The role of discourse context in the processing of a flexible word-order language

On-line comprehension studies of flexible word-order languages find that noncanonical ('scrambled') structures induce more difficulty than canonical structures [e.g., Hyona & Hujanen, Q. J. Exp. Psychol. 50A (1997) 841-858], with this difference being attributed to the structural complexity/infrequency of these forms. However, by presenting sentences in isolation, most existing studies have not examined the extent to which processing patterns can be explained by discourse factors. In Finnish, an articleless flexible word-order language with canonical SVO order, word order can be used to encode the given/new distinctions: OVS marks the object as given and the subject as new; SVO is more flexible, being used in multiple contexts. Thus, the observed dispreference for noncanonical orders in previous work may arise from additional presuppositions needed to understand them out of context [cf. Crain & Steedman, Natural Language Parsing, (1985), 320-358]. Two experiments were conducted to examine these issues in Finnish. Experiment I used a self-paced reading task to show that the usual difficulty associated with noncanonical constructions is partially alleviated in the presence of appropriate discourse contexts. In Experiment 2, the eye gaze of listeners was tracked as they heard spoken descriptions of scenes, so as to test whether specific on-line referential processes are involved in SVO/OVS comprehension: Upon hearing an OV... sequence, Finnish listeners should expect the upcoming noun to be discourse-new, whereas an SV... sequence makes no such prediction. The results confirmed these predictions. As compared to SVO, OVS sentences showed anticipatory eye movements to a discourse-new referent at the second noun onset, even before participants had enough acoustic information to recognize this word. Our findings illustrate that in a flexible word-order language, a noncanonical order can result in anticipatory processes regarding the discourse status of a yet-to-be-heard constituent. (C) 2004 Elsevier B.V. All rights reserved.