analiza aiqbench
This study uses contrastive vision-language models trained on 2,441 hours of egocentric video from 48 children to test whether cross-situational learning explains early noun acquisition. Models learned object-label mappings, but performance depended heavily on internet-pretrained visual features, and the learned representations diverged from children's learning trajectories. For AI readers, the takeaway is that these models show the strategy is viable but not yet developmentally faithful, and that visual representation quality is a key bottleneck.
Scaling cross-situational word learning on children's naturalistic experiences
arXiv:2610.31842v1 Announce Type: new Abstract: How do children learn the meanings of the simple, concrete words that form a majority of their early vocabulary? Statistical information about many word meanings can be recovered from the gradual accumulation of information about the co-occurrence of words with their referents, a proposal known as ``cross-situational learning''. Contrastive vision--language models allow this learning strategy to be tested on egocentric video data capturing children's early real-life experiences with visual and linguistic inputs. Initial successes of this method on small datasets provide a proof-of-concept, but vision models struggle to learn robust visual representations when trained on these same egocentric videos. How dependent is cross-situational word learning performance on the quality of the model's visual representations? And can cross-situational models scale to larger and more diverse datasets? To address these questions, we trained models on the BabyView corpus, including 2,441 hours of longitudinal egocentric video from 48 children. Models trained on this dataset learned object--label mappings, but performance was far higher when they used internet-pretrained visual representations as opposed to when visual representations were learned solely from the developmental video data. Further, the majority of the learning signal was carried by a small proportion of utterances that described a visible referent. Models learned lexical representations that showed recognizable human-like semantic structure, but model performance showed substantially different trajectories over training experiences than those observed in children. Cross-situational learning is a viable word learning strategy for early noun vocabulary, but constructing developmentally plausible models will require understanding how to learn high-quality visual representations from naturalistic data.
Authors:Michael C. Frank, Alvin W. M. Tan, Khai Loong Aw, Robert Z. Sparks, Victor Moreno, Grace Keene-Lee, Meesha R. Ryan, Tarun Sepuri, Jane Yang, Virginia A. Marchman, Daniel L. K. Yamins, Bria Long
Abstract:How do children learn the meanings of the simple, concrete words that form a majority of their early vocabulary? Statistical information about many word meanings can be recovered from the gradual accumulation of information about the co-occurrence of words with their referents, a proposal known as ``cross-situational learning''. Contrastive vision--language models allow this learning strategy to be tested on egocentric video data capturing children's early real-life experiences with visual and linguistic inputs. Initial successes of this method on small datasets provide a proof-of-concept, but vision models struggle to learn robust visual representations when trained on these same egocentric videos. How dependent is cross-situational word learning performance on the quality of the model's visual representations? And can cross-situational models scale to larger and more diverse datasets? To address these questions, we trained models on the BabyView corpus, including 2,441 hours of longitudinal egocentric video from 48 children. Models trained on this dataset learned object--label mappings, but performance was far higher when they used internet-pretrained visual representations as opposed to when visual representations were learned solely from the developmental video data. Further, the majority of the learning signal was carried by a small proportion of utterances that described a visible referent. Models learned lexical representations that showed recognizable human-like semantic structure, but model performance showed substantially different trajectories over training experiences than those observed in children. Cross-situational learning is a viable word learning strategy for early noun vocabulary, but constructing developmentally plausible models will require understanding how to learn high-quality visual representations from naturalistic data.
Computation and Language (cs.CL)
arXiv:2610.31842 [cs.CL]
(or arXiv:2610.31842v1 [cs.CL] for this version)
https://doi.org/10.48550/arXiv.2610.31842 arXiv-issued DOI via DataCite (pending registration)
Text integral sub licența deschisă a publicației · 305 cuvinte