Word skipping in Chinese reading: The role of high-frequency preview and syntactic felicity

Abstract

Two experiments are reported to investigate whether Chinese readers skip a high-frequency preview word without taking the syntax of the sentence context into account. In Experiment 1, we manipulated target word syntactic category, frequency, and preview using the boundary paradigm (Rayner, 1975). For high-frequency verb targets, there were identity and pseudocharacter previews alongside a low-frequency noun preview. For low-frequency verb targets, there were identity and pseudocharacter previews alongside a high-frequency noun preview. Results showed that for high-frequency targets, skipping rates were higher for identical previews compared with the syntactically infelicitous alternative low-frequency preview and pseudocharacter previews, however for low-frequency targets, skipping rates were higher for high-frequency previews (even when they were syntactically infelicitous) compared with the other 2 previews. Furthermore, readers were more likely to skip the target when they had a high-frequency, syntactically felicitous preview compared to a high-frequency, syntactically infelicitous preview. The pattern of felicity effects was statistically robust when readers launched saccades from near the target. In Experiment 2, we assessed whether display change awareness influenced the patterns of results in Experiment 1. Results showed that the overall patterns held in Experiment 2 regardless of some readers being more likely to be aware of the display change than others. These results suggest that decisions to skip a word in Chinese reading are primarily based on parafoveal word familiarity, though the syntactic felicity of a parafoveal word also exerts a robust influence for high-frequency previews. (PsycInfo Database Record (c) 2020 APA, all rights reserved).

Figure 1

An example set of sentences from the present study. The vertical black line represents the position of the invisible boundary. When readers’ eyes crossed the boundary, the preview changed to the target word (the target and preview words are in bold). English translation for the verb sentence version is “Aunty Wang has been relying on selling/spinning cotton for money to support her family,” and for the noun sentence version is “My sister bought the cakes/apricots that were popular with all of us.”

Figure 2

Skipping probability as a function of launch site distance (a median split analyses was applied to the launch site data). Note, Alternative preview refers to syntactically infelicitous alternative preview.