We propose that machine-learned computational models (MLCMs), in which the model parameters and perhaps even structure are learned from data, can complement extant approaches to the study of text and discourse. Such models are particularly useful when theoretical understanding is insufficient, when the data are rife with nonlinearities and…

The Simple View of Reading (SVR) model posits that reading is the product of word decoding and language comprehension and that oral language (listening) comprehension is the best predictor of reading comprehension once word-decoding skill has been established. The SVR model also proposes that there are good readers and three types of poor…

It is often assumed that graphemes are a crucial level of orthographic representation above letters. Current connectionist models of reading, however, do not address how the mapping from letters to graphemes is learned. One major challenge for computational modeling is therefore developing a model that learns this mapping and can assign the…

Texts are typically classified by researchers into one of two genres: narrative or expository. Narrative texts are meant to entertain (e.g., fictional novels and stories), while expository texts are meant to educate (e.g., text books and empirical articles) (Weaver & Bryant, 1995). One problem with this simple method for categorizing texts is that…

The problems of modeling a process as complex as reading are discussed, including such factors as the lack of agreement surrounding definitions of modeling, varying levels of rigor within and between models, the disjunctive categories within which models fall, and the difficulty of synthesis across fields which employ very different technical…

A brief review of reading research studies is presented, and the need for unifying reading theories is discussed. It is noted that speed training, comprehension skills, and vocabulary development compose the main areas of reading research and that most of the studies are taxonomic and do not give accurate explanations or allow for predictions and…