# Lexical Features Are More Vulnerable, Syntactic Features Have More Predictive Power

arXiv: https://arxiv.org/abs/1910.00065 · HTML: https://mlsanity.com/paper/1910.00065/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Sep 2019.

## Built on by (most cited first, 3 of 3)

- [AARGH! End-to-end Retrieval-Generation for Task-Oriented Dialog](https://mlsanity.com/paper/2209.03632/) (2022)
- [Robustness and Sensitivity of BERT Models Predicting Alzheimer's Disease from Text](https://mlsanity.com/paper/2109.11888/) (2021)
- [Impact of Environmental Noise on Alzheimer's Disease Detection from Speech: Should You Let a Baby Cry?](https://mlsanity.com/paper/2203.17110/) (2022)

## Abstract (arXiv)

Understanding the vulnerability of linguistic features extracted from noisy text is important for both developing better health text classification models and for interpreting vulnerabilities of natural language models. In this paper, we investigate how generic language characteristics, such as syntax or the lexicon, are impacted by artificial text alterations. The vulnerability of features is analysed from two perspectives: (1) the level of feature value change, and (2) the level of change of feature predictive power as a result of text modifications. We show that lexical features are more sensitive to text modifications than syntactic ones. However, we also demonstrate that these smaller changes of syntactic features have a stronger influence on classification performance downstream, compared to the impact of changes to lexical features. Results are validated across three datasets representing different text-classification tasks, with different levels of lexical and syntactic complexity of both conversational and written language.