mlsanityData to 7 Oct 2026

A BERT Baseline for the Natural Questions

arXiv 1901.08634 ↗First posted 24 Jan 2019cs.CLcited by 33

Not on the map. Why?

Abstract (arXiv)

This technical note describes a new baseline for the Natural Questions. Our model is based on BERT and reduces the gap between the model F1 scores reported in the original dataset paper and the human upper bound by 30% and 50% relative for the long and short answer tasks respectively. This baseline has been submitted to the official NQ leaderboard at ai.google.com/research/NaturalQuestions. Code, preprocessed data and pretrained model are available at https://github.com/google-research/language/tree/master/language/question_answering/bert_joint.

Key facts. Cited by 33 papers in the map (data through 7 Oct 2026). First posted on arXiv 24 Jan 2019.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 20; 2022: 6; 2023: 4; 2024: 1; 2025: 2.

33 papers.

Sort:

By area:

  1. 2021FinQA: A Dataset of Numerical Reasoning over Financial Datacited by 552
  2. 2025Humanity's Last Examcited by 467
  3. 2021Understanding by Understanding Not: Modeling Negation in Language Modelscited by 73
  4. 2021Poolingformer: Long Document Modeling with Pooling Attentioncited by 60
  5. 2021Knowing More About Questions Can Help: Improving Calibration in Question Answeringcited by 47
  6. 2021Can NLI Models Verify QA Systems' Predictions?cited by 46
  7. 2021SD-QA: Spoken Dialectal Question Answering for the Real Worldcited by 36
  8. 2021EntQA: Entity Linking as Question Answeringcited by 34
  9. 2021Capturing Row and Column Semantics in Transformer Based Question Answering over Tablescited by 31
  10. 2021Representations for Question Answering from Documents with Tables and Textcited by 21
  11. 2021What's in a Name? Answer Equivalence For Open-Domain Question Answeringcited by 21
  12. 2022Reasoning over Public and Private Data in Retrieval-Based Systemscited by 21
21 more
  1. 2021MuMuQA: Multimedia Multi-Hop News Question Answering via Cross-Media Knowledge Extraction and Groundingcited by 19
  2. 2022On Measuring Social Biases in Prompt-Based Multi-Task Learningcited by 10
  3. 2021Towards More Equitable Question Answering Systems: How Much More Data Do You Need?cited by 8
  4. 2022Synthetic Target Domain Supervision for Open Retrieval QAcited by 6
  5. 2023Comprehensive Overview of Named Entity Recognition: Models, Domain-Specific Applications and Challengescited by 6
  6. 2025Automatic Dataset Generation for Knowledge Intensive Question Answering Taskscited by 6
  7. 2021Toward Deconfounding the Influence of Entity Demographics for Question Answering Accuracycited by 5
  8. 2021Do Answers to Boolean Questions Need Explanations? Yescited by 5
  9. 2022Evaluation of Question Answering Systems: Complexity of judging a natural languagecited by 5
  10. 2024Human Latency Conversational Turns for Spoken Avatar Systemscited by 5
  11. 2023PrimeQA: The Prime Repository for State-of-the-Art Multilingual Question Answering Research and Developmentcited by 4
  12. 2021Towards Confident Machine Reading Comprehensioncited by 3
  13. 2021Investigating Post-pretraining Representation Alignment for Cross-Lingual Question Answeringcited by 3
  14. 2023Analysis of the Reasoning with Redundant Information Provided Ability of Large Language Modelscited by 2
  15. 2021When to Fold'em: How to answer Unanswerable questionscited by 1
  16. 2022GAAMA 2.0: An Integrated System that Answers Boolean and Extractive Questionscited by 1
  17. 2021BERT-based knowledge extraction method of unstructured domain textcited by 0
  18. 2021VAULT: VAriable Unified Long Text Representation for Machine Reading Comprehensioncited by 0
  19. 2021Android Security using NLP Techniques: A Reviewcited by 0
  20. 2022Zero-Shot Dynamic Quantization for Transformer Inferencecited by 0
  21. 2023A Quantitative Review on Language Model Efficiency Researchcited by 0