The surprisal of a word on a probabilistic grammar constitutes a promising
complexity metric for human sentence comprehension difficulty. Using two
different grammar types, surprisal is shown to have an effect on fixation durations
and regression probabilities in a sample of German readers’ eye movements, the
Potsdam Sentence Corpus. A linear mixed-effects model was used to quantify the
effect of surprisal while taking into account unigram frequency and bigram frequency
(transitional probability), word length, and empirically-derived word predictability;
the so-called “early” and “late” measures of processing difficulty both showed
an effect of surprisal. Surprisal is also shown to have a small but statistically
non-significant effect on empirically-derived predictability itself. This work thus
demonstrates the importance of including parsing costs as a predictor of comprehension difficulty in models of reading, and suggests that a simple identification
of syntactic parsing costs with early measures and late measures with durations of
post-syntactic events may be difficult to uphold.
%0 Journal Article
%1 BostonEtAl2008
%A Boston, Marisa F.
%A Hale, John T.
%A Kliegl, Reinhold
%A Patil, Umesh
%A Vasishth, Shravan
%D 2008
%J Journal of Eye Movement Research
%K corpusanalysis eyemovements reading retrieval surprisal
%N 1
%P 1--12
%T Parsing costs as predictors of reading difficulty: An evaluation using the Potsdam Sentence Corpus
%U http://scholar.google.com/scholar.bib?q=info:PsvBDm6rJugJ:scholar.google.com/&output=citation&hl=de&as_sdt=0,5&ct=citation&cd=0
%V 2
%X The surprisal of a word on a probabilistic grammar constitutes a promising
complexity metric for human sentence comprehension difficulty. Using two
different grammar types, surprisal is shown to have an effect on fixation durations
and regression probabilities in a sample of German readers’ eye movements, the
Potsdam Sentence Corpus. A linear mixed-effects model was used to quantify the
effect of surprisal while taking into account unigram frequency and bigram frequency
(transitional probability), word length, and empirically-derived word predictability;
the so-called “early” and “late” measures of processing difficulty both showed
an effect of surprisal. Surprisal is also shown to have a small but statistically
non-significant effect on empirically-derived predictability itself. This work thus
demonstrates the importance of including parsing costs as a predictor of comprehension difficulty in models of reading, and suggests that a simple identification
of syntactic parsing costs with early measures and late measures with durations of
post-syntactic events may be difficult to uphold.
@article{BostonEtAl2008,
abstract = {The surprisal of a word on a probabilistic grammar constitutes a promising
complexity metric for human sentence comprehension difficulty. Using two
different grammar types, surprisal is shown to have an effect on fixation durations
and regression probabilities in a sample of German readers’ eye movements, the
Potsdam Sentence Corpus. A linear mixed-effects model was used to quantify the
effect of surprisal while taking into account unigram frequency and bigram frequency
(transitional probability), word length, and empirically-derived word predictability;
the so-called “early” and “late” measures of processing difficulty both showed
an effect of surprisal. Surprisal is also shown to have a small but statistically
non-significant effect on empirically-derived predictability itself. This work thus
demonstrates the importance of including parsing costs as a predictor of comprehension difficulty in models of reading, and suggests that a simple identification
of syntactic parsing costs with early measures and late measures with durations of
post-syntactic events may be difficult to uphold.},
added-at = {2011-05-18T14:05:32.000+0200},
author = {Boston, Marisa F. and Hale, John T. and Kliegl, Reinhold and Patil, Umesh and Vasishth, Shravan},
biburl = {https://www.bibsonomy.org/bibtex/2ed8d8b563e92df7af3847f1ba05f3865/tmalsburg},
interhash = {68a20783192313ac792e8319a01a2eea},
intrahash = {ed8d8b563e92df7af3847f1ba05f3865},
journal = {Journal of Eye Movement Research},
keywords = {corpusanalysis eyemovements reading retrieval surprisal},
number = 1,
pages = {1--12},
timestamp = {2011-05-18T14:05:32.000+0200},
title = {Parsing costs as predictors of reading difficulty: An evaluation using the Potsdam Sentence Corpus},
url = {http://scholar.google.com/scholar.bib?q=info:PsvBDm6rJugJ:scholar.google.com/&output=citation&hl=de&as_sdt=0,5&ct=citation&cd=0},
volume = 2,
year = 2008
}