# Local Structure Matters Most in Most Languages

arXiv: https://arxiv.org/abs/2211.05025 · HTML: https://mlsanity.com/paper/2211.05025/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 37 references that are in the map.
- First posted on arXiv 9 Nov 2022.

## Builds on (most cited first, 30 of 30)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding](https://mlsanity.com/paper/1804.07461/) (2018)
- [mT5: A massively multilingual pre-trained text-to-text transformer](https://mlsanity.com/paper/2010.11934/) (2020)
- [Cross-lingual Language Model Pretraining](https://mlsanity.com/paper/1901.07291/) (2019)
- [Multilingual Denoising Pre-training for Neural Machine Translation](https://mlsanity.com/paper/2001.08210/) (2020)
- [Neural Network Acceptability Judgments](https://mlsanity.com/paper/1805.12471/) (2018)
- [XTREME: A Massively Multilingual Multi-task Benchmark for Evaluating Cross-lingual Generalization](https://mlsanity.com/paper/2003.11080/) (2020)
- [ByT5: Towards a token-free future with pre-trained byte-to-byte models](https://mlsanity.com/paper/2105.13626/) (2021)
- [CamemBERT: a Tasty French Language Model](https://mlsanity.com/paper/1911.03894/) (2019)
- [AraBERT: Transformer-based Model for Arabic Language Understanding](https://mlsanity.com/paper/2003.00104/) (2020)
- [XCOPA: A Multilingual Dataset for Causal Commonsense Reasoning](https://mlsanity.com/paper/2005.00333/) (2020)
- [CANINE: Pre-training an Efficient Tokenization-Free Encoder for Language Representation](https://mlsanity.com/paper/2103.06874/) (2021)
- [XGLUE: A New Benchmark Dataset for Cross-lingual Pre-training, Understanding and Generation](https://mlsanity.com/paper/2004.01401/) (2020)
- [Masked Language Modeling and the Distributional Hypothesis: Order Word Matters Pre-training for Little](https://mlsanity.com/paper/2104.06644/) (2021)
- [FlauBERT: Unsupervised Language Model Pre-training for French](https://mlsanity.com/paper/1912.05372/) (2019)
- [PhoBERT: Pre-trained language models for Vietnamese](https://mlsanity.com/paper/2003.00744/) (2020)
- [BERTje: A Dutch BERT Model](https://mlsanity.com/paper/1912.09582/) (2019)
- [Out of Order: How Important Is The Sequential Order of Words in a Sentence in Natural Language Understanding Tasks?](https://mlsanity.com/paper/2012.15180/) (2020)
- [UnNatural Language Inference](https://mlsanity.com/paper/2101.00010/) (2020)
- [What Context Features Can Transformer Language Models Use?](https://mlsanity.com/paper/2106.08367/) (2021)
- [Do Neural Dialog Systems Use the Conversation History Effectively? An Empirical Study](https://mlsanity.com/paper/1906.01603/) (2019)
- [BERT & Family Eat Word Salad: Experiments with Text Understanding](https://mlsanity.com/paper/2101.03453/) (2021)
- [Playing with Words at the National Library of Sweden -- Making a Swedish BERT](https://mlsanity.com/paper/2007.01658/) (2020)
- [PTT5: Pretraining and validating the T5 model on Brazilian Portuguese data](https://mlsanity.com/paper/2008.09144/) (2020)
- [Word Order Does Matter (And Shuffled Language Models Know It)](https://mlsanity.com/paper/2203.10995/) (2022)
- [When classifying grammatical role, BERT doesn't care about word order... except when it matters](https://mlsanity.com/paper/2203.06204/) (2022)
- [Local Structure Matters Most: Perturbation Study in NLU](https://mlsanity.com/paper/2107.13955/) (2021)
- [Shaking Syntactic Trees on the Sesame Street: Multilingual Probing with Controllable Perturbations](https://mlsanity.com/paper/2109.14017/) (2021)
- [Schr"odinger's Tree -- On Syntax and Neural Language Models](https://mlsanity.com/paper/2110.08887/) (2021)

## Built on by (most cited first, 1 of 1)

- [The Grammar of Transformers: A Systematic Review of Interpretability Research on Syntactic Knowledge in Language Models](https://mlsanity.com/paper/2601.19926/) (2026)

## Abstract (arXiv)

Many recent perturbation studies have found unintuitive results on what does and does not matter when performing Natural Language Understanding (NLU) tasks in English. Coding properties, such as the order of words, can often be removed through shuffling without impacting downstream performances. Such insight may be used to direct future research into English NLP models. As many improvements in multilingual settings consist of wholesale adaptation of English approaches, it is important to verify whether those studies replicate or not in multilingual settings. In this work, we replicate a study on the importance of local structure, and the relative unimportance of global structure, in a multilingual setting. We find that the phenomenon observed on the English language broadly translates to over 120 languages, with a few caveats.