# A Language-agnostic Model of Child Language Acquisition

arXiv: https://arxiv.org/abs/2408.12254 · HTML: https://mlsanity.com/paper/2408.12254/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 2 of its 22 references that are in the map.
- First posted on arXiv 22 Aug 2024.

## Builds on (most cited first, 2 of 2)

- [A computational model of early language acquisition from audiovisual experiences of young infants](https://mlsanity.com/paper/1906.09832/) (2019)
- [Cross-linguistically Consistent Semantic and Syntactic Annotation of Child-directed Speech](https://mlsanity.com/paper/2109.10952/) (2021)

## Built on by (most cited first, 1 of 1)

- [Modelling Child Learning and Parsing of Long-range Syntactic Dependencies](https://mlsanity.com/paper/2503.12832/) (2025)

## Abstract (arXiv)

This work reimplements a recent semantic bootstrapping child-language acquisition model, which was originally designed for English, and trains it to learn a new language: Hebrew. The model learns from pairs of utterances and logical forms as meaning representations, and acquires both syntax and word meanings simultaneously. The results show that the model mostly transfers to Hebrew, but that a number of factors, including the richer morphology in Hebrew, makes the learning slower and less robust. This suggests that a clear direction for future work is to enable the model to leverage the similarities between different word forms.