Our species' incredible capacity to quickly acquire words from 300 by age 2 to over 1, 000 by age 4 isn't fully understood. Some cognitive scientists and linguists have theorized that people are born with built-in expectations and logical constraints (约束) that make this possible. Now, however, machine-learning research is showing that preprogrammed assumptions aren't necessary to swiftly pick up word meanings from minimal data.
A team of scientists has successfully trained a basic artificial intelligence model to match images to words using just 61 hours of naturalistic footage (镜头) and sound-previously collected from a child named Sam in 2013 and 2014. Although it's a small slice of a child's life, it was apparently enough to prompt the AI to figure out what certain words mean.
The findings suggest that language acquisition could be simpler than previously thought. Maybe children "don't need a custom-built, high-class language-specific mechanism" to efficiently grasp word meanings, says Jessica Sullivan, an associate professor of psychology at Skidmore College. "This is a really beautiful study, " she says, because it offers evidence that simple information from a child's worldview is rich enough to kick-start pattern recognition and word comprehension.
The new study also demonstrates that it's possible for machines to learn similarly to the way that humans do. Large language models are trained on enormous amounts of data that can include billions and sometimes trillions of word combinations. Humans get by on orders of magnitude less information, says the paper's lead author Wai Keen Vong. With the right type of data, that gap between machine and human learning could narrow dramatically.
Yet additional study is necessary in certain aspects of the new research. For one, the scientists acknowledge that their findings don't prove how children acquire words. Moreover, the study only focused on recognizing the words for physical objects.
Still, it's a step toward a deeper understanding of our own mind, which can ultimately help us improve human education, says Eva Portelance, a computational linguistics researcher. She notes that AI research can also bring clarity to long-unanswered questions about ourselves. "We can use these models in a good way, to benefit science and society, " Portelance adds.
