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

Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics, pages 1073–1083, Baltimore, Maryland, USA, June 23-25 2014. c⃝2014 Association for Computational Linguistics Weak semantic context helps phonetic learning in a model of infant language acquisition Stella Frank sfrank@inf.ed.ac.uk ILCC, School of Informatics University of Edinburgh Edinburgh, EH8 9AB, UK Naomi H. Feldman nhf@umd.edu Department of Linguistics University of Maryland College Park, MD, 20742, USA Sharon Goldwater sgwater@inf.ed.ac.uk ILCC, School of Informatics University of Edinburgh Edinburgh, EH8 9AB, UK Abstract 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 knowledge. 1 Introduction Infants begin learning the phonetic categories of their native language in their first year (Kuhl et al., 1992; Polka and Werker, 1994; Werker and Tees, 1984). In theory, semantic information could offer a valuable cue for phoneme induction1 by helping infants distinguish between minimal pairs, as lin- guists do (Trubetzkoy, 1939). However, due to a widespread assumption that infants do not know the meanings of many words at the age when they are learning phonetic categories (see Swingley, 2009 for a review), most recent models of early phonetic category acquisition have explored the phonetic learning problem in the absence of semantic infor- mation (de Boer and Kuhl, 2003; Dillon et al., 2013; 1The models in this paper do not distinguish between pho- netic and phonemic categories, since they do not capture phonological processes (and there are also none present in our synthetic data). We thus use the terms interchangeably. Feldman et al., 2013a; McMurray et al., 2009; Val- labha et al., 2007). Models without any semantic information are likely to underestimate infants’ ability to learn pho- netic categories. Infants learn language in the wild, and quickly attune to the fact that words have (pos- sibly unknown) meanings. The extent of infants’ semantic knowledge is not yet known, but existing evidence shows that six-month-olds can associate some words with their referents (Bergelson and Swingley, 2012; Tincoff and Jusczyk, 1999, 2012), leverage non-acoustic contexts such as objects or ar- ticulations to distinguish similar sounds (Teinonen et al., 2008; Yeung and Werker, 2009), and map meaning (in the form of objects or images) to new word-forms in some laboratory settings (Friedrich and Friederici, 2011; Gogate and Bahrick, 2001; Shukla et al., 2011). These findings indicate that young infants are sensitive …

Content truncated to 500 words