Learning Where to Look: Modeling Eye Movements in Reading

We propose a novel machine learning task that consists in learning to predict which words in a text are fixated by a reader. In a first pilot experiment, we show that it is possible to out-perform a majority baseline using a transition-based model with a logistic regression classifier and a very limited set of features. We also show that the model is capable of capturing frequency effects on eye movements observed in human readers.

[1]  Alexander Pollatsek,et al.  E–Z Reader: A cognitive-control, serial-attention model of eye-movement behavior during reading , 2006, Cognitive Systems Research.

[2]  R H S Carpenter,et al.  An anatomically constrained, stochastic model of eye movement control in reading. , 2005, Psychological review.

[3]  K. Rayner,et al.  Eye Movements in Reading: Perceptual and Language Processes , 1985 .

[4]  Yuji Matsumoto,et al.  Statistical Dependency Analysis with Support Vector Machines , 2003, IWPT.

[5]  Ronan G. Reilly,et al.  Some empirical tests of an interactive activation model of eye movement control in reading , 2006, Cognitive Systems Research.

[6]  Dario D. Salvucci.  An integrated model of eye movements and visual encoding , 2001, Cognitive Systems Research.

[7]  K. Rayner,et al.  Eye movements in reading words and sentences , 2007 .

[8]  K. Rayner.  Eye movements in reading and information processing: 20 years of research. , 1998, Psychological bulletin.

[9]  Gary Feng,et al.  Eye movements as time-series random variables: A stochastic model of eye movement control in reading , 2006, Cognitive Systems Research.

[10]  Erik D. Reichle,et al.  Tests of the E-Z Reader model: Exploring the interface between cognition and eye-movement control , 2006, Cognitive Psychology.

[11]  Erik D. Reichle,et al.  The E-Z Reader model of eye-movement control in reading: Comparisons to other models , 2003, Behavioral and Brain Sciences.

[12]  Shun-Nan Yang,et al.  An oculomotor-based model of eye movements in reading: The competition/interaction model , 2006, Cognitive Systems Research.

[13]  G. Legge,et al.  Mr. Chips: an ideal-observer model of reading. , 1997, Psychological review.

[14]  Ralf Engbert,et al.  A dynamical model of saccade generation in reading based on spatially distributed lexical processing , 2002, Vision Research.

[15]  Joakim Nivre,et al.  Inductive Dependency Parsing , 2006, Text, speech and language technology.

[16]  K. Rayner,et al.  Eye movements during reading: some current controversies , 2001, Trends in Cognitive Sciences.

[17]  Erik D. Reichle,et al.  Toward a model of eye movement control in reading. , 1998, Psychological review.

[18]  Ian Witten,et al.  Data Mining , 2000 .

[19]  A. Kennedy,et al.  Parafoveal-on-foveal effects in normal reading , 2005, Vision Research.

[20]  Giuseppe Attardi,et al.  Experiments with a Multilanguage Non-Projective Dependency Parser , 2006, CoNLL.