mlsanityData to 14 Oct 2026

Bidirectional Attention Flow for Machine Comprehension

arXiv 1611.01603 ↗First posted 5 Nov 2016cs.CLcited by 278

Not on the map. Why?

Abstract (arXiv)

Machine comprehension (MC), answering a query about a given context paragraph, requires modeling complex interactions between the context and the query. Recently, attention mechanisms have been successfully extended to MC. Typically these methods use attention to focus on a small portion of the context and summarize it with a fixed-size vector, couple attentions temporally, and/or often form a uni-directional attention. In this paper we introduce the Bi-Directional Attention Flow (BIDAF) network, a multi-stage hierarchical process that represents the context at different levels of granularity and uses bi-directional attention flow mechanism to obtain a query-aware context representation without early summarization. Our experimental evaluations show that our model achieves the state-of-the-art results in Stanford Question Answering Dataset (SQuAD) and CNN/DailyMail cloze test.

Key facts. Cited by 278 papers in the map (data through 14 Oct 2026). First posted on arXiv 5 Nov 2016.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2020: 1; 2021: 109; 2022: 76; 2023: 47; 2024: 23; 2025: 14; 2026: 8.

278 papers.

Sort:

By area:

  1. 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,141
  2. 2022WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agentscited by 1,251
  3. 2021Dynabench: Rethinking Benchmarking in NLPcited by 459
  4. 2022ZeroGen: Efficient Zero-shot Learning via Dataset Generationcited by 211
  5. 2021Muppet: Massive Multi-task Representations with Pre-Finetuningcited by 192
  6. 2021Retrieving and Reading: A Comprehensive Survey on Open-domain Question Answeringcited by 178
  7. 2021Explaining Answers with Entailment Treescited by 152
  8. 2022Rich Knowledge Sources Bring Complex Knowledge Conflicts: Recalibrating Models to Reflect Conflicting Evidencecited by 144
  9. 2021Interventional Video Grounding with Dual Contrastive Learningcited by 94
  10. 2023Hierarchical Video-Moment Retrieval and Step-Captioningcited by 83
  11. 2022Tomayto, Tomahto. Beyond Token-level Answer Equivalence for Question Answering Evaluationcited by 67
  12. 2022A General Survey on Attention Mechanisms in Deep Learningcited by 64
38 more
  1. 2021Video Corpus Moment Retrieval with Contrastive Learningcited by 60
  2. 2021Natural Language Video Localization: A Revisit in Span-based Question Answering Frameworkcited by 55
  3. 2021Dynaboard: An Evaluation-As-A-Service Platform for Holistic Next-Generation Benchmarkingcited by 53
  4. 2021Attention, please! A survey of Neural Attention Models in Deep Learningcited by 51
  5. 2021Knowing More About Questions Can Help: Improving Calibration in Question Answeringcited by 47
  6. 2021Biomedical Question Answering: A Survey of Approaches and Challengescited by 46
  7. 2021Can NLI Models Verify QA Systems' Predictions?cited by 46
  8. 2023NaQ: Leveraging Narrations as Queries to Supervise Episodic Memorycited by 46
  9. 2025Wide-In, Narrow-Out: Revokable Decoding for Efficient and Effective DLLMscited by 46
  10. 2021Coreference Resolution without Span Representationscited by 45
  11. 2022Towards Visual-Prompt Temporal Answering Grounding in Medical Instructional Videocited by 43
  12. 2022Neural Approaches to Conversational Information Retrievalcited by 42
  13. 2021Bidirectional Machine Reading Comprehension for Aspect Sentiment Triplet Extractioncited by 40
  14. 2021Why Machine Reading Comprehension Models Learn Shortcuts?cited by 40
  15. 2021JointLK: Joint Reasoning with Language Models and Knowledge Graphs for Commonsense Question Answeringcited by 40
  16. 2021Paradigm Shift in Natural Language Processingcited by 39
  17. 2021ASPECTNEWS: Aspect-Oriented Summarization of News Documentscited by 37
  18. 2022Temporal Sentence Grounding in Videos: A Survey and Future Directionscited by 37
  19. 2022On Transforming Reinforcement Learning by Transformer: The Development Trajectorycited by 36
  20. 2021CONQUER: Contextual Query-aware Ranking for Video Corpus Moment Retrievalcited by 33
  21. 2021Conversational Question Answering: A Surveycited by 31
  22. 2025Self Speculative Decoding for Diffusion Large Language Modelscited by 30
  23. 2021Self-supervised Dialogue Learning for Spoken Conversational Question Answeringcited by 28
  24. 2023A Review of Deep Learning for Video Captioningcited by 28
  25. 2023Pushing the Limits of ChatGPT on NLP Taskscited by 27
  26. 2022A Dataset for Medical Instructional Video Classification and Question Answeringcited by 26
  27. 2021NoiseQA: Challenge Set Evaluation for User-Centric Question Answeringcited by 25
  28. 2021A Short Survey of Pre-trained Language Models for Conversational AI-A NewAge in NLPcited by 25
  29. 2021Introspective Distillation for Robust Question Answeringcited by 25
  30. 2024Distractor Generation in Multiple-Choice Tasks: A Survey of Methods, Datasets, and Evaluationcited by 25
  31. 2021Incorporating Commonsense Knowledge Graph in Pretrained Models for Social Commonsense Taskscited by 24
  32. 2022Video Activity Localisation with Uncertainties in Temporal Boundarycited by 24
  33. 2021Parallel Attention Network with Sequence Matching for Video Groundingcited by 22
  34. 2021Improving Unsupervised Question Answering via Summarization-Informed Question Generationcited by 21
  35. 2021Do Question Answering Modeling Improvements Hold Across Benchmarks?cited by 20
  36. 2021Contrastive Domain Adaptation for Question Answering using Limited Text Corporacited by 20
  37. 2021Benchmarking Knowledge-Enhanced Commonsense Question Answering via Knowledge-to-Text Transformationcited by 19
  38. 2021Idiomatic Expression Identification using Semantic Compatibilitycited by 19

50 most cited of 278 All 278 (JSON)