The DOI matches its Crossref record; 23 of the 23 references it cites were found in a registry or an index.
Masked Language Modeling and the Distributional Hypothesis: Order Word Matters Pre-training for Little
Open accessAbstract
A possible explanation for the impressive performance of masked language model (MLM) pre-training is that such models have learned to represent the syntactic structures prevalent in classical NLP pipelines.In this paper, we propose a different explanation: MLMs succeed on downstream tasks mostly due to their ability to model higher-order word cooccurrence statistics.To demonstrate this, we pre-train MLMs on sentences with randomly shuffled word order, and we show that these models still achieve high accuracy after finetuning on many downstream tasks -including tasks specifically designed to be challenging for models that ignore word order.Our models also perform surprisingly well according to some parametric syntactic probes, indicating possible deficiencies in how we test representations for syntactic information.Overall, our results show that purely distributional information largely explains the success of pretraining, and they underscore the importance of curating challenging evaluation datasets that require deeper linguistic knowledge.
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.
Integrity signals
Registry
Cites
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.
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
Hochreiter, S., & Schmidhuber, J. (1997) · Neural Computation · doi:10.1162/neco.1997.9.8.1735 · Cited by 102,318
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019) · Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers) · doi:10.18653/v1/n19-1423 · Cited by 54,325
Distributed Representations of Words and Phrases and their Compositionality
Mikolov, T., Sutskever, I., Chen, K., Corrado, G., & Dean, J. (2013) · arXiv · doi:10.48550/arxiv.1310.4546 · Cited by 24,533 · cited 3×
“On one hand, we can view BERT as the newest in a long line of NLP techniques (Deerwester et al., 1990; Landauer and Dumais, 1997; Collobert and Weston, 2008; Mikolov et al., 2013; Peters et al., 2018) that exploit the well-known distributional hypothesis (Harris, 1954).”
BackgroundMethodRoBERTa: A Robustly Optimized BERT Pretraining Approach
Liu, Y., Ott, M., Goyal, N., Du, J., Joshi, M., Chen, D., Levy, O., Lewis, M., Zettlemoyer, L., & Stoyanov, V. (2019) · arXiv · doi:10.48550/arxiv.1907.11692 · Cited by 16,515
Deep Contextualized Word Representations
Peters, M., Neumann, M., Iyyer, M., Gardner, M., Clark, C., Lee, K., & Zettlemoyer, L. (2018) · Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers) · doi:10.18653/v1/n18-1202 · Cited by 11,983
Landauer, T. K., & Dumais, S. T. (1997) · Psychological Review · doi:10.1037/0033-295x.104.2.211 · Cited by 6,282
SQuAD: 100,000+ Questions for Machine Comprehension of Text
Rajpurkar, P., Zhang, J., Lopyrev, K., & Liang, P. (2016) · Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d16-1264 · Cited by 6,208 · cited 4×
“The GLUE (Wang et al., 2018) benchmark is a collection of 9 datasets for evaluating natural language understanding systems, of which we use Corpus of Linguistic Acceptability (CoLA) (Warstadt et al., 2019b), Stanford Sentiment Treebank (SST) (Socher et al., 2013), Microsoft Research Paragraph Corpus (MRPC) (Dolan and…”
BackgroundInfluentialGoogle's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation
Wu, Y., Schuster, M., Chen, Z., Le, Q. V., Norouzi, M., Macherey, W., Krikun, M., Cao, Y., Gao, Q., Macherey, K., et al. (2016) · arXiv · doi:10.48550/arxiv.1609.08144 · Cited by 5,319 · cited 1×
“In order to work around the Byte-Pair Encoding (BPE) token split, we use the WordPiece (Wu et al., 2016) tokens prepended with a space, as used in RoBERTa to compute the probability of a correct focus word and an incorrect focus word.”
MethodA unified architecture for natural language processing: deep neural networks with multitask learning
Collobert, R., & Weston, J. (2008) · Proceedings of the 25th international conference on Machine learning - ICML '08 · doi:10.1145/1390156.1390177 · Cited by 5,058
Harris, Z. S. (1954) · WORD · doi:10.1080/00437956.1954.11659520 · Cited by 4,807
Cited by
FinBERT: A Large Language Model for Extracting Information from Financial Text*
Huang, A. H., Wang, H., & Yang, Y. (2023) · Contemporary Accounting Research · doi:10.1111/1911-3846.12832 · Cited by 778
True Few-Shot Learning with Language Models
Perez, E., Kiela, D., & Cho, K. (2021) · arXiv · doi:10.48550/arxiv.2105.11447 · Cited by 226
“Recent work has used MDL to determine which learning algorithms are most effective at explaining the given data [Rissanen Data Analysis; 10, 34].”
MethodSelf-citationRePrompt: Automatic Prompt Editing to Refine AI-Generative Art Towards Precise Expressions
Wang, Y., Shen, S., & Lim, B. Y. (2023) · Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3544548.3581402 · Cited by 120
“Our work falls in this domain of interpretable prompt engineering by leveraging usable information from AI models [54, 73, 82, 85] and providing interpretable automated edits.”
MethodLanguage Model Behavior: A Comprehensive Survey
Chang, T. A., & Bergen, B. K. (2024) · Computational Linguistics · doi:10.1162/coli_a_00492 · Cited by 105
Shortcut Learning of Large Language Models in Natural Language Understanding
Du, M., He, F., Zou, N., Tao, D., & Hu, X. (2024) · Communications of the ACM · doi:10.1145/3596490 · Cited by 94
Metadata
- Authors
- Sinha, K., Jia, R., Hupkes, D., Pineau, J., Williams, A., & Kiela, D.
- Venue
- Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
- Published
- 2021
- Pages
- 2888-2913
- OpenAlex
- W3152698349
- Cited by
- 181
- References
- 23
- FWCI
- 18.14
- Type
- conference paper
- Language
- en
- Open access
- hybrid
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: Masked Language Modeling and the Distributional Hypothesis: Order Word Matters Pre-training for Little. https://app.cochat.ai/papers/10.18653/v1/2021.emnlp-main.230
- The paper
- Sinha, K., Jia, R., Hupkes, D., Pineau, J., Williams, A., & Kiela, D. (2021). Masked Language Modeling and the Distributional Hypothesis: Order Word Matters Pre-training for Little. Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing. https://doi.org/10.18653/v1/2021.emnlp-main.230
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.