# Dual input stream transformer for vertical drift correction in eye-tracking reading data

arXiv: https://arxiv.org/abs/2311.06095 · HTML: https://mlsanity.com/paper/2311.06095/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 54 references that are in the map.
- First posted on arXiv 10 Nov 2023.

## Builds on (most cited first, 10 of 10)

- [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)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification](https://mlsanity.com/paper/1502.01852/) (2015)
- [Pointer Sentinel Mixture Models](https://mlsanity.com/paper/1609.07843/) (2016)
- [CoAtNet: Marrying Convolution and Attention for All Data Sizes](https://mlsanity.com/paper/2106.04803/) (2021)
- [Deep Neural Networks for Rank-Consistent Ordinal Regression Based On Conditional Probabilities](https://mlsanity.com/paper/2111.08851/) (2021)
- [Eyettention: An Attention-based Dual-Sequence Model for Predicting Human Scanpaths during Reading](https://mlsanity.com/paper/2304.10784/) (2023)
- [Assessing Language Proficiency from Eye Movements in Reading](https://mlsanity.com/paper/1804.07329/) (2018)
- [Do readers use character information when programming return-sweep saccades?](https://mlsanity.com/paper/1911.00716/) (2019)

## Built on by (most cited first, 2 of 2)

- [EMTeC: A Corpus of Eye Movements on Machine-Generated Texts](https://mlsanity.com/paper/2408.04289/) (2024)
- [Sure About That Line? Approaching Confidence-Based, Real-Time Line Assignment in Reading Gaze Data](https://mlsanity.com/paper/2605.00033/) (2026)

## Abstract (arXiv)

We introduce a novel Dual Input Stream Transformer (DIST) for the challenging problem of assigning fixation points from eye-tracking data collected during passage reading to the line of text that the reader was actually focused on. This post-processing step is crucial for analysis of the reading data due to the presence of noise in the form of vertical drift. We evaluate DIST against eleven classical approaches on a comprehensive suite of nine diverse datasets. We demonstrate that combining multiple instances of the DIST model in an ensemble achieves high accuracy across all datasets. Further combining the DIST ensemble with the best classical approach yields an average accuracy of 98.17 %. Our approach presents a significant step towards addressing the bottleneck of manual line assignment in reading research. Through extensive analysis and ablation studies, we identify key factors that contribute to DIST's success, including the incorporation of line overlap features and the use of a second input stream. Via rigorous evaluation, we demonstrate that DIST is robust to various experimental setups, making it a safe first choice for practitioners in the field.