Human Inspired Progressive Alignment and Comparative Learning for Grounded Word Acquisition
This work addresses the challenge of efficient and continual word learning for AI systems, though it appears incremental as it builds on cognitive insights without claiming broad breakthroughs.
The paper tackles the problem of grounded word acquisition by developing a computational process inspired by human language acquisition, which enables models to learn words efficiently through comparative learning and representation-symbol mapping, with results showing potential for efficient continual learning in controlled experiments.
Human language acquisition is an efficient, supervised, and continual process. In this work, we took inspiration from how human babies acquire their first language, and developed a computational process for word acquisition through comparative learning. Motivated by cognitive findings, we generated a small dataset that enables the computation models to compare the similarities and differences of various attributes, learn to filter out and extract the common information for each shared linguistic label. We frame the acquisition of words as not only the information filtration process, but also as representation-symbol mapping. This procedure does not involve a fixed vocabulary size, nor a discriminative objective, and allows the models to continually learn more concepts efficiently. Our results in controlled experiments have shown the potential of this approach for efficient continual learning of grounded words.