# Robustness and Sensitivity of BERT Models Predicting Alzheimer's Disease from Text

arXiv: https://arxiv.org/abs/2109.11888 · HTML: https://mlsanity.com/paper/2109.11888/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 39 references that are in the map.
- First posted on arXiv 24 Sep 2021.

## Builds on (most cited first, 22 of 22)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering](https://mlsanity.com/paper/1612.00837/) (2016)
- [HuggingFace's Transformers: State-of-the-art Natural Language Processing](https://mlsanity.com/paper/1910.03771/) (2019)
- [A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks](https://mlsanity.com/paper/1807.03888/) (2018)
- [Improving Neural Machine Translation Models with Monolingual Data](https://mlsanity.com/paper/1511.06709/) (2015)
- [Annotation Artifacts in Natural Language Inference Data](https://mlsanity.com/paper/1803.02324/) (2018)
- [Text Summarization with Pretrained Encoders](https://mlsanity.com/paper/1908.08345/) (2019)
- [Generating Natural Language Adversarial Examples](https://mlsanity.com/paper/1804.07998/) (2018)
- [Are We Modeling the Task or the Annotator? An Investigation of Annotator Bias in Natural Language Understanding Datasets](https://mlsanity.com/paper/1908.07898/) (2019)
- [Breaking NLI Systems with Sentences that Require Simple Lexical Inferences](https://mlsanity.com/paper/1805.02266/) (2018)
- [Alzheimer's Dementia Recognition through Spontaneous Speech: The ADReSS Challenge](https://mlsanity.com/paper/2004.06833/) (2020)
- [Performance Impact Caused by Hidden Bias of Training Data for Recognizing Textual Entailment](https://mlsanity.com/paper/1804.08117/) (2018)
- [To BERT or Not To BERT: Comparing Speech and Language-based Approaches for Alzheimer's Disease Detection](https://mlsanity.com/paper/2008.01551/) (2020)
- [Adversarial Over-Sensitivity and Over-Stability Strategies for Dialogue Models](https://mlsanity.com/paper/1809.02079/) (2018)
- [Comparing Natural Language Processing Techniques for Alzheimer's Dementia Prediction in Spontaneous Speech](https://mlsanity.com/paper/2006.07358/) (2020)
- [Impact of ASR on Alzheimer's Disease Detection: All Errors are Equal, but Deletions are More Equal than Others](https://mlsanity.com/paper/1904.01684/) (2019)
- [Detecting cognitive impairments by agreeing on interpretations of linguistic features](https://mlsanity.com/paper/1808.06570/) (2018)
- [The Effect of Heterogeneous Data for Alzheimer's Disease Detection from Speech](https://mlsanity.com/paper/1811.12254/) (2018)
- [Fantastic Features and Where to Find Them: Detecting Cognitive Impairment with a Subsequence Classification Guided Approach](https://mlsanity.com/paper/2010.06579/) (2020)
- [Lexical Features Are More Vulnerable, Syntactic Features Have More Predictive Power](https://mlsanity.com/paper/1910.00065/) (2019)

## Built on by (most cited first, 5 of 5)

- [On the data requirements of probing](https://mlsanity.com/paper/2202.12801/) (2022)
- [A Systematic Review of NLP for Dementia -- Tasks, Datasets and Opportunities](https://mlsanity.com/paper/2409.19737/) (2024)
- [DECK: Behavioral Tests to Improve Interpretability and Generalizability of BERT Models Detecting Depression from Text](https://mlsanity.com/paper/2209.05286/) (2022)
- [Impact of Environmental Noise on Alzheimer's Disease Detection from Speech: Should You Let a Baby Cry?](https://mlsanity.com/paper/2203.17110/) (2022)
- [Zero-Shot Multi-Lingual Speaker Verification in Clinical Trials](https://mlsanity.com/paper/2404.01981/) (2024)

## Abstract (arXiv)

Understanding robustness and sensitivity of BERT models predicting Alzheimer's disease from text is important for both developing better classification models and for understanding their capabilities and limitations. In this paper, we analyze how a controlled amount of desired and undesired text alterations impacts performance of BERT. We show that BERT is robust to natural linguistic variations in text. On the other hand, we show that BERT is not sensitive to removing clinically important information from text.