@article{PreglaLissonHernandezVasishthetal.2021,
  author    = {Pregla, Dorothea and Liss{\´o}n Hern{\´a}ndez, Paula J. and Vasishth, Shravan and Burchert, Frank and Stadie, Nicole},
  title     = {Variability in sentence comprehension in aphasia in German},
  series = {Brain \& language : a journal of the neurobiology of language},
  volume    = {222},
  journal   = {Brain \& language : a journal of the neurobiology of language},
  publisher = {Elsevier},
  address   = {Amsterdam},
  issn      = {0093-934X},
  doi       = {10.1016/j.bl.2021.105008},
  pages     = {20},
  year      = {2021},
  abstract  = {An important aspect of aphasia is the observation of behavioral variability between and within individual participants. Our study addresses variability in sentence comprehension in German, by testing 21 individuals with aphasia and a control group and involving (a) several constructions (declarative sentences, relative clauses and control structures with an overt pronoun or PRO), (b) three response tasks (object manipulation, sentence-picture matching with/without self-paced listening), and (c) two test phases (to investigate test-retest performance). With this systematic, large-scale study we gained insights into variability in sentence comprehension. We found that the size of syntactic effects varied both in aphasia and in control participants. Whereas variability in control participants led to systematic changes, variability in individuals with aphasia was unsystematic across test phases or response tasks. The persistent occurrence of canonicity and interference effects across response tasks and test phases, however, shows that the performance is systematically influenced by syntactic complexity.},
  language  = {en}
}
@article{SmithVasishth2020,
  author    = {Smith, Garrett and Vasishth, Shravan},
  title     = {A principled approach to feature selection in models of sentence processing},
  series = {Cognitive science : a multidisciplinary journal of anthropology, artificial intelligence, education, linguistics, neuroscience, philosophy, psychology ; journal of the Cognitive Science Society},
  volume    = {44},
  journal   = {Cognitive science : a multidisciplinary journal of anthropology, artificial intelligence, education, linguistics, neuroscience, philosophy, psychology ; journal of the Cognitive Science Society},
  number    = {12},
  publisher = {Wiley},
  address   = {Hoboken},
  issn      = {0364-0213},
  doi       = {10.1111/cogs.12918},
  pages     = {25},
  year      = {2020},
  abstract  = {Among theories of human language comprehension, cue-based memory retrieval has proven to be a useful framework for understanding when and how processing difficulty arises in the resolution of long-distance dependencies. Most previous work in this area has assumed that very general retrieval cues like [+subject] or [+singular] do the work of identifying (and sometimes misidentifying) a retrieval target in order to establish a dependency between words. However, recent work suggests that general, handpicked retrieval cues like these may not be enough to explain illusions of plausibility (Cunnings \& Sturt, 2018), which can arise in sentences like The letter next to the porcelain plate shattered. Capturing such retrieval interference effects requires lexically specific features and retrieval cues, but handpicking the features is hard to do in a principled way and greatly increases modeler degrees of freedom. To remedy this, we use well-established word embedding methods for creating distributed lexical feature representations that encode information relevant for retrieval using distributed retrieval cue vectors. We show that the similarity between the feature and cue vectors (a measure of plausibility) predicts total reading times in Cunnings and Sturt's eye-tracking data. The features can easily be plugged into existing parsing models (including cue-based retrieval and self-organized parsing), putting very different models on more equal footing and facilitating future quantitative comparisons.},
  language  = {en}
}
@article{LaurinavichyuteYadavVasishth2022,
  author    = {Laurinavichyute, Anna and Yadav, Himanshu and Vasishth, Shravan},
  title     = {Share the code, not just the data},
  series = {Journal of memory and language},
  volume    = {125},
  journal   = {Journal of memory and language},
  publisher = {Elsevier},
  address   = {San Diego},
  issn      = {0749-596X},
  doi       = {10.1016/j.jml.2022.104332},
  pages     = {12},
  year      = {2022},
  abstract  = {In 2019 the Journal of Memory and Language instituted an open data and code policy; this policy requires that, as a rule, code and data be released at the latest upon publication. How effective is this policy? We compared 59 papers published before, and 59 papers published after, the policy took effect. After the policy was in place, the rate of data sharing increased by more than 50\%. We further looked at whether papers published under the open data policy were reproducible, in the sense that the published results should be possible to regenerate given the data, and given the code, when code was provided. For 8 out of the 59 papers, data sets were inaccessible. The reproducibility rate ranged from 34\% to 56\%, depending on the reproducibility criteria. The strongest predictor of whether an attempt to reproduce would be successful is the presence of the analysis code: it increases the probability of reproducing reported results by almost 40\%. We propose two simple steps that can increase the reproducibility of published papers: share the analysis code, and attempt to reproduce one's own analysis using only the shared materials.},
  language  = {en}
}
@misc{StoneVasishthMalsburg2022,
  author    = {Stone, Kate and Vasishth, Shravan and Malsburg, Titus von der},
  title     = {Does entropy modulate the prediction of German long-distance verb particles?},
  series = {Zweitver{\"o}ffentlichungen der Universit{\"a}t Potsdam : Humanwissenschaftliche Reihe},
  journal   = {Zweitver{\"o}ffentlichungen der Universit{\"a}t Potsdam : Humanwissenschaftliche Reihe},
  publisher = {Universit{\"a}tsverlag Potsdam},
  address   = {Potsdam},
  issn      = {1866-8364},
  doi       = {10.25932/publishup-56231},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-562312},
  pages     = {1 -- 25},
  year      = {2022},
  abstract  = {In this paper we examine the effect of uncertainty on readers' predictions about meaning. In particular, we were interested in how uncertainty might influence the likelihood of committing to a specific sentence meaning. We conducted two event-related potential (ERP) experiments using particle verbs such as turn down and manipulated uncertainty by constraining the context such that readers could be either highly certain about the identity of a distant verb particle, such as turn the bed […] down, or less certain due to competing particles, such as turn the music […] up/down. The study was conducted in German, where verb particles appear clause-finally and may be separated from the verb by a large amount of material. We hypothesised that this separation would encourage readers to predict the particle, and that high certainty would make prediction of a specific particle more likely than lower certainty. If a specific particle was predicted, this would reflect a strong commitment to sentence meaning that should incur a higher processing cost if the prediction is wrong. If a specific particle was less likely to be predicted, commitment should be weaker and the processing cost of a wrong prediction lower. If true, this could suggest that uncertainty discourages predictions via an unacceptable cost-benefit ratio. However, given the clear predictions made by the literature, it was surprisingly unclear whether the uncertainty manipulation affected the two ERP components studied, the N400 and the PNP. Bayes factor analyses showed that evidence for our a priori hypothesised effect sizes was inconclusive, although there was decisive evidence against a priori hypothesised effect sizes larger than 1μV for the N400 and larger than 3μV for the PNP. We attribute the inconclusive finding to the properties of verb-particle dependencies that differ from the verb-noun dependencies in which the N400 and PNP are often studied.},
  language  = {en}
}
@article{StoneVasishthMalsburg2022,
  author    = {Stone, Kate and Vasishth, Shravan and Malsburg, Titus von der},
  title     = {Does entropy modulate the prediction of German long-distance verb particles?},
  series = {PLOS ONE},
  journal   = {PLOS ONE},
  publisher = {PLOS ONE},
  address   = {San Francisco, California, US},
  issn      = {1932-6203},
  doi       = {10.1371/journal.pone.0267813},
  pages     = {1 -- 25},
  year      = {2022},
  abstract  = {In this paper we examine the effect of uncertainty on readers' predictions about meaning. In particular, we were interested in how uncertainty might influence the likelihood of committing to a specific sentence meaning. We conducted two event-related potential (ERP) experiments using particle verbs such as turn down and manipulated uncertainty by constraining the context such that readers could be either highly certain about the identity of a distant verb particle, such as turn the bed […] down, or less certain due to competing particles, such as turn the music […] up/down. The study was conducted in German, where verb particles appear clause-finally and may be separated from the verb by a large amount of material. We hypothesised that this separation would encourage readers to predict the particle, and that high certainty would make prediction of a specific particle more likely than lower certainty. If a specific particle was predicted, this would reflect a strong commitment to sentence meaning that should incur a higher processing cost if the prediction is wrong. If a specific particle was less likely to be predicted, commitment should be weaker and the processing cost of a wrong prediction lower. If true, this could suggest that uncertainty discourages predictions via an unacceptable cost-benefit ratio. However, given the clear predictions made by the literature, it was surprisingly unclear whether the uncertainty manipulation affected the two ERP components studied, the N400 and the PNP. Bayes factor analyses showed that evidence for our a priori hypothesised effect sizes was inconclusive, although there was decisive evidence against a priori hypothesised effect sizes larger than 1μV for the N400 and larger than 3μV for the PNP. We attribute the inconclusive finding to the properties of verb-particle dependencies that differ from the verb-noun dependencies in which the N400 and PNP are often studied.},
  language  = {en}
}
@article{SchadVasishthHohensteinetal.2020,
  author    = {Schad, Daniel and Vasishth, Shravan and Hohenstein, Sven and Kliegl, Reinhold},
  title     = {How to capitalize on a priori contrasts in linear (mixed) models},
  series = {Journal of memory and language},
  volume    = {110},
  journal   = {Journal of memory and language},
  publisher = {Elsevier},
  address   = {San Diego},
  issn      = {0749-596X},
  doi       = {10.1016/j.jml.2019.104038},
  pages     = {40},
  year      = {2020},
  abstract  = {Factorial experiments in research on memory, language, and in other areas are often analyzed using analysis of variance (ANOVA). However, for effects with more than one numerator degrees of freedom, e.g., for experimental factors with more than two levels, the ANOVA omnibus F-test is not informative about the source of a main effect or interaction. Because researchers typically have specific hypotheses about which condition means differ from each other, a priori contrasts (i.e., comparisons planned before the sample means are known) between specific conditions or combinations of conditions are the appropriate way to represent such hypotheses in the statistical model. Many researchers have pointed out that contrasts should be "tested instead of, rather than as a supplement to, the ordinary 'omnibus' F test" (Hays, 1973, p. 601). In this tutorial, we explain the mathematics underlying different kinds of contrasts (i.e., treatment, sum, repeated, polynomial, custom, nested, interaction contrasts), discuss their properties, and demonstrate how they are applied in the R System for Statistical Computing (R Core Team, 2018). In this context, we explain the generalized inverse which is needed to compute the coefficients for contrasts that test hypotheses that are not covered by the default set of contrasts. A detailed understanding of contrast coding is crucial for successful and correct specification in linear models (including linear mixed models). Contrasts defined a priori yield far more useful confirmatory tests of experimental hypotheses than standard omnibus F-tests. Reproducible code is available from https://osf.io/7ukf6/.},
  language  = {en}
}
@article{RabeChandraKruegeletal.2021,
  author    = {Rabe, Maximilian Michael and Chandra, Johan and Kr{\"u}gel, Andr{\´e} and Seelig, Stefan A. and Vasishth, Shravan and Engbert, Ralf},
  title     = {A bayesian approach to dynamical modeling of eye-movement control in reading of normal, mirrored, and scrambled texts},
  series = {Psychological Review},
  volume    = {128},
  journal   = {Psychological Review},
  number    = {5},
  publisher = {American Psychological Association},
  address   = {Washington},
  issn      = {0033-295X},
  doi       = {10.1037/rev0000268},
  pages     = {803 -- 823},
  year      = {2021},
  abstract  = {In eye-movement control during reading, advanced process-oriented models have been developed to reproduce behavioral data. So far, model complexity and large numbers of model parameters prevented rigorous statistical inference and modeling of interindividual differences. Here we propose a Bayesian approach to both problems for one representative computational model of sentence reading (SWIFT; Engbert et al., Psychological Review, 112, 2005, pp. 777-813). We used experimental data from 36 subjects who read the text in a normal and one of four manipulated text layouts (e.g., mirrored and scrambled letters). The SWIFT model was fitted to subjects and experimental conditions individually to investigate between- subject variability. Based on posterior distributions of model parameters, fixation probabilities and durations are reliably recovered from simulated data and reproduced for withheld empirical data, at both the experimental condition and subject levels. A subsequent statistical analysis of model parameters across reading conditions generates model-driven explanations for observable effects between conditions.},
  language  = {en}
}
@article{MaetzigVasishthEngelmannetal.2018,
  author    = {M{\"a}tzig, Paul and Vasishth, Shravan and Engelmann, Felix and Caplan, David and Burchert, Frank},
  title     = {A computational investigation of sources of variability in sentence comprehension difficulty in aphasia},
  series = {Topics in cognitive science},
  volume    = {10},
  journal   = {Topics in cognitive science},
  number    = {1},
  publisher = {Wiley},
  address   = {Hoboken},
  issn      = {1756-8757},
  doi       = {10.1111/tops.12323},
  pages     = {161 -- 174},
  year      = {2018},
  abstract  = {We present a computational evaluation of three hypotheses about sources of deficit in sentence comprehension in aphasia: slowed processing, intermittent deficiency, and resource reduction. The ACT-R based Lewis and Vasishth (2005) model is used to implement these three proposals. Slowed processing is implemented as slowed execution time of parse steps; intermittent deficiency as increased random noise in activation of elements in memory; and resource reduction as reduced spreading activation. As data, we considered subject vs. object relative sentences, presented in a self-paced listening modality to 56 individuals with aphasia (IWA) and 46 matched controls. The participants heard the sentences and carried out a picture verification task to decide on an interpretation of the sentence. These response accuracies are used to identify the best parameters (for each participant) that correspond to the three hypotheses mentioned above. We show that controls have more tightly clustered (less variable) parameter values than IWA; specifically, compared to controls, among IWA there are more individuals with slow parsing times, high noise, and low spreading activation. We find that (a) individual IWA show differential amounts of deficit along the three dimensions of slowed processing, intermittent deficiency, and resource reduction, (b) overall, there is evidence for all three sources of deficit playing a role, and (c) IWA have a more variable range of parameter values than controls. An important implication is that it may be meaningless to talk about sources of deficit with respect to an abstract verage IWA; the focus should be on the individual's differential degrees of deficit along different dimensions, and on understanding the causes of variability in deficit between participants.},
  language  = {en}
}
@article{NicenboimVasishth2018,
  author    = {Nicenboim, Bruno and Vasishth, Shravan},
  title     = {Models of retrieval in sentence comprehension},
  series = {Journal of memory and language},
  volume    = {99},
  journal   = {Journal of memory and language},
  publisher = {Elsevier},
  address   = {San Diego},
  issn      = {0749-596X},
  doi       = {10.1016/j.jml.2017.08.004},
  pages     = {1 -- 34},
  year      = {2018},
  abstract  = {Research on similarity-based interference has provided extensive evidence that the formation of dependencies between non-adjacent words relies on a cue-based retrieval mechanism. There are two different models that can account for one of the main predictions of interference, i.e., a slowdown at a retrieval site, when several items share a feature associated with a retrieval cue: Lewis and Vasishth's (2005) activation-based model and McElree's (2000) direct-access model. Even though these two models have been used almost interchangeably, they are based on different assumptions and predict differences in the relationship between reading times and response accuracy. The activation-based model follows the assumptions of the ACT-R framework, and its retrieval process behaves as a lognormal race between accumulators of evidence with a single variance. Under this model, accuracy of the retrieval is determined by the winner of the race and retrieval time by its rate of accumulation. In contrast, the direct-access model assumes a model of memory where only the probability of retrieval can be affected, while the retrieval time is drawn from the same distribution; in this model, differences in latencies are a by-product of the possibility of backtracking and repairing incorrect retrievals. We implemented both models in a Bayesian hierarchical framework in order to evaluate them and compare them. The data show that correct retrievals take longer than incorrect ones, and this pattern is better fit under the direct-access model than under the activation-based model. This finding does not rule out the possibility that retrieval may be behaving as a race model with assumptions that follow less closely the ones from the ACT-R framework. By introducing a modification of the activation model, i.e., by assuming that the accumulation of evidence for retrieval of incorrect items is not only slower but noisier (i.e., different variances for the correct and incorrect items), the model can provide a fit as good as the one of the direct-access model. This first ever computational evaluation of alternative accounts of retrieval processes in sentence processing opens the way for a broader investigation of theories of dependency completion.},
  language  = {en}
}
@article{WuKaiserVasishth2017,
  author    = {Wu, Fuyun and Kaiser, Elsi and Vasishth, Shravan},
  title     = {Effects of early cues on the processing of chinese relative clauses},
  series = {Cognitive science : a multidisciplinary journal of anthropology, artificial intelligence, education, linguistics, neuroscience, philosophy, psychology ; journal of the Cognitive Science Society},
  volume    = {42},
  journal   = {Cognitive science : a multidisciplinary journal of anthropology, artificial intelligence, education, linguistics, neuroscience, philosophy, psychology ; journal of the Cognitive Science Society},
  publisher = {Wiley},
  address   = {Hoboken},
  issn      = {0364-0213},
  doi       = {10.1111/cogs.12551},
  pages     = {1101 -- 1133},
  year      = {2017},
  abstract  = {We used Chinese prenominal relative clauses (RCs) to test the predictions of two competing accounts of sentence comprehension difficulty: the experience-based account of Levy () and the Dependency Locality Theory (DLT; Gibson, ). Given that in Chinese RCs, a classifier and/or a passive marker BEI can be added to the sentence-initial position, we manipulated the presence/absence of classifiers and the presence/absence of BEI, such that BEI sentences were passivized subject-extracted RCs, and no-BEI sentences were standard object-extracted RCs. We conducted two self-paced reading experiments, using the same critical stimuli but somewhat different filler items. Reading time patterns from both experiments showed facilitative effects of BEI within and beyond RC regions, and delayed facilitative effects of classifiers, suggesting that cues that occur before a clear signal of an upcoming RC can help Chinese comprehenders to anticipate RC structures. The data patterns are not predicted by the DLT, but they are consistent with the predictions of experience-based theories.},
  language  = {en}
}