A connectionist account of Spanish determiner production

Abstract

Evidence from experimental studies of Spanish children's production of determiners reveals that they pay more attention to phonological cues present in nouns than to natural semantics when assigning gender to determiners (Pérez-Pereira, 1991). This experimental work also demonstrated that Spanish children are more likely to produce the correct determiner when given a noun with phonological cues which suggest it is masculine, and more likely to assign masculine gender to nouns with ambiguous cues. In this paper, we investigate the phonological cues available to children and seek to explore the possibility that differential frequency in the linguistic input explains the priority given to masculine forms when children are faced with ambiguous novel items. A connectionist model of determiner production was incrementally trained on a lexicon of determiner-noun phrases taken from parental speech in a longitudinal study of a child between the ages of 1;7 and 2;11 (López Ornat, Fernandez, Gallo & Mariscal, 1994) preserving the type and token frequency information. An analysis of the database of parental productions revealed that while regular feminine nouns were slightly more frequent than regular masculine nouns, irregular masculine nouns outnumbered irregular feminine nouns by roughly 2 to 1. On the basis of this, we made the prediction that as the training lexicon builds up, the network will perform better overall on masculine determiners than would be predicted from their forms alone and will tend to assign masculine gender to ambiguous novel nouns in a test set. The findings indicate that, at least in the case of Spanish gender agreement for determiners and nouns, a general associative learning mechanism can account for important characteristics of the acquisition process seen in children.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 25 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.