With blinkers on: Robust prediction of eye movements across readers

TY - GEN

T1 - With blinkers on: Robust prediction of eye movements across readers

AU - Matthies, Franz

AU - Søgaard, Anders

PY - 2013

Y1 - 2013

N2 - Nilsson and Nivre (2009) introduced a tree-based model of persons' eye movements in reading. The individual variation between readers reportedly made application across readers impossible. While a tree-based model seems plausible for eye movements, we show that competitive results can be obtained with a linear CRF model. Increasing the inductive bias also makes learning across readers possible. In fact we observe next-to-no performance drop when evaluating models trained on gaze records of multiple readers on new readers.

AB - Nilsson and Nivre (2009) introduced a tree-based model of persons' eye movements in reading. The individual variation between readers reportedly made application across readers impossible. While a tree-based model seems plausible for eye movements, we show that competitive results can be obtained with a linear CRF model. Increasing the inductive bias also makes learning across readers possible. In fact we observe next-to-no performance drop when evaluating models trained on gaze records of multiple readers on new readers.

M3 - Article in proceedings

SP - 803

EP - 807

BT - EMNLP 2013

PB - Association for Computational Linguistics

ER -