mlsanityData to 14 Oct 2026

Cognitive Science in the era of Artificial Intelligence: A roadmap for reverse-engineering the infant language-learner

arXiv 1607.08723 ↗First posted 29 Jul 2016cs.CL cs.AI cs.LGcited by 68

Not on the map. Why?

Abstract (arXiv)

During their first years of life, infants learn the language(s) of their environment at an amazing speed despite large cross cultural variations in amount and complexity of the available language input. Understanding this simple fact still escapes current cognitive and linguistic theories. Recently, spectacular progress in the engineering science, notably, machine learning and wearable technology, offer the promise of revolutionizing the study of cognitive development. Machine learning offers powerful learning algorithms that can achieve human-like performance on many linguistic tasks. Wearable sensors can capture vast amounts of data, which enable the reconstruction of the sensory experience of infants in their natural environment. The project of 'reverse engineering' language development, i.e., of building an effective system that mimics infant's achievements appears therefore to be within reach. Here, we analyze the conditions under which such a project can contribute to our scientific understanding of early language development. We argue that instead of defining a sub-problem or simplifying the data, computational models should address the full complexity of the learning situation, and take as input the raw sensory signals available to infants. This implies that (1) accessible but privacy-preserving repositories of home data be setup and widely shared, and (2) models be evaluated at different linguistic levels through a benchmark of psycholinguist tests that can be passed by machines and humans alike, (3) linguistically and psychologically plausible learning architectures be scaled up to real data using probabilistic/optimization principles from machine learning. We discuss the feasibility of this approach and present preliminary results.

Key facts. Cited by 68 papers in the map (data through 14 Oct 2026). First posted on arXiv 29 Jul 2016.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 8; 2022: 7; 2023: 10; 2024: 11; 2025: 20; 2026: 12.

68 papers.

Sort:

By area:

  1. 2021Generative Spoken Language Modeling from Raw Audiocited by 340
  2. 2022What Artificial Neural Networks Can Tell Us About Human Language Acquisitioncited by 99
  3. 2025Findings of the BabyLM Challenge: Sample-Efficient Pretraining on Developmentally Plausible Corporacited by 88
  4. 2022Toward a realistic model of speech processing in the brain with self-supervised learningcited by 63
  5. 2023Call for Papers -- The BabyLM Challenge: Sample-efficient pretraining on a developmentally plausible corpuscited by 62
  6. 2025Embodied AI Agents: Modeling the Worldcited by 61
  7. 2021The paradox of the compositionality of natural language: a neural machine translation case studycited by 59
  8. 2025How Linguistics Learned to Stop Worrying and Love the Language Modelscited by 51
  9. 2023Language acquisition: do children and language models follow similar learning stages?cited by 41
  10. 2022Word Discovery in Visually Grounded, Self-Supervised Speech Modelscited by 37
  11. 2022Context Limitations Make Neural Language Models More Human-Likecited by 34
  12. 2022Self-supervised language learning from raw audio: Lessons from the Zero Resource Speech Challengecited by 34
38 more
  1. 2023BabySLM: language-acquisition-friendly benchmark of self-supervised spoken language modelscited by 29
  2. 2024Investigating Critical Period Effects in Language Acquisition through Neural Language Modelscited by 16
  3. 2022Evaluating context-invariance in unsupervised speech representationscited by 11
  4. 2024From Babble to Words: Pre-Training Language Models on Continuous Streams of Phonemescited by 11
  5. 2025Do Construction Distributions Shape Formal Language Learning In German BabyLMs?cited by 11
  6. 2026Why AI systems don't learn and what to do about it: Lessons on autonomous learning from cognitive sciencecited by 11
  7. 2025Developmentally-plausible Working Memory Shapes a Critical Period for Language Acquisitioncited by 10
  8. 2024A systematic framework for generating novel experimental hypotheses from language modelscited by 9
  9. 2021Do Acoustic Word Embeddings Capture Phonological Similarity? An Empirical Studycited by 8
  10. 2021How Familiar Does That Sound? Cross-Lingual Representational Similarity Analysis of Acoustic Word Embeddingscited by 8
  11. 2023On "Scientific Debt" in NLP: A Case for More Rigour in Language Model Pre-Training Researchcited by 7
  12. 2024From Form(s) to Meaning: Probing the Semantic Depths of Language Models Using Multisense Consistencycited by 7
  13. 2024Unsupervised Word Discovery: Boundary Detection with Clustering vs. Dynamic Programmingcited by 7
  14. 2023Pre-training LLMs using human-like development data corpuscited by 5
  15. 2025A Distributional Perspective on Word Learning in Neural Language Modelscited by 4
  16. 2025What do self-supervised speech models know about Dutch? Analyzing advantages of language-specific pre-trainingcited by 4
  17. 2025Unpacking Let Alone: Human-Scale Models Generalize to a Rare Construction in Form but not Meaningcited by 4
  18. 2025Should Top-Down Clustering Affect Boundaries in Unsupervised Word Discovery?cited by 4
  19. 2025Unsupervised lexicon learning from speech is limited by representations rather than clusteringcited by 4
  20. 2024Revisiting speech segmentation and lexicon learning with better featurescited by 3
  21. 2024A model of early word acquisition based on realistic-scale audiovisual naming eventscited by 3
  22. 2025Challenges in Automated Processing of Speech from Child Wearables: The Case of Voice Type Classifiercited by 3
  23. 2021Unsupervised Word Segmentation from Discrete Speech Units in Low-Resource Settingscited by 2
  24. 2022How Adults Understand What Young Children Saycited by 2
  25. 2023A framework for the emergence and analysis of language in social learning agentscited by 2
  26. 2023Compositional Learning of Visually-Grounded Concepts Using Reinforcementcited by 2
  27. 2023Audio-Visual Neural Syntax Acquisitioncited by 2
  28. 2025BabyLM's First Words: Word Segmentation as a Phonological Probing Taskcited by 2
  29. 2026Emergence of Phonemic, Syntactic, and Semantic Representations in Artificial Neural Networkscited by 2
  30. 2021Development of collective behavior in newborn artificial agentscited by 1
  31. 2023Does Vision Accelerate Hierarchical Generalization in Neural Language Learners?cited by 1
  32. 2023The Construction of Reality in an AI: A Reviewcited by 1
  33. 2024No Such Thing as a General Learner: Language models and their dual optimizationcited by 1
  34. 2025Scaling and context steer LLMs along the same computational path as the human braincited by 1
  35. 2025SpidR-Adapt: A Universal Speech Representation Model for Few-Shot Adaptationcited by 1
  36. 2026Computational modeling of early language learning from acoustic speech and audiovisual input without linguistic priorscited by 1
  37. 2026Tracking the emergence of linguistic structure in self-supervised models learning from speechcited by 1
  38. 2026The Evaluation Trap: Benchmark Design as Theoretical Commitmentcited by 1

50 most cited of 68 All 68 (JSON)