# Can Pretrained Language Models Derive Correct Semantics from Corrupt Subwords under Noise?

arXiv: https://arxiv.org/abs/2306.15268 · HTML: https://mlsanity.com/paper/2306.15268/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 33 of its 65 references that are in the map.
- First posted on arXiv 27 Jun 2023.

## Builds on (most cited first, 30 of 33)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [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)
- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [SQuAD: 100,000+ Questions for Machine Comprehension of Text](https://mlsanity.com/paper/1606.05250/) (2016)
- [Neural Machine Translation of Rare Words with Subword Units](https://mlsanity.com/paper/1508.07909/) (2015)
- [ALBERT: A Lite BERT for Self-supervised Learning of Language Representations](https://mlsanity.com/paper/1909.11942/) (2019)
- [Deep Learning with Differential Privacy](https://mlsanity.com/paper/1607.00133/) (2016)
- [Extracting Training Data from Large Language Models](https://mlsanity.com/paper/2012.07805/) (2020)
- [SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processing](https://mlsanity.com/paper/1808.06226/) (2018)
- [Neural Network Acceptability Judgments](https://mlsanity.com/paper/1805.12471/) (2018)
- [How Contextual are Contextualized Word Representations? Comparing the Geometry of BERT, ELMo, and GPT-2 Embeddings](https://mlsanity.com/paper/1909.00512/) (2019)
- [Universal Adversarial Triggers for Attacking and Analyzing NLP](https://mlsanity.com/paper/1908.07125/) (2019)
- [Generating Natural Language Adversarial Examples](https://mlsanity.com/paper/1804.07998/) (2018)
- [Synthetic and Natural Noise Both Break Neural Machine Translation](https://mlsanity.com/paper/1711.02173/) (2017)
- [Bidirectional Attention Flow for Machine Comprehension](https://mlsanity.com/paper/1611.01603/) (2016)
- [Representation Degeneration Problem in Training Natural Language Generation Models](https://mlsanity.com/paper/1907.12009/) (2019)
- [ConSERT: A Contrastive Framework for Self-Supervised Sentence Representation Transfer](https://mlsanity.com/paper/2105.11741/) (2021)
- [Unlearnable Examples: Making Personal Data Unexploitable](https://mlsanity.com/paper/2101.04898/) (2021)
- [Learning to Ask: Neural Question Generation for Reading Comprehension](https://mlsanity.com/paper/1705.00106/) (2017)
- [Counter-fitting Word Vectors to Linguistic Constraints](https://mlsanity.com/paper/1603.00892/) (2016)
- [MetaPoison: Practical General-purpose Clean-label Data Poisoning](https://mlsanity.com/paper/2004.00225/) (2020)
- [Unlearn Dataset Bias in Natural Language Inference by Fitting the Residual](https://mlsanity.com/paper/1908.10763/) (2019)
- [LowKey: Leveraging Adversarial Attacks to Protect Social Media Users from Facial Recognition](https://mlsanity.com/paper/2101.07922/) (2021)
- [CharacterBERT: Reconciling ELMo and BERT for Word-Level Open-Vocabulary Representations From Characters](https://mlsanity.com/paper/2010.10392/) (2020)
- [Imitation Attacks and Defenses for Black-box Machine Translation Systems](https://mlsanity.com/paper/2004.15015/) (2020)
- [Superbizarre Is Not Superb: Derivational Morphology Improves BERT's Interpretation of Complex Words](https://mlsanity.com/paper/2101.00403/) (2021)
- [Why Machine Reading Comprehension Models Learn Shortcuts?](https://mlsanity.com/paper/2106.01024/) (2021)
- [Character-level White-Box Adversarial Attacks against Transformers via Attachable Subwords Substitution](https://mlsanity.com/paper/2210.17004/) (2022)

## Built on by (most cited first, 6 of 6)

- [Making Harmful Behaviors Unlearnable for Large Language Models](https://mlsanity.com/paper/2311.02105/) (2023)
- [MultiDelete for Multimodal Machine Unlearning](https://mlsanity.com/paper/2311.12047/) (2023)
- [MU-Bench: A Multitask Multimodal Benchmark for Machine Unlearning](https://mlsanity.com/paper/2406.14796/) (2024)
- [Toward Availability Attacks in 3D Point Clouds](https://mlsanity.com/paper/2407.11011/) (2024)
- [HiddenSpeaker: Generate Imperceptible Unlearnable Audios for Speaker Verification System](https://mlsanity.com/paper/2405.15655/) (2024)
- [Scrambled text: training Language Models to correct OCR errors using synthetic data](https://mlsanity.com/paper/2409.19735/) (2024)

## Abstract (arXiv)

For Pretrained Language Models (PLMs), their susceptibility to noise has recently been linked to subword segmentation. However, it is unclear which aspects of segmentation affect their understanding. This study assesses the robustness of PLMs against various disrupted segmentation caused by noise. An evaluation framework for subword segmentation, named Contrastive Lexical Semantic (CoLeS) probe, is proposed. It provides a systematic categorization of segmentation corruption under noise and evaluation protocols by generating contrastive datasets with canonical-noisy word pairs. Experimental results indicate that PLMs are unable to accurately compute word meanings if the noise introduces completely different subwords, small subword fragments, or a large number of additional subwords, particularly when they are inserted within other subwords.