Sentence reading: Do we make use of orthographic cues in homophones?

Starting from the finding that currently phonological models of visual word processing predominate, we examined what happened when important morphological information is disclosed in the orthography but not in the phonology. To do so, we made use of a peculiarity in Dutch. In this language, some forms of the present and the past tense of verbs are homophones or homographs. This allowed us to look at the power of orthographic and phonological cues to derive the tense of the verb. Two experiments showed that orthographic cues alone suffice to recover the tense of the verb, and that this recovery does not take more time than tense recovery on the basis of a combination of orthographic and phonological cues. On the basis of these results, we conclude that orthographic cues in homophones are very efficient during silent reading, Our findings, however, do not allow us to conclude whether this is due to a direct route from orthography to meaning, or to a specialised, morpho-syntactic back-up strategy elicited by certain sequences of letters. (C) 2000 Elsevier Science B.V. All rights reserved.