Computational and Robotic Models of Early Language Development

Oudeyer, Pierre-Yves; Kachergis, George; Schueller, William

doi:10.4324/9781315110622-5

Cited by 7 publications

(4 citation statements)

References 81 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Computational analyses suggest that self-directed sampling can vastly simplify the task of learning new words and categories under uncertainty, as long as learners employ strategies that increase the frequency of word meanings that have higher uncertainty (Hidaka et al, 2017;Oudeyer, Kachergis, & Schueller, 2019;Settles, 2012).…”

Section: Introductionmentioning

confidence: 99%

Sampling to learn words: Adults and children sample words that reduce referential ambiguity

Zettersten

Saffran

2020

Developmental Science

View full text Add to dashboard Cite

Why do we seek out new information during learning? One proposal is that information-seeking behavior is driven by uncertainty reduction (e.g., Kidd & Hayden, 2015). At least in some contexts, children may be motivated to gather information to reduce uncertainty after ambiguous or surprising events (Lapidow & Walker, 2020;Schulz & Bonawitz, 2007;Stahl & Feigenson, 2015). For instance, infants and children preferentially seek out information from social partners when they are more uncertain (Goupil et al., 2016) or when confronted with ambiguous or incomplete information (Bazhydai et al., 2020;Hembacher et al., 2020;Vaish et al., 2011). Understanding the nature of children's information-seeking strategies may provide key insights concerning how children are able to rapidly solve complex learning problems across development (Gopnik et al., 2017;Oudeyer & Smith, 2016).A classic problem in word learning is how learners determine the meanings of words in potentially ambiguous situations (Quine, 1960). One solution is that children disambiguate word meanings by tracking co-occurrences of object-label pairs across multiple ambig-

show abstract

Section: Introductionmentioning

confidence: 99%

Sampling to learn words: Adults and children sample words that reduce referential ambiguity

Zettersten

Saffran

2020

Developmental Science

View full text Add to dashboard Cite

show abstract

“…However, according to our knowledge, none of the existing models for joint segmentation, meaning acquisition, and subword unit learning have been tested with real naturalistic input available to language learning infants (see also [5]). Instead, the models (or robots) have used supervised phone recognizer front-ends [12,13,27], or simplified enacted high-quality caregiver speech (e.g., using CAREGIVER corpus [28], as in [14][15][16][17]).…”

Section: Introductionmentioning

confidence: 99%

“…Computational modeling, on the other hand, enables evaluation of theories and models while considering multiple aspects of the learning process simultaneously (see [5] for a recent overview). In this respect, previous models have shown that fully unsupervised acoustic word discovery is challenging due to the variable nature of acoustic speech, even though some recurrent patterns are still learnable (e.g., [6][7][8][9][10]).…”

Section: Introductionmentioning

confidence: 99%

A Computational Model of Early Language Acquisition from Audiovisual Experiences of Young Infants

Räsänen

Khorrami

2019

Interspeech 2019

View full text Add to dashboard Cite

Earlier research has suggested that human infants might use statistical dependencies between speech and non-linguistic multimodal input to bootstrap their language learning before they know how to segment words from running speech. However, feasibility of this hypothesis in terms of real-world infant experiences has remained unclear. This paper presents a step towards a more realistic test of the multimodal bootstrapping hypothesis by describing a neural network model that can learn word segments and their meanings from referentially ambiguous acoustic input. The model is tested on recordings of real infant-caregiver interactions using utterancelevel labels for concrete visual objects that were attended by the infant when caregiver spoke an utterance containing the name of the object, and using random visual labels for utterances during absence of attention. The results show that beginnings of lexical knowledge may indeed emerge from individually ambiguous learning scenarios. In addition, the hidden layers of the network show gradually increasing selectivity to phonetic categories as a function of layer depth, resembling models trained for phone recognition in a supervised manner.

show abstract

“…For studies exploring the contribution of the visual modality, we will refer to Alishahi and Fazly (2010) for models operating on image/caption pairs, or and Nikolaus et al (2022) for models operating on videos -see also Chrupała (2022) for a recent review. Similarly, embodied or socially grounded language learning agents have been proposed in Yu and Ballard (2003), Hermann et al (2017), Lair et al (2019), andOudeyer et al (2019).…”

Section: The Environment Model: From What Is Language Learned?mentioning

confidence: 99%

Artificial neural networks to analyze and simulate language acquisition in children

Lavechin

2023

Preprint

View full text Add to dashboard Cite

Lightweight child-worn recorders that collect audio across an entire day allow for a big-data approach to the study of language development. By collecting the child's production and linguistic environment, these recordings offer us a uniquely naturalistic view of everyday language uses. However, such recordings quickly accumulate thousands of hours of audio and require the use of automatic speech processing algorithms. Besides providing ecologically-valid measures of what children hear and say, these recordings can fuel computational models of early language acquisition with what infants truly hear. This opens up new opportunities for running realistic language learning simulations.A first aspect of my doctoral work is dedicated to developing automatic speech processing algorithms for child-centered long-form recordings. In this manuscript, I first show that current state-of-the-art automatic speech recognition systems fail to capture the complexity of naturalistic speech as found in long-forms. I then present our attempt to propose a free, open-source, and more accurate alternative to the LENA proprietary software, which is currently the standard tool for obtaining automatic analyses of long-forms. Using supervised learning methods, my collaborators and I built a suite of speech processing tools to detect voice activity, identify voice signal sources (child vocalizations, female or male speech), count the number of linguistic units (phonemes, syllables, or words), and estimate the quantity of background noise and reverberation. A second aspect of my doctoral work is dedicated to computational models of early language acquisition. I present a first modeling study showing that self-supervised learning algorithms trained on audiobooks can learn phonetic and lexical aspects of their training language. I then show that the same algorithm trained on ecological long-forms needs inductive biases to learn phonetic aspects of its training language reliably and reflect on whether similar inductive biases may guide language learning in infants. Interestingly, there is no evidence for lexical learning on long-forms, contrary to what has been shown in the literature on more curated data. This series of studies illustrates the importance of considering ecologically-valid input data when modeling language acquisition.

show abstract

Computational and Robotic Models of Early Language Development

Cited by 7 publications

References 81 publications

Sampling to learn words: Adults and children sample words that reduce referential ambiguity

Sampling to learn words: Adults and children sample words that reduce referential ambiguity

A Computational Model of Early Language Acquisition from Audiovisual Experiences of Young Infants

Artificial neural networks to analyze and simulate language acquisition in children

Contact Info

Product

Resources

About