Student or educator? Sign up with your school email and get 6 months of Pro free.
CoChat

The DOI matches its Crossref record; 53 of the 53 references it cites were found in a registry or an index.

SpanBERT: Improving Pre-training by Representing and Predicting Spans

Open access
Joshi, Mandar, Chen, Danqi, Liu, Yinhan, Weld, Daniel S., Zettlemoyer, Luke, Levy, Omer · 2020 · Transactions of the Association for Computational Linguistics

Abstract

We present SpanBERT, a pre-training method that is designed to better represent and predict spans of text. Our approach extends BERT by (1) masking contiguous random spans, rather than random tokens, and (2) training the span boundary representations to predict the entire content of the masked span, without relying on the individual token representations within it. SpanBERT consistently outperforms BERT and our better-tuned baselines, with substantial gains on span selection tasks such as question answering and coreference resolution. In particular, with the same training data and model size as BERT large , our single model obtains 94.6% and 88.7% F1 on SQuAD 1.1 and 2.0 respectively. We also achieve a new state of the art on the OntoNotes coreference resolution task (79.6% F1), strong performance on the TACRED relation extraction benchmark, and even gains on GLUE. 1

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1162/tacl_a_00300

Cites

53 of 53 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 51 references

Research works printed but not linked: 44

  1. Ba Jimmy Lei, 2016, arXiv preprint arXiv:1607.06450 · arXiv
  2. Cer Daniel, 2017, International Workshop on Semantic Evaluation (SemEval), 1
  3. Dagan Ido, 2005, Machine Learning Challenges Workshop, 177
  4. Dai Andrew M., 2015, Advances in Neural Information Processing Systems (NIPS), 3079
  5. Dai Zihang, 2019, Association for Computational Linguistics (ACL)
  6. Devlin Jacob, 2019, North American Association for Computational Linguistics (NAACL)
  7. Dolan William B., 2005, Proceedings of the International Workshop on Paraphrasing
  8. Li Dong, 2019, Advances in Neural Information Processing Systems (NIPS)
  9. Fisch Adam, 2019, Proceedings of 2nd Machine Reading for Reading Comprehension (MRQA) Workshop at EMNLP
  10. Giampiccolo Danilo, 2007, Proceedings of the ACL-PASCAL Workshop on Textual Entailment and Paraphrasing, 1
  11. He Luheng, 2018, Association for Computational Linguistics (ACL), 364
  12. Hendrycks Dan, 2016, arXiv preprint arXiv:1606.08415 · arXiv
  13. Howard Jeremy, 2018, arXiv preprint arXiv:1801.06146 · arXiv
  14. Joshi Mandar, 2019, North American Association for Computational Linguistics (NAACL), 3597
  15. Joshi Mandar, 2017, Association for Computational Linguistics (ACL), 1601
  16. Joshi Mandar, 2019, Empirical Methods in Natural Language Processing (EMNLP)
  17. Kingma Diederik, 2015, International Conference on Learning Representations (ICLR)
  18. Kiros Ryan, 2015, Advances in Neural Information Processing Systems (NIPS)
  19. Kwiatkowski Tom, 2019, Transactions of the Association of Computational Linguistics (TACL)
  20. Lample Guillaume, 2019, Advances in Neural Information Processing Systems (NIPS)
  21. Lee Kenton, 2017, Empirical Methods in Natural Language Processing (EMNLP), 188
  22. Lee Kenton, 2018, North American Association for Computational Linguistics (NAACL), 687
  23. Levesque Hector J., 2011, AAAI Spring Symposium: Logical Formalizations of Commonsense Reasoning, 46, 47
  24. Liu Xiaodong, 2019, Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
  25. Loshchilov Ilya, 2019, International Conference on Learning Representations (ICLR)
  26. Melamud Oren, 2016, Computational Natural Language Learning (CoNLL), 51
  27. Ott Myle, 2019, North American Association for Computational Linguistics (NAACL), 48
  28. Peters Matthew, 2018, North American Association for Computational Linguistics (NAACL), 2227
  29. Pradhan Sameer, 2012, Joint Conference on EMNLP and CoNLL-Shared Task, 1
  30. Press Ofir, 2017, Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 2, Short Papers, 157
  31. Rajpurkar Pranav, 2018, Association for Computational Linguistics (ACL), 784
  32. Rajpurkar Pranav, 2016, Empirical Methods in Natural Language Processing (EMNLP), 2383
  33. Soares Livio Baldini, 2019, Association for Computational Linguistics (ACL), 2895
  34. Socher Richard, 2013, Empirical Methods in Natural Language Processing (EMNLP), 1631
  35. Song Kaitao, 2019, International Conference on Machine Learning (ICML), 5926
  36. Stern Mitchell, 2018, Advances in Neural Information Processing Systems (NIPS)
  37. Vaswani Ashish, 2017, Advances in Neural Information Processing Systems (NIPS)
  38. Wang Alex, 2019, International Conference on Learning Representations (ICLR)
  39. Warstadt Alex, 2018, arXiv preprint arXiv:1805.12471 · arXiv
  40. Williams Adina, 2018, North American Association for Computational Linguistics (NAACL), 1112
  41. Yang Zhilin, 2019, Advances in Neural Information Processing Systems (NeurIPS)
  42. Yang Zhilin, 2018, Empirical Methods in Natural Language Processing (EMNLP), 2369
  43. Zhang Yuhao, 2017, Empirical Methods in Natural Language Processing (EMNLP), 35
  44. Zhang Zhengyan, 2019, Association for Computational Linguistics (ACL), 1441

Cited by

See all 1,827

Metadata

Authors
Joshi, M., Chen, D., Liu, Y., Weld, D. S., Zettlemoyer, L., & Levy, O.
Affiliations
  • University of Washington (US)
  • Princeton University (US)
  • Meta (United States) (US)
Venue
Transactions of the Association for Computational Linguistics
Publisher
MIT Press
Published
2020-12
Volume
8
Pages
64-77
ISSN
2307-387X (ISSN-L)
OpenAlex
W2962753370
Cited by
1,827
References
51
Citations by year
2026: 84 · 2025: 169 · 2024: 214 · 2023: 373 · 2022: 342 · 2021: 393 · 2020: 224
FWCI
130.82
Type
journal article
Language
en
Open access
Licence
cc-by
Locations
  • Transactions of the Association for Computational Linguistics (publishedVersion, cc-by)
  • arXiv (Cornell University) (submittedVersion)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
  • arXiv (Cornell University)
Funders
University of Washington
Topics
  • Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
  • Physical Sciences › Computer Science › Artificial Intelligence › Natural Language Processing Techniques
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Multimodal Machine Learning Applications
Keywords
SpanBERT, BERT pre-training, span prediction, question answering, coreference resolution, relation extraction, text representation learning

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: SpanBERT: Improving Pre-training by Representing and Predicting Spans. https://app.cochat.ai/papers/10.1162/tacl_a_00300
The paper
Joshi, M., Chen, D., Liu, Y., Weld, D. S., Zettlemoyer, L., & Levy, O. (2020). SpanBERT: Improving Pre-training by Representing and Predicting Spans. Transactions of the Association for Computational Linguistics. https://doi.org/10.1162/tacl_a_00300

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.