The learning of first and second person pronouns in English: network models and analysis

Although most English-speaking children master the correct use of first and second person pronouns by three years, some children show persistent rever sal errors in which they refer to themselves as you and to others as me. Re cently, such differences have been attributed to the relative availability of overheard speech during the learning process. The present study tested t his proposal with feed-forward neural networks learning these pronouns. Net work learning speed and analysis of their knowledge representations confirm ed the importance of exposure to shifting reference provided by overheard s peech. Errorless pronoun learning was linked to the amount of overheard spe ech, interactions with a greater number of speakers, and prior knowledge of the basic-level kind PERSON.