Modeling Task Effects in Human Reading with Neural Network-based Attention
This work addresses the problem of modeling task effects in human reading for researchers in cognitive science and computational linguistics, but it is incremental as it builds on existing hypotheses with neural network techniques.
The paper tackled the challenge of predicting task-specific reading behavior by introducing NEAT, a neural network-based attention model that hypothesizes human reading optimizes a tradeoff between attention economy and task success, and it successfully accounted for reading behavior across different tasks in an eyetracking study.
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.