[ICML23] MEWL: Few-shot multimodal word learning with referential uncertainty

Abstract

Without explicit feedback, humans can rapidly learn the meaning of words. Children can acquire a new word after just a few passive exposures, a process known as fast mapping. This word learning capability is believed to be the most fundamental building block of multimodal understanding and reasoning. Despite recent advancements in multimodal learning, a systematic and rigorous evaluation is still missing for humanlike word learning in machines. To fill in this gap, we introduce the MachinE Word Learning (MEWL) benchmark to assess how machines learn word meaning in grounded visual scenes. MEWL covers human’s core cognitive toolkits in word learning: cross-situational reasoning, bootstrapping, and pragmatic learning. Specifically, MEWL is a few-shot benchmark suite consisting of nine tasks for probing various word learning capabilities. These tasks are carefully designed to be aligned with the children’s core abilities in word learning and echo the theories in the developmental literature. By evaluating multimodal and unimodal agents’ performance with a comparative analysis of human performance, we notice a sharp divergence in human and machine word learning. We further discuss these differences between humans and machines and call for human-like few-shot word learning in machines.

Type
Publication
In Proceedings of the International Conference on Machine Learning

Guangyuan Jiang
Guangyuan Jiang
Tong Class '20
Manjie Xu
Manjie Xu
MSc. '22, co-advised with Prof. Wei Liang

I focus on making my agents not too silly.

Shiji Xin
Shiji Xin
Turing Class '19
Wei Liang
Wei Liang
Professor
Yujia Peng
Yujia Peng
Assistant Professor
Chi Zhang
Chi Zhang
Research Scientist
Yixin Zhu
Yixin Zhu
Assistant Professor

I build humanlike AI.

Related