style Transfer for Controllable Intensity

  2026cites this paper
• Enhancing news classification: domain-specific guided pretraining based on adaptive selective masking

  2026cites this paper
• Adaptive and Robust Cost-Aware Proof of Quality for Decentralized LLM Inference Networks

  2026cites this paper
• Leveraging LLMs for Smart Cities Qualitative Data Analysis

  2026cites this paper
• Efficient Extractive Summarization with MAMBA-Transformer Hybrids for Low-Resource Scenarios

  2026cites this paper
• Phase transitions in large language model compression

  2026cites this paper
• ModeX: Evaluator-Free Best-of-N Selection for Open-Ended Generation

  2026cites this paper
• OSNIP: Breaking the Privacy-Utility-Efficiency Trilemma in LLM Inference via Obfuscated Semantic Null Space

  2026cites this paper
• Capability-Oriented Training Induced Alignment Risk

  2026cites this paper
• Speculative Decoding with a Speculative Vocabulary

  2026cites this paper
• DART-ing Through the Drift: Dynamic Tracing of Knowledge Neurons for Adaptive Inference-Time Pruning

  2026cites this paper
• Powerful Training-Free Membership Inference Against Autoregressive Language Models

  2026cites this paper
• WorldCup Sampling for Multi-bit LLM Watermarking

  2026cites this paper
• Differentially Private and Communication Efficient Large Language Model Split Inference via Stochastic Quantization and Soft Prompt

  2026cites this paper
• Effective document summarization: a hybrid clustering approach using transformer model

  2026cites this paper
• Variation is the Key: A Variation-Based Framework for LLM-Generated Text Detection

  2026influential citation
• Blind to the Human Touch: Overlap Bias in LLM-Based Summary Evaluation

  2026cites this paper
• Dependence-Aware Label Aggregation for LLM-as-a-Judge via Ising Models

  2026cites this paper
• Simplify-This: A Comparative Analysis of Prompt-Based and Fine-Tuned LLMs

  2026cites this paper
• MARS: Unleashing the Power of Speculative Decoding via Margin-Aware Verification

  2026cites this paper
• Mechanistic Analysis of Catastrophic Forgetting in Large Language Models During Continual Fine-tuning

  2026cites this paper
• AP-OOD: Attention Pooling for Out-of-Distribution Detection

  2026cites this paper
• FactSim: Fact-Checking for Opinion Summarization

  2026cites this paper
• Iterative Prompt Refinement for Dyslexia-Friendly Text Summarization Using GPT-4o

  2026cites this paper
• Task-Centric Acceleration of Small-Language Models

  2026cites this paper
• DIAL-SUMMER: A Structured Evaluation Framework of Hierarchical Errors in Dialogue Summaries

  2026cites this paper
• Ranking Augmented Generation: Leveraging Diversity for Better Text Generation

  2026cites this paper
• Combining retrieved with generated contexts via a listwise reranker for open-domain question answering

  2026cites this paper
• References Matter: Investigating the Impact of Reference Set Variation on Summarization Evaluation

  2025influential citation
• On-the-Fly Adaptive Distillation of Transformer to Dual-State Linear Attention

  2025cites this paper
• Chain-of-Thought Prompting Obscures Hallucination Cues in Large Language Models: An Empirical Evaluation

  2025cites this paper
• WeightLoRA: Keep Only Necessary Adapters

  2025cites this paper
• Cross-Attention Speculative Decoding

  2025cites this paper
• Automatic text summarization techniques: A categorization, evolution and future scope

  2025cites this paper
• Fine-Tuning LLaMA 3.2-1B for Long-Text Summarization: A Case Study on Book Summarization

  2025cites this paper
• APE: Selective Fine-tuning with Acceptance Criteria for Language Model Adaptation

  2025cites this paper
• The Case for Repeatable, Open, and Expert-Grounded Hallucination Benchmarks in Large Language Models

  2025cites this paper
• It's High Time: A Survey of Temporal Information Retrieval and Question Answering

  2025cites this paper
• Interpretable Traces, Unexpected Outcomes: Investigating the Disconnect in Trace-Based Knowledge Distillation

  2025cites this paper
• Scalable LLM Reasoning Acceleration with Low-rank Distillation

  2025cites this paper
• Hallucinate at the Last in Long Response Generation: A Case Study on Long Document Summarization

  2025cites this paper
• Document-Level Text Generation with Minimum Bayes Risk Decoding using Optimal Transport

  2025cites this paper
• APE: A Data-Centric Benchmark for Efficient LLM Adaptation in Text Summarization

  2025influential citation
• Sentence Embeddings as an intermediate target in end-to-end summarisation

  2025cites this paper
• DisComp: A Two-Stage Prompt Optimization Framework Combining Task-Agnostic and Task-Aware Compression

  2025cites this paper
• Advances and Challenges in the Automatic Identification of Indirect Quotations in Scholarly Texts and Literary Works

  2025cites this paper
• MorphMark: Flexible Adaptive Watermarking for Large Language Models

  2025cites this paper
• Abstractive text summarization: A comprehensive survey of techniques, systems, and challenges

  2025cites this paper
• A survey on biomedical automatic text summarization with large language models

  2025cites this paper
• Mechanistic Interpretability of GPT-like Models on Summarization Tasks

  2025influential citation
• LMR-IPGN: An Effective Model for automatic summarization of Chinese text

  2025cites this paper
• Advancing Low-Resource NLP: Contextual Question Answering for Bengali Language Using Llama

  2025cites this paper
• Parameter efficient multi-model vision assistant for polymer solvation behaviour inference

  2025cites this paper
• Mamba Drafters for Speculative Decoding

  2025cites this paper
• Improving Language Model Distillation through Hidden State Matching

  2025cites this paper
• Controlling Summarization Length Through EOS Token Weighting

  2025cites this paper
• StealthInk: A Multi-bit and Stealthy Watermark for Large Language Models

  2025cites this paper
• Dataset of News Articles with Provenance Metadata for Media Relevance Assessment

  2025cites this paper
• FlexQuant: A Flexible and Efficient Dynamic Precision Switching Framework for LLM Quantization

  2025cites this paper
• CRC-MRC: Reader Comments Augmented Machine Reading Comprehension for social emotion prediction

  2025cites this paper
• Rethinking Natural Language Generation with Layer-Wise Multi-View Decoding

  2025cites this paper
• SEEval: Advancing LLM Text Evaluation Efficiency and Accuracy through Self-Explanation Prompting

  2025cites this paper
• FactGuard: Leveraging Multi-Agent Systems to Generate Answerable and Unanswerable Questions for Enhanced Long-Context LLM Extraction

  2025cites this paper
• SWI: Speaking with Intent in Large Language Models

  2025cites this paper
• Improving zero-shot cross-domain slot filling via machine reading comprehension prompt template

  2025cites this paper
• D-GEN: Automatic Distractor Generation and Evaluation for Reliable Assessment of Generative Model

  2025cites this paper
• Key, Value, Compress: A Systematic Exploration of KV Cache Compression Techniques

  2025cites this paper
• Design and Research of Intelligent Chatbot for Campus Information Consultation Assistant

  2025cites this paper
• Can one size fit all?: Measuring Failure in Multi-Document Summarization Domain Transfer

  2025cites this paper
• Detection avoidance techniques for large language models

  2025cites this paper
• LLM Output Compliance with Handcrafted Linguistic Features: An Experiment

  2025cites this paper
• Integrating Concept Associations for Query Focused Knowledge Summarization

  2025cites this paper
• Hybrid text summarization: Integrating extractive and abstractive models for enhanced cross-domain summarization

  2025cites this paper
• HalluLens: LLM Hallucination Benchmark

  2025cites this paper
• Cl2sum: abstractive summarization via contrastive prompt constructed by LLMs hallucination

  2025cites this paper
• QFAS-KE: Query focused answer summarization using keyword extraction

  2025cites this paper
• RetriEVAL: Evaluating Text Generation with Contextualized Lexical Match

  2025cites this paper
• Large Language Models for Summarizing Czech Historical Documents and Beyond

  2025cites this paper
• Large Language Models Are Effective Human Annotation Assistants, But Not Good Independent Annotators

  2025cites this paper
• GPT-C: Generative PrompT Compression

  2025cites this paper
• HR-SKGs: Hyper-Relational Semantic Knowledge Graphs for Multi-hop Reading Comprehension

  2025cites this paper
• OpeNLGauge: An Explainable Metric for NLG Evaluation with Open-Weights LLMs

  2025cites this paper
• Bridging the LLM Accessibility Divide? Performance, Fairness, and Cost of Closed versus Open LLMs for Automated Essay Scoring

  2025cites this paper
• Generation of text summaries based on preprocessing pointer networks

  2025cites this paper
• Summarization Metrics for Spanish and Basque: Do Automatic Scores and LLM-Judges Correlate with Humans?

  2025cites this paper
• WikiVideo: Article Generation from Multiple Videos

  2025cites this paper
• YaleNLP @ PerAnsSumm 2025: Multi-Perspective Integration via Mixture-of-Agents for Enhanced Healthcare QA Summarization

  2025cites this paper
• Pay Attention to What and Where? Interpretable Feature Extractor in Vision-based Deep Reinforcement Learning

  2025cites this paper
• LLM-as-a-Judge: Reassessing the Performance of LLMs in Extractive QA

  2025cites this paper
• Prompt Tuning Techniques for Chinese Idiom Recommendation

  2025cites this paper
• A Survey on the Recent Advancements in Human-Centered Dialog Systems

  2025cites this paper
• FreqKV: Key-Value Compression in Frequency Domain for Context Window Extension

  2025cites this paper
• A Typology of Synthetic Datasets for Dialogue Processing in Clinical Contexts

  2025cites this paper
• Frame In, Frame Out: Do LLMs Generate More Biased News Headlines than Humans?

  2025cites this paper
• Benchmarking LLM Faithfulness in RAG with Evolving Leaderboards

  2025cites this paper
• An Evaluation Metric for Assessing Summary-Level Semantic Similarity in Abstractive Text Summarization

  2025cites this paper
• What are Models Thinking about? Understanding Large Language Model Hallucinations "Psychology" through Model Inner State Analysis

  2025cites this paper