Two experiments investigated the factors that govern children's use of singular and plural forms of count nouns. Experiment 1 used an elicited production task to investigate whether children use referential and/or syntactic information to determine the form of the count nouns when the two sources of information conflict (e.g. each x, one of the xs), as well as when the linguistic context does not provide any constraint on the form of the noun, but the referential context does (e.g. the dog(s)). 48 children, aged 1;9 to 5;6, participated in Experiment 1. The results suggest that even the youngest children can use referential information when relevant, and can ignore referential information when necessary. Children did, however, show a tendency to make errors with the quantifier each in non-partitive contexts, and a developmental trend was found in the use and avoidance of each in non-partitive contexts. Experiment 2, an act out task, provided a second test of the role of referential information in children's use of singular and plural forms. Experiment 2 also investigated children's appreciation of the semantic distinction between each and all. 48 children, aged 1;8 to 5;6, participated in Experiment 2. A weak sensitivity to the semantic distinction between the two quantifiers as well as the syntactic context in which they were used was found. The results of the two experiments suggest that, from the beginning, children approach the task of learning when to use singular and plural forms of count nouns on the basis of morpho-syntactic, semantic, and referential properties of utterances, rather than initially using only one of these types of information.