Learning Words and Their Meanings from Unsegmented Child-directed Speech

Most work on language acquisition treats word segmentation--the identification of linguistic segments from continuous speech-and word learning--the mapping of those segments to meanings--as separate problems. These two abilities develop in parallel, however, raising the question of whether they might interact. To explore the question, we present a new Bayesian segmentation model that incorporates aspects of word learning and compare it to a model that ignores word meanings. The model that learns word meanings proposes more adult-like segmentations for the meaning-bearing words. This result suggests that the non-linguistic context may supply important information for learning word segmentations as well as word meanings.

• Type: Journal
• Year: 2010
• Where: NAACL
• Authors: Bevan K. Jones, Mark Johnson, Michael C. Frank
• Keywords: Computational Linguistics, Continuous Speech-and Word, NAACL 2010, Word Meanings, Word Segmentations