Modeling Task Effects in Human Reading with Neural Network-based Attention

TL;DR

This paper presents NEAT, a neural network-based model that predicts how human attention during reading varies with different tasks, demonstrating that task effects are optimal adaptations to task demands.

Contribution

The paper introduces NEAT, a novel neural network model that explicitly predicts task-specific attention allocation in human reading, supported by empirical eye-tracking data.

Findings

NEAT accurately predicts attention patterns across different reading tasks.

Task effects in reading can be modeled as optimal adaptations to task demands.

Empirical data supports the model's predictions.

Abstract

Research on human reading has long documented that reading behavior shows task-specific effects, but it has been challenging to build general models predicting what reading behavior humans will show in a given task. We introduce NEAT, a computational model of the allocation of attention in human reading, based on the hypothesis that human reading optimizes a tradeoff between economy of attention and success at a task. Our model is implemented using contemporary neural network modeling techniques, and makes explicit and testable predictions about how the allocation of attention varies across different tasks. We test this in an eyetracking study comparing two versions of a reading comprehension task, finding that our model successfully accounts for reading behavior across the tasks. Our work thus provides evidence that task effects can be modeled as optimal adaptation to task demands.