Controlling Reading Ease with Gaze-Guided Text Generation
This work addresses text simplification for information accessibility and personalized educational material for language learners, representing a novel application but with incremental method improvements.
The study tackled the problem of generating texts with controllable reading ease by using a model that predicts human gaze patterns to steer language model outputs, and the results showed it effectively made texts easier or harder to read, as measured by reading times and perceived difficulty in an eye-tracking experiment.
The way our eyes move while reading can tell us about the cognitive effort required to process the text. In the present study, we use this fact to generate texts with controllable reading ease. Our method employs a model that predicts human gaze patterns to steer language model outputs towards eliciting certain reading behaviors. We evaluate the approach in an eye-tracking experiment with native and non-native speakers of English. The results demonstrate that the method is effective at making the generated texts easier or harder to read, measured both in terms of reading times and perceived difficulty of the texts. A statistical analysis reveals that the changes in reading behavior are mostly due to features that affect lexical processing. Possible applications of our approach include text simplification for information accessibility and generation of personalized educational material for language learning.