The effect of lexicalization biases on cross-situational statistical learning of novel verbs

NR George, S Ciaccio, L Berry, DJ Weiss - Language and Cognition, 2024 - cambridge.org
Languages vary in the map** of relational terms onto events. For instance, English motion
descriptions favor manner (how something moves) verbs over path (where something move) …

Action recognition based on cross-situational action-object statistics

S Tsutsui, X Wang, G Weng, Y Zhang… - … on Development and …, 2022 - ieeexplore.ieee.org
Machine learning models of visual action recognition are typically trained and tested on data
from specific situations where actions are associated with certain objects. It is an open …

Cross‐situational learning from ambiguous egocentric input is a continuous process: Evidence using the human simulation paradigm

Y Zhang, D Yurovsky, C Yu - Cognitive science, 2021 - Wiley Online Library
Recent laboratory experiments have shown that both infant and adult learners can acquire
word‐referent map**s using cross‐situational statistics. The vast majority of the work on …

Laying the Foundation: Extracting Partial Meanings of Hard Nouns via Observational Contexts

K Boskovic, SH Suanda - Proceedings of the Annual Meeting of …, 2023 - escholarship.org
A key aspect of understanding how children learn the meanings of words involves
understanding how they mine different sources of information (eg, observational, linguistic) …

[PDF][PDF] Laying the Foundation: Extracting Partial Meanings of Hard Nouns via Observational

K Boskovic, SH Suanda - … of the Annual Meeting of the …, 2023 - comdev.media.uconn.edu
A key aspect of understanding how children learn the meanings of words involves
understanding how they mine different sources of information (eg, observational, linguistic) …

[BUCH][B] Rethinking the Role of Training Data for Computer Vision: Scientific Studies of Egocentric Vision

S Tsutsui - 2021 - search.proquest.com
The vast majority of work in computer vision focuses on proposing and applying new
machine learning models and algorithms for visual recognition. In contrast, relatively little …

Quantifying cross-situational statistics during parent-child toy play

E Cain, R Ryskin, C Yu - Proceedings of the Annual Meeting of the …, 2022 - escholarship.org
According to cross-situational learning, infants aggregate statistical information across
naming events to resolve ambiguous word-referent map**s. While lab experiments show …

When close isn't enough: Semantic similarity does not facilitate cross-situational word-learning

AS LaTourrette, C Yang, J Trueswell - Proceedings of the Annual …, 2022 - escholarship.org
Infants' earliest words are learned by observation of the referent world, but substantial
research suggests such learning is highly error-prone. However, recent work suggests that …