Computational models have shown that purely statistical knowledge about words' linguistic contexts is sufficient to learn many properties of words, including syntactic and semantic category. For example, models can infer that "postman" and "mailman" are semantically similar because they have quantitatively similar patterns of…

We investigated the associations between teacher-rated and direct assessments of early elementary students' speech and language skills to explore whether using teachers as primary screeners yielded assessment data that reliably identified young students with language difficulties who many need a more comprehensive evaluation. We assessed first-…