Paper: Weak semantic context helps phonetic learning in a model of infant language acquisition

ACL ID P14-1101
Title Weak semantic context helps phonetic learning in a model of infant language acquisition
Venue Annual Meeting of the Association of Computational Linguistics
Session Main Conference
Year 2014
Authors

Learning phonetic categories is one of the first steps to learning a language, yet is hard to do using only distributional phonetic in- formation. Semantics could potentially be useful, since words with different mean- ings have distinct phonetics, but it is un- clear how many word meanings are known to infants learning phonetic categories. We show that attending to a weaker source of semantics, in the form of a distribution over topics in the current context, can lead to improvements in phonetic category learn- ing. In our model, an extension of a pre- vious model of joint word-form and pho- netic category inference, the probability of word-forms is topic-dependent, enabling the model to find significantly better pho- netic vowel categories and word-forms than a model with no semantic kno...