Paper: A Rudimentary Lexicon and Semantics Help Bootstrap Phoneme Acquisition

ACL ID W14-1620
Title A Rudimentary Lexicon and Semantics Help Bootstrap Phoneme Acquisition
Venue International Conference on Computational Natural Language Learning
Session
Year 2014
Authors

Infants spontaneously discover the rele- vant phonemes of their language without any direct supervision. This acquisition is puzzling because it seems to require the availability of high levels of linguistic structures (lexicon, semantics), that logi- cally suppose the infants having a set of phonemes already. We show how this cir- cularity can be broken by testing, in real- size language corpora, a scenario whereby infants would learn approximate represen- tations at all levels, and then refine them in a mutually constraining way. We start with corpora of spontaneous speech that have been encoded in a varying number of de- tailed context-dependent allophones. We derive, in an unsupervised way, an approx- imate lexicon and a rudimentary seman- tic representation. Despite the fact that all ...