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

Frank, Stella; Feldman, Naomi H.; Goldwater, Sharon

doi:10.3115/v1/p14-1101

Cited by 14 publications

(19 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The results showed that information from the derived lexicon and semantics, albeit very rudimentary, help discriminate between allophonic and phonemic contrasts, with a high degree of accuracy. Thus, this works strongly support the claim that the lexicon and semantics play a role in the refinement of the phonemic inventory (Feldman et al, 2013a;Frank et al, 2014), and, interestingly, that this role remains functional under more realistic assumptions (unsupervised word segmentation, and bottom-up inferred semantics). We also found that lexical and semantic information were not redundant and could be usefully combined, the former being more resistant to the scarcity of data and variation, and the latter being more resistant to segmentation errors.…”

Section: General Discussion and Future Worksupporting

confidence: 82%

A Rudimentary Lexicon and Semantics Help Bootstrap Phoneme Acquisition

Fourtassi¹,

Dupoux²

2014

Proceedings of the Eighteenth Conference on Computational Natural Language Learning

View full text Add to dashboard Cite

Infants spontaneously discover the relevant 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 logically suppose the infants having a set of phonemes already. We show how this circularity can be broken by testing, in realsize language corpora, a scenario whereby infants would learn approximate representations 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 detailed context-dependent allophones. We derive, in an unsupervised way, an approximate lexicon and a rudimentary semantic representation. Despite the fact that all these representations are poor approximations of the ground truth, they help reorganize the fine grained categories into phoneme-like categories with a high degree of accuracy.

show abstract

Section: General Discussion and Future Worksupporting

confidence: 82%

A Rudimentary Lexicon and Semantics Help Bootstrap Phoneme Acquisition

Fourtassi¹,

Dupoux²

2014

Proceedings of the Eighteenth Conference on Computational Natural Language Learning

View full text Add to dashboard Cite

show abstract

“…Initial modeling work investigating the feasibility of learning phonetic categories through distributional learning sidestepped the lack of invariance and phonetic category segmentation problems by focusing on drastically simplified learning conditions (40)(41)(42)(43)(44)(45), but subsequent studies considering more realistic variability have failed to learn phonetic categories accurately (9,12,14,15,46,47) (see Supplementary Discussion 1).…”

Section: R a F Tmentioning

confidence: 99%

“…the degree of vocal tract opening at a constriction-and some accounts remain noncommittal (7). natural speech (9,12,14,15,43,(46)(47)(48). Attempts to extend 101 them to more realistic learning conditions have failed (13,16) 102 (see Supplementary Discussion 1).…”

Section: R a F Tmentioning

confidence: 99%

Early phonetic learning without phonetic categories: Insights from large-scale simulations on realistic input

Schatz

Feldman

Goldwater

et al. 2021

Proc. Natl. Acad. Sci. U.S.A.

Self Cite

156

View full text Add to dashboard Cite

Before they even speak, infants become attuned to the sounds of the language(s) they hear, processing native phonetic contrasts more easily than nonnative ones. For example, between 6 to 8 mo and 10 to 12 mo, infants learning American English get better at distinguishing English and [l], as in “rock” vs. “lock,” relative to infants learning Japanese. Influential accounts of this early phonetic learning phenomenon initially proposed that infants group sounds into native vowel- and consonant-like phonetic categories—like and [l] in English—through a statistical clustering mechanism dubbed “distributional learning.” The feasibility of this mechanism for learning phonetic categories has been challenged, however. Here, we demonstrate that a distributional learning algorithm operating on naturalistic speech can predict early phonetic learning, as observed in Japanese and American English infants, suggesting that infants might learn through distributional learning after all. We further show, however, that, contrary to the original distributional learning proposal, our model learns units too brief and too fine-grained acoustically to correspond to phonetic categories. This challenges the influential idea that what infants learn are phonetic categories. More broadly, our work introduces a mechanism-driven approach to the study of early phonetic learning, together with a quantitative modeling framework that can handle realistic input. This allows accounts of early phonetic learning to be linked to concrete, systematic predictions regarding infants’ attunement.

show abstract

“…Notice that this distribution needs to be defined over an infinite set of possible expansions, since the learner does not know ahead of time which expansions will be needed for their language. Recent probabilistic models of language acquisition , 2010Feldman, Griffiths, Goldwater, & Morgan, 2013;S. Frank, Feldman, & Goldwater, 2014;Goldwater et al, 2009), have demonstrated that Dirichlet Processes can be used to successfully model such infinite distributions, so we adopt that approach here.…”

Section: The Probabilistic Modelmentioning

confidence: 99%

Bootstrapping language acquisition

et al. 2017

Self Cite

View full text Add to dashboard Cite

The semantic bootstrapping hypothesis proposes that children acquire their native language through exposure to sentences of the language paired with structured representations of their meaning, whose component substructures can be associated with words and syntactic structures used to express these concepts. The child's task is then to learn a language-specific grammar and lexicon based on (probably contextually ambiguous, possibly somewhat noisy) pairs of sentences and their meaning representations (logical forms). Starting from these assumptions, we develop a Bayesian probabilistic account of semantically bootstrapped first-language acquisition in the child, based on techniques from computational parsing and interpretation of unrestricted text. Our learner jointly models (a) word learning: the mapping between components of the given sentential meaning and lexical words (or phrases) of the language, and (b) syntax learning: the projection of lexical elements onto sentences by universal construction-free syntactic rules. Using an incremental learning algorithm, we apply the model to a dataset of real syntactically complex child-directed utterances and (pseudo) logical forms, the latter including contextually plausible but irrelevant distractors. Taking the Eve section of the CHILDES corpus as input, the model simulates several well-documented phenomena from the developmental literature. In particular, the model exhibits syntactic bootstrapping effects (in which previously learned constructions facilitate the learning of novel words), sudden jumps in learning without explicit parameter setting, acceleration of word-learning (the "vocabulary spurt"), an initial bias favoring the learning of nouns over verbs, and one-shot learning of words and their meanings. The learner thus demonstrates how statistical learning over structured representations can provide a unified account for these seemingly disparate phenomena.

show abstract

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

Cited by 14 publications

References 41 publications

A Rudimentary Lexicon and Semantics Help Bootstrap Phoneme Acquisition

A Rudimentary Lexicon and Semantics Help Bootstrap Phoneme Acquisition

Early phonetic learning without phonetic categories: Insights from large-scale simulations on realistic input

Bootstrapping language acquisition

Contact Info

Product

Resources

About